Adapting to the “Open World”: The Utility of Hybrid Hierarchical Reinforcement Learning and Symbolic Planning (2024)

Pierrick Lorang and Helmut Horvath and Tobias Kietreiber and Patrik Zips and Clemens Heitzinger and Matthias Scheutz

Open-world robotic tasks such as autonomous driving pose significant challenges to robot control due to unknown and unpredictable events that disrupt task performance. Neural network-based reinforcement learning (RL) techniques (like DQN, PPO, SAC, etc.) struggle to adapt in large domains and suffer from catastrophic forgetting.

Dialogue-Based Task Instructions and Modifications for Industrial Robots (2024)

M. Scheutz and B. Oosterveld and J. Peterson and E. Wyss

Programming robots effectively remains a challenge for small businesses due to the high ongoing costs of robot programming experts. What is missing is a user-friendly software system such as a natural language-enabled cognitive assistant for developing robot programs that (1) does not require any particular training before it can be…

A Multi-Robot Architecture Framework for Effective Robot Teammates in Mixed-Initiative Teams (2024)

M. Scheutz and B. Oosterveld and J. Peterson and E. Wyss and E. Krause

Effective robotic teammates should be able to interact with humans in natural language about all task aspects, keep track of task and team states to coordinate their actions, and handle unexpected events autonomously. In this paper, we introduce a multi-robot architectural framework for effective robot teammates that allows robots to…

Robots That Perform Norm-Based Reference Resolution (2024)

Mitchell Abrams and Christopher Thierauf and Matthias Scheutz

Embodied agents must perform reference resolution if they are to achieve sufficient language understanding with humans. But sit- uated interaction introduces social norms, which are often overlooked yet critically need to be reasoned together with language to resolve ref- erences. To address this issue, we offer a novel normative-based…

Automating Dataset Production Using Generative Text and Image Models (2024)

Christopher Thierauf and Mitchell Abrams and Matthias Scheutz

Practical and ethical dataset collection remains a challenge blocking many empirical methods in natural language processing, resulting in a lack of benchmarks or data on which to test hypotheses. We propose a solution to some of these areas by presenting a pipeline to reduce the research burden of producing image and text datasets when…

Oh, Now I See What You Want: Learning Agent Models with Internal States from Observations (2024)

P. Lymperopoulos and M. Scheutz

Learning behavior models of other agents from observations is challenging because agents typically do not act based on observ- able states alone, but usually take their internal, for external agents unobservable, states such as desires, motivations, preferences, and others into account. We propose a novel approach to on- line agent model…

NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds (2024)

S. Goel and P. Lymperopoulos and Y. Wei and K. Chura and M. Scheutz and J. Sinapov

As AI agents leave the lab and venture into the real world as autonomous vehicles, delivery robots, and cooking robots, it is increasingly necessary to design and comprehensively evaluate algorithms that tackle the "open-world". To this end, we introduce NovelGym, a flexible and adaptable ecosystem designed to simulate gridworld…

Robots in healthcare as envisioned by care professional (2024)

F. Soljacic and T. Law and M. Chita-Tegmark and M.Scheutz

Caregiving in its best form addresses challenges in a multitude of dimensions of a person’s life: from physical to social-emotional and sometimes even existential dimensions such as issues surrounding life and death. In this study, we use semi-structured qualitative interviews administered to healthcare professionals with…

Towards Genuine Robot Teammates: Improving Human-Robot Team Performance Beyond Shared Mental Models with Proactivity (2024)

Gwendolyn Edgar and Ayca Aygun and Matthew McWilliams and Matthias Scheutz

Recent work in human-robot teaming has demonstrated that when robots build and maintain "shared mental models", the effectiveness of the whole human-robot team is overall better compared to a baseline with no shared mental models. In this work, we expand on this insight by introducing proactive behaviors in addition to shared mental…

A neurosymbolic cognitive architecture framework for handling novelties in open worlds (2024)

Shivam Goel and Panagiotis Lymperopoulos and Ravenna Thielstrom and Evan Krause and Patrick Feeney and Pierrick Lorang and Sarah Schneider and Yichen Wei and Eric Kildebeck and Stephen Goss and Michael C. Hughes and Liping Liu and Jivko Sinapov and Matthias Scheutz

"Open world" environments are those in which novel objects, agents, events, and more can appear and contradict previous understandings of the environment. This runs counter to the "closed world" assumption used in most AI research, where the environment is assumed to be fully understood and unchanging. This paper presents a novel…

Using Puzzle Video Games to Study Cognitive Processes in Human Insight and Creative Problem-Solving (2024)

Sarathy, Vasanth and Rabb, Nicholas and Kasenberg, Daniel and Scheutz, Matthias

Classical approaches to studying insight problem-solving typically use specialized problems (e.g., nine-dot problem, compound-remote associates task) as stimuli together with verbal reports from subjects during problem-solving to reveal their thought processes, possibly adding other task-related metrics such as completion rate and…

Assessment of Multiple Systemic Human Cognitive States using Pupillometry (2024)

Aygun, Ayca and Nguyen, Thuan and Scheutz, Matthias

How to best and robustly detect human systemic cognitive states like workload, sense of urgency, mind wandering, interference, and others is still an open question as the answer essentially depends both on the employed physiological measurements as well as the trained computational classification models. In this paper, we analyze data…

A Framework for Neurosymbolic Goal-Conditioned Continual Learning in Open World Environments (2024)

Pierrick Lorang and Shivam Goel and Yash Shukla and Patrik Zips and Matthias Scheutz

In dynamic open-world environments, agents continually face new challenges due to sudden and unpredictable novelties, hindering Task and Motion Planning (TAMP) in autonomous systems. We introduce a novel TAMP architecture that integrates symbolic planning with reinforcement learning to enable autonomous adaptation in such environments,…

Fixing symbolic plans with reinforcement learning in object-based action spaces (2024)

Christopher Thierauf and Matthias Scheutz

Reinforcement learning techniques are widely used when robots have to learn new tasks but they typically operate on action spaces defined by the joints of the robot. We present a contrasting approach where actions spaces are the trajectories of objects in the environment, requiring robots to discover events such as object changes and…

Self-Debugging Robots: Fault recovery through reasoning and planning (2024)

Christopher Thierauf and Matthias Scheutz

Unexpected perturbations in an open-world task environment can cause various types of faults and failures which have to be dealt with to ensure long-term autonomous operation. We present an inference framework that enables an autonomous robot to generate and test fault hypotheses in open- world scenarios. The tests involve different…

Trust Transfer in Robots between Task Environments (2024)

T. Law and M. Chita-Tegmark and M.Scheutz

Trust and capability transfer between tasks and environments is common in human-human interactions. For human-robot interac- tions it is unclear how a robot’s performance of a task in one envi- ronment affects humans predictions about the robot’s performance of another related or unrelated task in a different environment.

A Principled Approach to Model Validation in Domain Generalization (2023)

Lyu, Boyang and Nguyen, Thuan and Scheutz, Matthias and Ishwar, Prakash and Aeron, Shuchin

Domain generalization aims to learn a model with good generalization ability, that is, the learned model should not only perform well on several seen domains but also on unseen domains with different data distributions. State-of-the-art domain generalization methods typically train a representation function followed by a classifier…

NovelCraft: A Dataset for Novelty Detection and Discovery in Open Worlds (2023)

Patrick Feeney and Sarah Schneider and Panagiotis Lymperopoulos and Liping Liu and Matthias Scheutz and Michael C Hughes

In order for artificial agents to successfully perform tasks in changing environments, they must be able to both detect and adapt to novelty. However, visual novelty detection research often only evaluates on repurposed datasets such as CIFAR-10 originally intended for object classification, where images focus on one distinct, well-centered object.

Encoding Semantic Attributes - Towards Explainable AI in Industry (2023)

Sarah Schneider and Doris Antensteiner and Daniel Soukup and Matthias Scheutz

The transformation of industrial environments is progressing at a fast pace as more and more autonomous systems are installed and operated. Save and explainable AI algorithms are thus essen- tial, especially for collaborative interactive systems that operate in human spaces. We propose the “Semantic Encoder”, a 2D-vision based CNN model…

Barycentric-alignment and reconstruction loss minimization for domain generalization (2023)

Lyu, Boyang and Nguyen, Thuan and Ishwar, Prakash and Scheutz, Matthias and Aeron, Shuchin

This paper advances the theory and practice of Domain Generalization (DG) in machine learning. We consider the typical DG setting where the hypothesis is composed of a representation mapping followed by a labeling function. Within this setting, the majority of popular DG methods aim to jointly learn the representation and the labeling…

On the failure of Invariant Risk Minimization and an effective fix via classification error control (2023)

Nguyen, Thuan and Scheutz, Matthias and Aeron, Shuchin

Invariant Risk Minimization is a well-known Domain Generalization framework that has received much attention over the past few years. Invariant Risk Minimization is capable of learning domain-invariant features from multiple domains by finding representation features such that the optimal classifier on top of these features matches all training domains.

"Do this instead"-- Robots that Adequately Respond to Corrected Instructions (2023)

Christopher Thierauf and Ravenna Thielstrom and Bradley Oosterveld and Will Becker and Matthias Scheutz

Natural language instructions are effective at tasking autonomous robots and for teaching them new knowledge quickly. Yet, human instructors are not perfect and are likely to make mistakes at times, and will correct themselves when they notice errors in their own instructions. In this paper, we introduce a complete system for robot…

Investigating a Generalization of Probabilistic Material Implication and Bayesian Conditionals (2023)

Michael Jahn and Matthias Scheutz

Probabilistic "if A then B" rules are typically formalized as Bayesian conditionals P (B|A), as many (e.g., Pearl) have argued that Bayesian conditionals are the correct way to think about such rules. However, there are challenges with standard inferences such as modus ponens and modus tol- lens that might make probabilistic material…

Generalizing Probabilistic Material Implication and Bayesian Conditionals (2023)

Michael Jahn and Matthias Scheutz

Conditional statements in natural language of the form "if A then B" have multiple interpretations that require different logical treatment. In this paper, we focus on probabilistic "if A then B" rules that are given either a Bayesian interpretation via conditional probabilities P(B|A), or couched as probabilistic material implication.

Resilience for Goal-Based Agents: Formalism, Metrics, and Case Studies (2023)

Jennifer Leaf and Julie A. Adams and Matthias Scheutz and Michael A. Goodrich

Goal-based agents need to be resilient to perturbations in the world. Existing resilience definitions emphasize maintenance-type goals and, consequently, describe how well systems can recover and return to a desirable operating state after a perturbation. An alternative formulation of resilience is required for achievement-type goals…

Understanding the spirit of a norm: Challenges for norm-learning agents (2023)

Thomas Arnold and Matthias Scheutz

Social and moral norms are a fabric for holding human societies together and helping them to function. As such they will also become a means of evaluating the performance of future human-machine systems. While machine ethics has offered various approaches to endowing machines with normative competence, from the more logic-based to the…

Estimating Systemic Cognitive States from a Mixture of Physiological and Brain Signals (2023)

Matthias Scheutz and Shuchin Aeron and Ayca Aygun and J.P. de Ruiter and Sergio Fantini and Cristianne Fernandez and Zachary Haga and Thuan Nguyen and Boyang Lyu

We introduce an experimental and machine learning framework for investigating whether various human physiological parameters such as heart rate, respiration rate, blood pressure, and skin conductance, as well as brain activity inferred from functional near-infrared spectroscopy or electroencephalogram sufficient to isolate systemic…

Toward Competent Robot Apprentices: Enabling Proactive Troubleshooting in Collaborative Robots (2023)

Christopher Thierauf and Theresa Law and Tyler Frasca and Matthias Scheutz

For robots to become effective apprentices and collaborators, they must exhibit some level of autonomy, for example, recognizing failures and identifying ways to address them with the aid of their human teammates. In this systems paper, we present an integrated cognitive robotic architecture for a “robot apprentice” that is capable of…

Only Those Who Can Obey Can Disobey: the Intentional Implications of Artificial Agent Disobedience (2022)

Arnold, Thomas and Briggs, Gordon and Scheutz, Matthias

Recent attention has been brought to robots that “disobey” or so-called “rebel” agents that might reject commands. However, any discussion of autonomous agents that “disobey” risks engaging in a potentially hazardous conflation of simply non-conforming behavior with true disobedience. The goal of this paper is to articulate a sense of…

RAPid-Learn: A Framework for Learning to Recover for Handling Novelties in Open-World Environments (2022)

Shivam Goel and Yash Shukla and Vasanth Sarathy and Matthias Scheutz and Jivko Sinapov

We propose an integrated planning and learning approach that utilizes learning from failures and transferring knowledge over time to overcome novelty scenarios. The approach is more sample efficient in adapting to sudden and unknown changes (i.e., novelties) than the existing hybrid approaches. We showcase our results on a…

Keywords: reinforcement learning, planning, open-world AI, novelty accommodation

Speeding-up Continual Learning through Information Gains in Novel Experiences (2022)

Pierrick Lorang and Shivam Goel and Patrik Zips and Jivko Sinapov and Matthias Scheutz

We propose an integrated planning and learning approach that utilizes learning from failures and transferring knowledge over time to overcome novelty scenarios. The approach is more sample efficient in adapting to sudden and unknown changes (i.e., novelties) than the existing hybrid approaches. We showcase our results on a…

Keywords: reinforcement learning, planning, open-world AI, novelty accommodation

ACuTE: Automatic Curriculum Transfer from Simple to Complex Environments (2022)

Yash Shukla and Christopher Thierauf and Ramtin Hosseini and Gyan Tatiya and Jivko Sinapov

We formulate the curriculum transfer problem, in which the schema of a curriculum optimized in a simpler, easy-to-solve environment (e.g., a grid world) is transferred to a complex, realistic scenario (e.g., a physics-based robotics simulation or the real world). We present "ACuTE", Automatic Curriculum Transfer from Simple to Complex…

Keywords: reinforcement learning, curriculum learning

BIPLEX: Creative Problem-Solving by Planning for Experimentation (2022)

Vasanth Sarathy and Matthias Scheutz

We propose a novel problem solving algorithm called BIPLEX that involves hypothesis generation, experimentation, and outcome observation as part of the search for solutions. We introduce BIPLEX through various examples in a baking domain that demonstrate important features of the framework, including its representation of objects in…

Keywords: problem solving, open-world AI, planning, creativity

Trade-off between reconstruction loss and feature alignment for domain generalization (2022)

Thuan Nguyen, Boyang Lyu, Prakash Ishwar, Matthias Scheutz, Shuchin Aeron

To deal with challenging settings in domain generalization (DG) where both data and label of the unseen domain are not available at training time, the most common approach is to design the classifiers based on the domain-invariant representation features, i.e., the latent representations that are unchanged and transferable between domains.

Keywords: domain generalization

Joint covariate-alignment and concept-alignment: a framework for domain generalization (2022)

Thuan Nguyen, Boyang Lyu, Prakash Ishwar, Matthias Scheutz, Shuchin Aeron

In this paper, we propose a novel domain generalization (DG) framework based on a new upper bound to the risk on the unseen domain. Particularly, our framework proposes to jointly minimize both the covariate-shift as well as the concept-shift between the seen domains for a better performance on the unseen domain. While the proposed…

Keywords: domain generalization

Conditional entropy minimization principle for learning domain invariant representation features (2022)

Thuan Nguyen, Boyang Lyu, Prakash Ishwar, Matthias Scheutz, Shuchin Aeron

Invariance-principle-based methods such as Invariant Risk Minimization (IRM), have recently emerged as promising approaches for Domain Generalization (DG). Despite promising theory, such approaches fail in common classification tasks due to mixing of "true invariant features" and "spurious invariant features". To address this, we propose…

Keywords: domain generalization

A Framework for Robot Self-Assessment of Expected Task Performance (2022)

Tyler Frasca and Matthias Scheutz

We propose a self-assessment framework which enables a robot to estimate how well it will perform a known or novel task. The robot simulates the task by sampling performance distributions to generate a state distribution of possible outcomes and determines 1) the likelihood of success, 2) the most probable failure location, and 3) the…

Keywords: self-assessment, diarc, Human-Robot Interaction

Transparency through Explanations and Justifications in Human-Robot Task-Based Communications (2022)

Scheutz, Matthias and Thielstrom, Ravenna and Abrams, Mitchell

Transparent task-based communication between human instructors and robot instructees requires robots to be able to determine whether a human instruction can and should be carried out, i.e., whether the human is authorized, and whether the robot can and should do it. If the instruction is not appropriate, the robot needs to be able to…

Keywords: human-robot interaction, transparency, explanation, justification

Social Norms Guide Reference Resolution (2022)

Abrams, Mitchell and Scheutz, Matthias

Humans use natural language, vision, and con- text to resolve referents in their environment. While some situated reference resolution is triv- ial, ambiguous cases arise when the language is underspecified or there are multiple candidate referents. This study investigates how prag- matic modulators external to the linguistic con- tent…

Keywords: nlp, social norms, reference resolution

Analysis of the Future Potential of Autoencoders in Industrial Defect Detection (2022)

Sarah Schneider and Doris Antensteiner and Daniel Soukup and Matthias Scheutz

We investigated the anomaly detection behaviour of three convolutional autoencoder types - a "standard” convolutional autoencoder (CAE), a variational convolutional autoencoder (VAE) and an adversarial convolutional autoencoder (AAE) - by applying them to different visual anomaly detection scenarios. First, we utilized our three…

Keywords: vision, anomaly detection, defect detection

Autoencoders - A Comparative Analysis in the Realm of Anomaly Detection (2022)

Sarah Schneider and Doris Antensteiner and Daniel Soukup and Matthias Scheutz

We applied convolutional versions of a "standard" autoencoder (CAE), a variational autoencoder (VAE) and an adversarial autoencoder (AAE) to two different publicly available datasets and compared their anomaly detection performances. We used the MNIST dataset as a simple anomaly detection scenario. The CIFAR10 dataset was used to examine…

Keywords: vision, anomaly detection

An Architecture for Novelty Handling in a Multi-Agent Stochastic Environment: Case Study in Open-World Monopoly. (2022)

Thai, Tung and Shen, Ming and Varshney, Neeraj and Gopalakrishnan, Sriram and Soni, Utkarsh and Baral, Chitta and Sinapov, Jivko and Scheutz, Matthias

The ability of AI agents and architectures to detect and adapt to sudden changes in their environments remains an outstand- ing challenge. In the context of multi-agent games, the agent may face novel situations where the rules of the game, the available actions, the environment dynamics, the behavior of other agents, as well as the…

Cognitive Workload Assessment via Eye Gaze and EEG in an Interactive Multi-Modal Driving Task (2022)

Aygun, Ayca and Lyu, Boyang and Nguyen, Thuan and Haga, Zachary and Aeron, Shuchin and Scheutz, Matthias

Assessing cognitive workload of human interactants in mixed initiative teams is a critical capability for autonomous interactive systems to enable adaptations that improve team performance. Yet, it is still unclear, due to diverg ing evidence, which sensing modality might work best for the determination of human workload. In this paper,…

Keywords: workload detection, cognitive load, EEG, eye gaze, driving experiment

Investigating Methods for Cognitive Workload Estimation for Assistive Robots (2022)

Aygun, Ayca and Nguyen, Thuan and Haga, Zachary and Aeron, Shuchin and Scheutz, Matthias

We analyzed and modeled data from a multi-modal simulated driving study specifically designed to evaluate different levels of cognitive workload induced by various secondary tasks such as dialogue interactions and braking events in addition to the primary driving task. Our analyses provide evidence for eye gaze being the best…

Keywords: workload detection, cognitive load, EEG, eye gaze, driving experiment

Extended Norms: Locating Accountable Decision-making In Contexts of Human-Robot Interaction (2022)

Arnold, Thomas and Scheutz, Matthias

Machine ethics has sought to establish how autonomous systems could make ethically appropriate decisions in the world. While mere statistical machine learning approaches have focused on learning human preferences from observations and attempted actions, hybrid approaches to machine ethics attempt to provide more explicit guidance for…

Cognitive Contagion: How to model (and potentially counter) the spread of fake news (2022)

Rabb, Nicholas and Cowen, Lenore and de Ruiter, Jan P. and Scheutz, Matthias

Understanding the spread of false or dangerous beliefs—often called misinformation or disinformation—through a population has never seemed so urgent. We introduce a cognitive cascade model that combines a network science belief cascade approach with an internal cognitive model of the individual agents as in opinion diffusion models as a…

Examining attachment to robots: Benefits, challenges, and alternatives (2022)

Law, Theresa and Chita-Tegmark, Meia and Rabb, Nicholas,and Scheutz, Matthias

Potential applications of robots in private and public human spaces have prompted the design of so-called “social robots” that can interact with humans in social settings and potentially cause humans to attach to the robots. The focus of this article is an analysis of possible benefits and challenges arising from such human-robot…

Keywords: Attachment, unidirectional emotional bonds, relationships with robots

Metrics for Robot Proficiency Self-Assessment and Communication of Proficiency in Human-Robot Teams (2022)

Norton, Adam and Admoni, Henry and Crandall, Jacob and Fitzgerald, Tesca and Gautam, Alvika and Goodrich, Michael and Saretsky, Amy and Scheutz, Matthias and Simmons, Reid and Steinfeld, Aaron and Yanco, Holly

As development of robots with the ability to self-assess their proficiency for accomplishing tasks continues to grow, metrics are needed to evaluate the characteristics and performance of these robot systems and their interactions with humans. This proficiency-based human-robot interaction (HRI) use case can occur before, during, or…

A Novel Architectural Method for Producing Dynamic Gaze Behavior in Human-Robot Interactions (2022)

Briggs, Gordon and Chita-Tegmark, Meia and Krause, Evan and Bridewell, Will and Bello, Paul and Scheutz, Matthias

We present a novel integration between a computational framework for modeling attention-driven perception and cognition (ARCADIA) with a cognitive robotic architecture (DIARC), demonstrating how this integration can be used to drive the gaze behavior of a robotic platform. Although some previous approaches to controlling gaze behavior in…

NovelGridworlds: A Benchmark Environment for Detecting and Adapting to Novelties in Open Worlds (2021)

Goel, Shivam and Tatiya, Gyan and Scheutz, Matthias and Sinapov, Jivko

As researchers are developing methods for detecting and accommo- dating novelties that will make AI agents more robust to unknown sudden changes in the “open worlds”, there is an increasing need for benchmark environments that allow for the systematic evalua- tions of the proposed AI techniques. We present “NovelGridworlds”, an OpenAI…

Integrating Planning, Execution and Monitoring in the presence of Open World Novelties: Case Study of an Open World Monopoly Solver (2021)

Gopalakrishnan, Sriram and Soni, Utkarsh and Thai, Tung and Lymperopoulos, Panagiotis and Scheutz, Matthias and Kambhampati, Subbarao

The game of monopoly is an adversarial multi-agent domain where there is no fixed goal other than to be the last player solvent, There are useful subgoals like monopolizing sets of properties, and developing them. There is also a lot of randomness from dice rolls, card-draws, and adversaries' strategies. This unpredictability is made…

May Machines Take Lives to Save Lives? Human Perceptions of Autonomous Robots (with the Capacity to Kill) (2021)

Malle, Bertram and Scheutz, Matthias

In the future, artificial agents are likely to make life-and-death decisions about humans. Ordinary people are the likely arbiters of whether these decisions are morally acceptable. We summarize research on how ordinary people evaluate artificial (compared to human) agents that make life-and-death decisions. The results suggest that many…

Keywords: moral psychology, moral dilemmas, human-robot interaction, blame, moral justifications

Mind Readers and Mind Users: The Utility of Sharing Architectural Components across Multiple Robots (2021)

Matthias Scheutz

We introduce the concept of architectural "component-sharing" as the basis for "knowledge sharing" in hive minds, e.g., a system multiple robots connecting by shared components in their control architectures. We discuss the architectural requirements and demonstrate the utility for multi-robot instruction and automatic reasoning across…

Blaming the Reluctant Robot: Parallel Blame Judgments for Robots in Moral Dilemmas across U.S. and Japan (2021)

Takanori Komatsu and Bertram F. Malle and Matthias Scheutz

We present two experiments comparing moral judgments of robots among Japanese and U.S. participants. The experiments assess multiple ways in which cross-cultural differences in moral evaluations may emerge: in the willingness to treat robots as moral agents; the norms that are imposed on robots' behaviors; and the degree of blame that…

Autonomy Reconsidered: Toward Developing Multi-Agent Systems (2021)

Michael Goodrich and Julie Adams and Matthias Scheutz

An agent’s autonomy can be viewed as the set of physically and computationally grounded algorithms that can be performed by the agent. This view leads to two useful notions related to autonomy: behav- ior potential and success potential, which can be used to measure of how well an agent fulfills its potential, call fulfillment.

Evaluating Task-General Resilience Mechanisms in a Multi-Robot Team Task (2021)

James Staley and Matthias Scheutz

Real-word intelligent agents must be able to detect sudden and unexpected changes to their task environment and effectively respond to those changes in order to function properly in the long term. We thus isolate a set of perturbations that agents ought to address and demonstrate how task-agnostic perturbation detection and mitigation…

Parents Adaptively Use Anaphora During Parent-child Social Interaction (2021)

Jasmine Falk and Yayun Zhang and Matthias Scheutz and Chen Yu

Anaphora, a ubiquitous feature of natural language, poses a particular challenge to young children as they first learn lan- guage due to its referential ambiguity. Through an eye-tracking study in a naturalistic free-play context, we examine the strategies that parents employ to calibrate their use of anaphora to their child's linguistic development level.

How Should Agents Ask Questions For Situated Learning? An Annotated Dialogue Corpus (2021)

Felix Gervits and Anthony Roque and Gordon Briggs and Matthias Scheutz and Matthew Marge

We present the Human-Robot Dialogue Learning (HuRDL) Corpus, a novel dialogue corpus collected in an online interactive virtual environment in which human participants play the role of a robot performing a collaborative tool-organization task. We describe the corpus data and a corresponding annotation scheme to offer insight into the…

Decision-Theoretic Question Generation for Situated Reference Resolution: An Empirical Study and Computational Model (2021)

Felix Gervits and Gordon Briggs and Anthony Roque and Genki Kadomatsu and Dean Thurston and Matthew Marge and Matthias Scheutz

We analyzed dialogue data from an interactive study in which participants controlled a virtual robot tasked with organizing a set of tools while engaging in dialogue with a live, remote experimenter. We discovered a number of novel results, including the distribution of question types used to resolve ambiguity and the influence of…

Assistive robots for the social management of health: A framework for robot design and human-robot interaction research (2021)

Meia Chita-Tegmark and Matthias Scheutz

We propose a function framework for robots assisting with the social management of health, and conduct a literature review on mediator robots.

Keywords: hri

A Novelty-Centric Agent Architecture for Changing Worlds (2021)

Faizan Muhammad and Vasanth Sarathy and Gyan Tatiya and Shivam Goel and Saurav Gyawali and Mateo Guaman and Jivko Sinapov and Matthias Scheutz

Open-world AI requires artificial agents to cope with novelties that arise during task performance, i.e., they must (1) detect novelties, (2) characterize them, in order to (3) accommodate them, especially in cases where sudden changes to the environment make task accomplishment impossible without utilizing the novelty. We present a…

Can you trust your trust measure? (2021)

Meia Chita-Tegmark and Theresa Law and Nicholas Rabb and Matthias Scheutz

We examined how typical trust questionnaires used in HRI were affected when participants had the option to choose "not applicable to this robot" or "not applicable to robots in general" for any given question. We found that participants do make use of these choices, particularly for questionnaires that get at social dimensions of trust.

Keywords: Trust, trust measurement, questionnaire design

SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning (2021)

Vasanth Sarathy and Daniel Kasenberg and Shivam Goel and Jivko Sinapov and Matthias Scheutz

We developed a new integrated planning and reinforcement learning framework called SPOTTER to enable agents to solve problems unsolvable from their initial planning domain.

Robot Development and Path Planning for Indoor Ultraviolet Light Disinfection (2021)

Jonathan Conroy and Christopher Thierauf and Parker Rule and Evan Krause and Hugo Akitaya and Andrei Gonczi and Matias Korman and Matthias Scheutz

We demonstrate in simulations the efficacy of a UVC irradiation algorithm and show a prototypical run of the autonomous integrated robotic system

Keywords: robotics, healthcare

Explaining In Time: Meeting Interactive Standards of Explanation for Robotic Systems (2021)

Thomas Arnold and Daniel Kasenberg and Matthias Scheutz

In this paper we show how a social robot's actions can face explanatory demands for how it came to act on its decision, what goals, tasks, or purposes its design had those actions pursue, and what norms or social constraints the system recognizes in the course of its action. As a result, we argue that explanations for social robots will…

Keywords: hri, ethics, moral, arch, dia, prag, comm

Enabling Fast Instruction-Based Modification of Learned Robot Skills (2021)

Tyler Frasca and Bradley Oosterveld and Meia Chita-Tegmark and Matthias Scheutz

We develop a framework to allow humans to modify a robot's learned skills through natural language instructions. Additionally, we provide an online study showing that participants would prefer to know they can modify a robot's skills primarily through natural language.

Keywords: Instruction Based Task Learning, Human-Robot Interaction

Why and how robots should say 'no' (2021)

Gordon Briggs and Tom Williams and Ryan Blake Jackson and Matthias Scheutz

Language-enabled robots with moral reasoning capabilities will inevitably face situations in which they have to respond to human commands that might violate normative principles and could cause harm to humans. We present research in both engineering language-enabled robots that can engage in rudimentary rejection dialogues, as well as…

An Attachment Framework for Human-Robot Interaction (2021)

Nicholas Rabb and Theresa Law and Meia Chita-Tegmark and Matthias Scheutz

Attachment theory is a research area in psychology that has enjoyed decades of successful study, and has subsequently become explored in realms beyond that of the original infant-caregiver bonds. We discuss attachment in Human-Robot Interaction (HRI) using a notion of weak attachment and strong attachment before setting both as distinct…

Keywords: Attachment, framework, attachment theory

EnviRobots: How Human–Robot Interaction Can Facilitate Sustainable Behavior (2021)

Clara Scheutz and Theresa Law and Matthias Scheutz

We first present a literature review on the current state of social robots that are used to encourage sustainable behaviors. We next present eight hypothetical scenarios which are informed by the progress that has already been made in social robots in sustainability, as well as notable gaps where further environmental psychological…

Keywords: Environment, sustainability, sustainable behavior, environmental psychology

Spoken language interaction with robots: Recommendations for future research (2021)

Marge, Matthew and Espy-Wilson, Carol and Ward, Nigel G. and Alwan, Abeer and Artzi, Yoav and Bansal, Mohit and Blankenship, Gil and Chai, Joyce and Daumé, Hal and Dey, Debadeepta and Harper, Mary and Howard, Thomas and Kennington, Casey and Kruijff-Korbayová, Ivana and Manocha, Dinesh and Matuszek, Cynthia and Mead, Ross and Mooney, Raymond and Moore, Roger K. and Ostendorf, Mari and Pon-Barry, Heather and Rudnicky, Alexander I. and Scheutz, Mattias and St. Aman, Robert and Sun, Tong and Tellex, Stefanie and Traum, David and Yu, Zhou

With robotics rapidly advancing, more effective human–robot interaction is increasingly needed to realize the full potential of robots for society. While spoken language must be part of the solution, our ability to provide spoken language interaction capabilities is still very limited. In this article, based on the report of an…

Robot Planning with Mental Models of Co-Present Humans (2020)

Buckingham, David and Chita-Tegmark, Meia and Scheutz, Matthias

Robots are increasingly embedded in human societies where they encounter human collaborators, potential adversaries, and even uninvolved by-standers. Such robots must plan to accomplish joint goals with teammates while avoiding interference from competitors, possibly utilizing bystanders to advance the robot’s goals. We propose a…

Models of Cross-Situational and Crossmodal Word Learning in Task-Oriented Scenarios (2020)

Krenn, Brigitte and Sadeghi, Sepideh and Neubarth, Friedrich and Gross, Stephanie and Trapp, Martin and Scheutz, Matthias

We present two related but different cross-situational and crossmodal models of incremental word learning. Model 1 is a Bayesian approach for co-learning object-word mappings and referential intention which allows for incremental learning from only a few situations where the display of referents to the learning system is systematically varied.

The Interplay between Emotional Intelligence, Trust, and Gender in human-robot interaction (2020)

Theresa Law and Meia Chita-Tegmark and Matthias Scheutz

Through a series of vignette-style studies, we explored how a robot's gender, level of emotional intelligence, and level of trustworthiness interact to affect a person's trust in a robot.

Keywords: Trust, emotional intelligence, gender, robot gender

Trust: Recent Concepts and Evaluations in Human-Robot Interaction (2020)

Theresa Law and Matthias Scheutz

We present a survey of the current empirical literature on trust in HRI. We categorize trust as being either performance-based or relation-based. We compare how each paper in our survey uses performance- or relation-based trust in their trust definitions, research questions, and trust measurements.

Keywords: trust, literature review, performance trust, relational trust

Toward Genuine Robot Teammates: Improving Human-Robot Team Performance Using Robot Shared Mental Models (2020)

Felix Gervits and Dean Thurston and Ravenna Thielstrom and Terry Fong and Quinn Pham and Matthias Scheutz

We implemented a computational framework for Shared Mental Models (SMMs) in which robots use a distributed knowledgebase to coordinate activity. We also built a novel system connecting the robotic architecture, DIARC, to the 3D simulation environment, Unity, to serve as an evaluation platform for the framework implementation.

Keywords: hri, mixed, multi, arch

Emotion Expression in a Socially Assistive Robot for Persons with Parkinson's disease (2020)

Andrew P. Valenti and Avram Bock and Meia Chita-Tegmark and Michael Gold and Matthias Scheutz

Emotions are crucial for human social interactions and thus people communicate emotions through a variety of modalities: kinesthetic (through facial expressions, body posture and gestures), auditory (the acoustic features of speech) and semantic (the content of what they say). Sometimes however, communication channels for certain…

Keywords: hri, learn, neural

It's About Time: Turn-Entry Timing for Situated Human-Robot Dialogue (2020)

Felix Gervits and Ravenna Thielstrom and Antonio Roque and Matthias Scheutz

We introduce a computational framework, based on work from psycholinguistics, which is aimed at achieving proper turn-entry timing for situated agents. We demonstrate that: 1) the system is superior to a non-incremental system in terms of faster responses, reduced gap between turns, and the ability to perform actions early, 2) the system…

Keywords: hri, arch, dia, comm

Let's do that first! A Comparative Analysis of Instruction-Giving in Human-Human and Human-Robot Situated Dialogue (2020)

Matthew Marge and Felix Gervits and Gordon Briggs and Matthias Scheutz and Antonio Roque

We present an annotation scheme that captures the structure and content of task intentions in situated dialogue where humans instruct robots to perform novel action sequences and sub-sequences. This representation identifies patterns and structural differences between human-human and human-robot communications. We find that humans engage…

Keywords: hri, dia, comm

Developing a corpus of indirect speech act schemas (2020)

Antonio Roque and Alexander Tsuetaki and Vasanth Sarathy and Matthias Scheutz

Resolving Indirect Speech Acts (ISAs), in which the intended meaning of an utterance is not identical to its literal meaning, is essential to enabling the participation of intelligent systems in peoples’ everyday lives. Especially challenging are those cases in which the interpretation of such ISAs depends on context. To test a system’s…

Keywords: hri, dia, comm

Simultaneous Representation of Knowledge and Belief for Epistemic Planning with Belief Revision (2020)

David Buckingham and Daniel Kasenberg and Matthias Scheutz

We propose a novel approach to the problem of false belief revision in epistemic planning. Our state representations are pointed Kripke models with two binary relations over possible worlds: one representing agents' necessarily true knowledge, and one representing agents' possibly false beliefs. State transition functions maintain S5n…

Keywords: hri, multi

Generating Explanations for Temporal Logic Planner Decisions (2020)

Daniel Kasenberg and Ravenna Thielstrom and Matthias Scheutz

Although temporal logic has been touted as a fruitful language for specifying interpretable agent objectives, there has been little emphasis on generating explanations for agents with temporal logic objectives. In this paper, we develop an approach to generating explanations for the behavior of agents planning with several temporal logic objectives.

Keywords: moral, comm

"Can you Do This?" Self-Assessment Dialogues with Autonomous Robots Before, During, and After a Mission (2020)

Tyler Frasca and Ravenna Thielstrom and Evan Krause and Matthias Scheutz

The sophisticated capabilities of autonomous robots can be difficult for humans to understand the robot's expected performance. In this papaer, we present a robot self assessment framework which enables a robot to assess its expected task performance before, during, and after execution. We demonstrate the framework in the DIARC cognitive-robotic architecture.

Keywords: Robot-Self Task Performance Assessment, Human-Robot Interaction

Going Cognitive: A Demonstration of the Utility of Task-General Cognitive Architectures for Adaptive Robotic Task Performance (2020)

Tyler Frasca and Zhao Han and Jordan Allspaw and Holly Yanco and Matthias Scheutz

A main advantage of cognitive architectures over specialized robotic architectures is that they are task-general and can learn new tasks online. In this paper, we provide empirical evidence to for this claim, by directly comparing a high-performing custom robotic architecture developed for the standardized robotic "FetchIt!" challenge…

Keywords: Cognitive-Robotic Architectures, Human-Robot Interaction, FetchIt! Robotics Challenge

A Multi-level Framework for Understanding Spoken Dialogue Using Topic Detection (2020)

Andrew Valenti and Ravenna Thielstrom and Michael Gold and Felix Gervits and Matthias Scheutz

Spoken Dialogue Systems (SDS) are used to interact with intelligent agents through natu- ral language. Speech processing errors may cause the system to fail to generate an ap- propriate response. In this paper, we present a novel framework for understanding spoken dialogue in which utterance analysis is esca- lated through a multi-level…

Keywords: hri, dia, speech

Generating Explanations of Action Failures in a Cognitive Robotic Architecture (2020)

Ravenna Thielstrom and Antonio Roque and Meia Chita-Tegmark and Matthias Scheutz

We describe an approach to generating explanations about why robot actions fail, focusing on the considerations of robots that are run by cognitive robotic architectures. We define a set of Failure Types and Explanation Templates, motivating them by the needs and constraints of cognitive architectures that use action scripts and…

Keywords: hri, dia, prag

Reasoning Requirements for Indirect Speech Act Interpretation (2020)

Vasanth Sarathy and Alexander Tsuetaki and Antonio Roque and Matthias Scheutz

We perform a corpus analysis to develop a representation of the knowledge and reasoning used to interpret indirect speech acts. An indirect speech act (ISA) is an utterance whose intended meaning is different from its literal meaning. We focus on those speech acts in which slight changes in situational or contextual information can…

Keywords: hri, prag

A touching connection: How observing robotic touch can affect human trust in a robot (2020)

Theresa Law and Bertram Malle and Matthias Scheutz

Through a series of online studies, we explored how a observing a robotic touch to the shoulder affects people's trust in the robot and perception of the robot's behavior.

Keywords: Trust, touch, social touch

Mate or weight? Perceptions of a robot as agent or object in a creative problem solving task (2020)

Theresa Law and Daniel Kasenberg and Matthias Scheutz

In this experiment we examine the extent to which this agency ascription can be overcome when required for completion of a task. In particular, we construct an “escape room”-like task, completion of which requires the participant to treat a robot as an object to be physically manipulated rather than an agent with which to be interacted.

Keywords: Creative problem solving, perceptions of agency, escape room

Challenges in Designing a Fully Autonomous Socially Assistive Robot for People with Parkinson's Disease (2020)

J.R. Wilson and L. Tickle-Degnen and M. Scheutz

Assistive robots are becoming an increasingly important application platform for research in robotics, AI, and HRI, as there is a pressing need to develop systems that support the elderly and people with disabilities, with a clear path to market. Yet, what remains unclear is whether current autonomous systems are already up to the task…

Requirements for an Artificial Agent with Norm Competence (2019)

Malle, Bertram F. and Bello, Paul and Scheutz, Matthias

Human behavior is frequently guided by social and moral norms, and no human community can exist without norms. Robots that enter human societies must therefore behave in norm-conforming ways as well. However, currently there is no solid cognitive or computational model available of how human norms are represented, activated, and learned.

Acquisition of Word-Object Associations from Human-Robot and Human-Human Dialogues (2019)

Sadeghi, Sepideh and Oosterveld, Brad and Krause, Evan and Scheutz, Matthias

Past work on acquisition of word-object associations in robots has focused on either fast instruction-based methods which accept highly constrained input or gradual cross-situational learning methods, but not a mixture of both. In this paper, we present an integrated robotic system which allows for a combination of these methods to…

Functional Knowledge Requirements for Interactive Task Learning (2019)

Wray, Robert E. III and Taatgen, Niels A. and Lebiere, Christian and Pastra, Katerina and Pirolli, Peter and Rosenbloom, Paul S. and Scheutz, Matthias and Stewart, Terrence C. and Janet Wiles

What knowledge needs to be learned to acquire a novel task? What background knowledge does an agent need to use newly acquired knowledge effectively? This chapter considers the functional roles of knowledge in task learning. These roles of knowledge span interaction with other entities and the environment and core functional capabilities…

Ethical Aspects and Challenges for Interactive Task Learning (2019)

Scheutz, Matthias

As with all transformative technologies, humanity needs to analyze the ethical chal- lenges and potential impacts associated with implementation. This chapter explores fundamental questions that pertain to interactive task learning (ITL): What is being taught and what are the associated risks? What are the dynamics of human–machine…

Dempster-shafer theoretic resolution of referential ambiguity (2019)

Williams, Tom and Yazdani, Fereshta and Suresh, Prasanth and Scheutz, Matthias and Beetz, Michael

Robots designed to interact with humans in realistic environments must be able to handle uncertainty with respect to the identities and properties of the people, places, and things found in their environments. When humans refer to these entities using under-specified language, robots must often generate clarification requests to…

A Classification-Based Approach to Automating Human-Robot Dialogue (2019)

Felix Gervits and Anton Leuski and Claire Bonial and Carla Gordon and David Traum

We present a dialogue system based on statistical classification which was used to automate human-robot dialogue in a collaborative navigation domain. The classifier was trained on a small corpus of multi-floor Wizard-of-Oz dialogue. We evaluate our system on several sets of source data from the corpus and find that response accuracy is…

Keywords: hri, dia, learn

Learning Context-Sensitive Norms under Uncertainty (2019)

Vasanth Sarathy

Norms and conventions play a central role in maintaining social order in multi-agent societies [2, 5]. I study the problem of how these norms and conventions can be learned from observation of heterogeneous sources, under conditions of uncertainty. This is necessary as it is not enough to simply hard code a set of norms into a new agent…

Keywords: ethics, multi

Towards the Engineering of Virtuous Machines (2019)

Naveen Sundar Govindarajulu and Selmer Bringsjord and Rikhiya Ghosh and Vasanth Sarathy

In this paper, we introduce a formalism for virtue ethics using the language of deontic cognitive event calculus (DCEC*).

Keywords: ethics, moral

On Resolving Ambiguous Anaphoric Expressions in Imperative Discourse (2019)

Vasanth Sarathy and Matthias Scheutz

In this paper we describe situated anaphora resolution problems, a class of anaphora resolution problems which depends on tracking the evolving state of the world as the discourse progresses, and in which commonsense knowledge about the world, communicative interactants and community expectations play a role.

Keywords: prag, dia

When Exceptions are the Norm: Exploring the Role of Consent in HRI (2019)

Vasanth Sarathy and Thomas Arnold and Matthias Scheutz

In this paper, we propose consent as a distinct, critical area for HRI research. By sorting various kinds of consent through social and legal doctrine, we delineate empirical and technical questions to meet consent challenges faced in major application domains and robotic roles.

Keywords: ethics, hri, moral, arch

Merging Representation and Management of Physical and Spoken Action (2019)

Charles Threlkeld and Matthias Scheutz

Effective human-robot interaction (HRI) is a critical requirement for current and future space operations. However, given the limitations of autonomous technologies, robots are not yet capable of coordinating with human crew as peers under real-world mission constraints. Due to the complexity inherent in space robotics operations, it is…

An Overview of the Distributed Integrated Affect and Reflection Cognitive DIARC Architecture (2019)

Matthias Scheutz and Thomas Williams and Evan Krause and Brley Oosterveld and Vasanth Sarathy and Tyler Frasca

Different from other cognitive architectures like SOAR or ACT-R, DIARC is an intrinsically component-based distributed architecture scheme that can be instantiated in many different ways. Moreover, DIARC has several distinguishing features, such as affect processing and deep natural language integration, is open-world and multi-agent…

Learning How to Behave: Moral Competence for Social Robots (2019)

Malle, Bertram and Scheutz, Matthias

We describe a theoretical framework and recent research on one key aspect of robot ethics: the development and implementation of a robot’s moral competence. As autonomous machines take on increasingly social roles in human communities, these machines need to have some level of moral competence to ensure safety, acceptance, and justified trust.

When your face and tone of voice don't say it all: Inferring emotional state from word semantics and conversational topics (2019)

Andrew P. Valenti and Meia Chita-Tegmark and Theresa Law and Alexander W. Bock and Bradley Oosterveld and Matthias Scheutz

We describe the initial development stage of a cognitive robotic architecture that can assist the communication and detection of emotions in interactions where some modalities are totally or partially compromised. We hypothesize that the distribution of topics extracted from each sentence, that is part of a collection of written text…

Keywords: hri, learn, neural

Using topic modeling to infer the emotional state of people living with Parkinson's disease (2019)

Andrew P. Valenti and Meia Chita-Tegmark and Linda Tickle-Degnen and Alexander W. Bock and Matthias J. Scheutz

We describe the initial development stage of a robot companion that can assist the communication and detection of emotions in interactions where some modalities are totally or partially compromised. Such is the case for people living with Parkinson's disease. Our approach is based on a Latent Dirichlet Allocation topic model as a…

Keywords: hri, learn, neural

Generating Justifications for Norm-Related Agent Decisions (2019)

Daniel Kasenberg and Antonio Roque and Ravenna Thielstrom and Meia Chita-Tegmark and Matthias Scheutz

We present an approach to generating natural language justifications of decisions derived from norm-based reasoning. Assuming an agent which maximally satisfies a set of rules specified in an object-oriented temporal logic, the user can ask factual questions (about the agent's rules, actions, and the extent to which the agent violated…

Keywords: moral, comm

Engaging in Dialogue about an Agent's Norms and Behaviors (2019)

Daniel Kasenberg and Antonio Roque and Ravenna Thielstrom and Matthias Scheutz

We present a set of capabilities allowing an agent planning with moral and social norms represented in temporal logic to respond to queries about its norms and behaviors in natural language, and for the human user to add and remove norms directly in natural language. The user may also pose hypothetical modifications to the agent's norms…

Keywords: moral, comm

Effects of Assistive Robot Behavior on Impressions of Patient Psychological Attributes: Vignette-Based Human-Robot Interaction Study (2019)

Meia Chita-Tegmark and Janet M Ackerman and Matthias Scheutz

In this paper we show that the language used by assistive robot (person-centric vs. task-centric) can influence how other people perceive the assisted person, as more or less intelligent, disciplined, competent etc.

Keywords: hri

Gender effects in perceptions of robots and humans with varying emotional intelligence (2019)

Meia Chita-Tegmark and Monika Lohani and Matthias Scheutz

In this paper we show that people have different emotional intelligence expectations from female vs. male-gendered robots.

Keywords: hri

Uncertain Logic Processing: logic-based inference and reasoning using Dempster–Shafer models (2018)

Núñez, Rafael C. and Murthi, Manohar N. and Premaratne, Kamal and Scheutz, Matthias and Bueno, Otávio

First order logic lies at the core of many methods in mathematics, philosophy, linguistics, and computer science. Although important efforts have been made to extend first order logic to the task of handling uncertainty, existing solutions are sometimes limited by the way they model uncertainty, or simply by the complexity of the problem formulation.

Supporting Human Autonomy in a Robot-Assisted Medication Sorting Task (2018)

Wilson, Jason R. and Lee, Nah Young and Saechao, Annie and Tickle-Degnen, Linda and Scheutz, Matthias

Medication management is a significant challenge for older adults, and the resultant drug-related problems are linked with hospitalizations and increased need for nursing homes. In this work, we explored the role of a socially assistive robot for one aspect of medication management: sorting. Specifically, we proposed a human-centric…

Learning and Obeying Conflicting Norms in Stochastic Domains (2018)

Daniel Kasenberg

Artificial agents will need to be able to reason about and obey human moral and social norms. Additionally, agents must be able to learn norms, both from instruction (eg, by natural language interaction with humans) and by observing the behavior of humans or other agents. This is necessary because (1) humans have many moral and social…

Keywords: ethics, moral, learn

Norms, Rewards, and the Intentional Stance: Comparing Machine Learning Approaches to Ethical Training (2018)

Daniel Kasenberg and Thomas Arnold and Matthias Scheutz

We compare our norm inference approach with inverse reinforcement learning for the task of learning moral and social norms from demonstrators that either are governed by explicit temporal logic representations of norms, or are reward-maximizing. We argue that our approach can be thought of as analogous to Dennett's "intentional stance".

Keywords: ethics, moral, learn

Inverse Norm Conflict Resolution (2018)

Daniel Kasenberg and Matthias Scheutz

Given observed agent behavior in a stochastic environment and a set ofmoral/social norms represented in Linear Temporal Logic, we present an algorithm for computing a set of weights indicating the relative importance of those norms.

Keywords: ethics, moral, learn

Inferring and Obeying Norms in Temporal Logic (2018)

Daniel Kasenberg

Robots and other artificial agents are increasingly being considered in domains involving complex decision-making and interaction with humans. These agents must adhere to human moral social norms: agents that fail to do so will be at best unpopular, and at worst dangerous. Artificial agents should have the ability to learn (both from…

Keywords: ethics, moral

Norm Conflict Resolution in Stochastic Domains (2018)

Daniel Kasenberg and Matthias Scheutz

We present an algorithm for artificial agents planning in Markov Decision Processes to maximally satisfy a set of potentially-conflicting norms (represented in Linear Temporal Logic).

Keywords: ethics, moral

"Thank You for Sharing that Interesting Fact!": Effects of Capability and Context on Indirect Speech Act Use in Task-Based Human-Robot Dialogue (2018)

Tom Williams and Daria Thames and Julia Novakoff and Matthias Scheutz

Naturally interacting robots must be able to understand natural human speech. As such, recent work has sought to allow robots to infer the intentions behind commonly used non-literal utterances such as indirect speech acts (ISAs). However, it is still unclear to what extent ISAs will actually be used in task-based human-robot dialogue,…

Early Syntactic Bootstrapping in an Incremental Memory-Limited Word Learner (2018)

Sepideh Sadeghi and Matthias Scheutz

We first present a probabilistic framework in which the knowledge of word order and word referent can be jointly learned in the absence of any prior syntactic knowledge (e.g., “subjecthood” or lexical categories), then we use our framework to study the utility of joint acquisition of word order and word referent and its onset, in…

Keywords: sem, learn

Towards a Conversation-Analytic Taxonomy of Speech Overlap (2018)

Felix Gervits and Matthias Scheutz

We present a taxonomy for classifying speech overlap in natural language dialogue. We describe the various dimensions of this scheme and show how it was applied to a corpus of remote dialogue.

Keywords: dia, comm

Observing Robot Touch in Context: How Does Touch and Attitude Affect Perception of a Robot's Social Qualities? (2018)

Thomas Arnold and Matthias Scheutz

We examine how the observation of a robot-initiated touch, shown in a task scenario and accompanied by either a positive or negative attitude in the robot's verbal feedback, affects how a robot's social qualities are evaluated.

Keywords: hri, ethics

The "Big Red Button" Is Too Late: an Alternative Model For the Ethical Evaluation of AI Systems (2018)

Thomas Arnold and Matthias Scheutz

We describe the demands that recent big red button proposals have failed to address, and we offer a preliminary model of an approach based on an ethical core (EC) consisting of a scenario-generating mechanism and a simulation environment.

Keywords: ethics, hri

Quasi-Dilemmas for Artificial Moral Agents (2018)

Daniel Kasenberg and Vasanth Sarathy and Thomas Arnold and Matthias Scheutz and Tom Williams

We describe moral quasi-dilemmas: situations similar to moral dilemmas, but in which an agent is unsure whether exploring the plan space or the world may reveal a course of action that satisfies all moral requirements. We argue that artificial moral agents should be built to handle MQDs, and that MQDs may be useful for evaluating AMA architectures.

Keywords: ethics, moral

Modeling Cell Migration in a Simulated Bioelectrical Signaling Network for Anatomical Regeneration (2018)

Giordano B. S. Ferreira and Matthias Scheutz and Michael Levin

In this paper, we further developed a cell-cell communication mechanism that enables structure discovery an regeneration by cell networks. More specifically, we restricted cell division to adult stem cells and we added stem cell migration as a possible cell behavior. Our results showed that after incorporating these constraints, the…

Keywords: cells, comm

Mate choice strategies in a spatially-explicit model environment (2018)

Giordano B. S. Ferreira AND Matthias Scheutz AND Sunny K. Boyd

We developed a biologically plausible agent-based model to investigate two common mate choice rules that may be used by female gray treefrogs (Hyla versicolor). Our results showed that females using the minimum-threshold strategy found higher quality males and traveled shorter distances on average, compared with females using best-of-n strategy.

Keywords: multi

HRI ethics and type-token ambiguity: what kind of robotic identity is most responsible? (2018)

Thomas Arnold and Matthias Scheutz

We explore the ethical challenges of a robot being taken as a general system and as a particular, discrete machine.

Keywords: ethics, hri

Sensitivity to Input Order: Evaluation of an Incremental and Memory-Limited Bayesian Cross-Situational Word Learning Model (2018)

Sepideh Sadeghi and Matthias Scheutz

We present an incremental and memory-limited Bayesian cross-situational word learning model and evaluate the model in terms of its functional performance and its sensitivity to input order. We show that the functional performance of our sub-optimal model on corpus data is close to that of its optimal counterpart (Frank et al., 2009),…

Keywords: sem, learn

Accidental encounters: can accidents be adaptive? (2018)

Giordano B. S. Ferreira and Matthias Scheutz

We investigate the extent of accidental encounters in a Multi Agent Territory Exploration (MATE) Task. Accidental encounters happen between agents and an unintended checkpoint. We found that even though accidents are often detrimental to the individual, there are cases in which they are beneficial to the population.

Keywords: multi

A Generalized Framework for Detecting Anomalies in Real-Time Using Contextual Information (2018)

Evana Gizzi and Lisa Le Vie and Matthias Scheutz and Vasanth Sarathy and Jivko Sinapov

Detecting non-conforming behaviors, called anomalies, is an important tool for intelligent systems, as it serves as a first step for learning new information and handling it in an appropriate way. To establish a technique for capturing anomalies using contextual and predictive information, we present a generalized framework for detecting…

Knowledge Acquisition in the Cockpit Using One-Shot Learning (2018)

Evana Gizzi and Lisa Le Vie and Matthias Scheutz and Vasanth Sarathy and Jivko Sinapov

Intelligent systems for aviation need to be capable of understanding and representing anomalous events as they happen in real-time. We explore this problem with a proof of concept framework based on contextual one-shot learning, run on a human-in-the-loop flight simulator.

Keywords: learn

Learning Cognitive Affordances for Objects from Natural Language Instruction (2018)

Vasanth Sarathy and Bradley Oosterveld and Evan Krause and Matthias Scheutz

In this work, we describe, demonstrate and evaluate an integrated cognitive robotic architecture which can learn cognitive affordances for objects from natural language and immediately use this knowledge in a dialoguebased learning and instruction task.

Keywords: prag, hri, dia, learn, arch

MacGyver Problems: AI Challenges for Testing Resourcefulness and Creativity (2018)

Vasanth Sarathy and Matthias Scheutz

When faced with real-world problems that seem unsolvable, humans display an exceptional degree of flexibility and creativity, improvising solutions with the limited resources available. In this essay, we propose a class of domain-independent AI challenge tasks - MacGyver Problems - that target these capabilities.

Real World Problem-Solving (2018)

Sarathy, Vasanth

In this paper, I attempt to combine the relevant neuroscientific literature on creativity and problem-solving with the scattered and nascent work in perceptually-driven learning from the environment. I propse a potential new theory for real world problem-solving and map out its hypothesized neural basis.

Pardon the Interruption: Managing Turn-Taking through Overlap Resolution in Embodied Artificial Agents (2018)

Felix Gervits and Matthias Scheutz

We introduce a computational cognitive model for overlap resolution in articial agents. The model was inspired by findings from Conversation Analysis, and works by identifying the function of an overlap based on its position in the dialogue. Policies to drop out or maintain the turn are based on the type of overlap, the local discourse…

Keywords: dia, hri, comm

Shared Mental Models to Support Distributed Human-Robot Teaming in Space (2018)

Felix Gervits and Terry Fong and Matthias Scheutz

We extend our Shared Mental Model (SMM) interaction framework to show how it can be used to overcome some of the challenges inherent in distributed HRI and facilitate coordination in space robotics teams. We conducted an exploratory HRI study to identify potential benefits that the SMM mechanisms can afford in a task domain involving…

Keywords: hri, multi

Recursive Spoken Instruction-Based One-Shot Object and Action Learning (2018)

Matthias Scheutz and Evan Krause and Bradley Oosterveld and Tyler Frasca and Robert Platt

Learning new knowledge from single instructions and being able to apply it immediately is highly desirable for artificial agents. We provide the first demonstration of spoken instruction-based one-shot object and action learning in a cognitive robotic architecture and briefly discuss the architectural modifications required to enable…

One-Shot Interaction Learning from Natural Language Instruction and Demonstration (2018)

Tyler Frasca and Bradley Oosterveld and Evan Krause and Matthias Scheutz

In this paper, we present an action learning framework which allows a robot to learn new actions containing multiple agents.

Keywords: Instruction Based Task Learning, Human-Robot Interaction

Guidelines for Improving Task-based Natural Language Understanding in Human-Robot Rescue Teams (2017)

Yazdani, Fereshta and Scheutz, Matthias and Beetz, Michael

Mixed human-robot teams are increasingly considered for accomplishing complex mission due to their complementary capabilities. A major barrier for deploying such heterogeneous teams in real-world settings, is the current lack of natural skills in robotic team members, such as the understanding and interpretation of natural language…

Cognition-enabled Task Interpretation for Human-Robot Teams in a Simulation-based Search and Rescue Mission (2017)

Yazdani, Fereshta and Scheutz, Matthias and Beetz, Michael

Due to humans and robots complementary capabilities, mixed human-robot teams are considerably deployed in real-world settings. A favored communication means is the natural language used by humans that is still a challenge for robotic teammates. They need to understand the environment from the viewpoint of their human teammates in order…

The Case for Explicit Ethical Agents (2017)

Sheutz, Matthias

Morality is a fundamentally human trait that permeates all levels of human society, from basic etiquette and normative expectations of social groups, to formalized legal principles upheld by societies. Hence, future interactive AI systems, in particular, cognitive systems on robots deployed in human settings, will have to meet human…

Interactive Task Learning (2017)

John E. Laird and Kevin Gluck and John Anderson and Kenneth D. Forbus and Odest Chadwicke Jenkins and Christian Lebiere and Dario Salvucci and Matthias Scheutz and Andrea Thomaz and Greg Trafton and Robert E. Wray and Shiwali Mohan and James R. Kirk

This article presents a new research area called interactive task learning (ITL), in which an agent actively tries to learn not just how to perform a task better but the actual definition of a task through natural interaction with a human instructor while attempting to perform the task. The authors provide an analysis of desiderata for…

Value Alignment or Misalignment -- What Will Keep Systems Accountable? (2017)

Thomas Arnold and Daniel Kasenberg and Matthias Scheutz

We present here a critique of a turn toward inverse reinforcement-learning as a way to guarantee ethical AI systems. We argue that a hybrid architecture, which can represent norms explicitly, is necessary for basic social coordination and moral reasoning between people and AI systems.

Keywords: ethics, hri, moral, prag

Disfluency Handling for Robot Teammates (2017)

Felix Gervits

I report on my empirical work which shows that effective human teams produced about twice as many self-repair disfluencies as ineffective teams in a collaborative search task. I then describe ongoing work to implement disfluency-handling mechanisms for robots that serve on teams with humans.

Keywords: dia, comm, hri

Blue Sky Ideas in Artificial Intelligence Education from the EAAI’17 New and Future AI Educator Program (2017)

Eric Eaton and Sven Koenig and Claudia Schulz and Francesco Maurelli and John Lee and Joshua Eckroth and Mark Crowley and Richard Freedman and Rogelio Cardona-Rivera and Tiago Machado and Tom Williams

The 7th Symposium on Educational Advances in Artificial Intelligence (EAAI'17, co-chaired by Sven Koenig and Eric Eaton) launched the EAAI New and Future AI Educator Program to support the training of early-career university faculty, secondary school faculty, and future educators (PhD candidates or postdocs who intend a career in academia).

A Tale of Two Architectures: A Dual-Citizenship Integration of Natural Language and the Cognitive Map (2017)

Tom Williams and Collin Johnson and Matthias Scheutz and Benjamin Kuipers

Vulcan and DIARC are two robot architectures with very different capabilities: Vulcan uses rich spatial representations to facilitate navigation capabilities in real-world, campus-like environments, while DIARC uses high-level cognitive representations to facilitate human-like tasking through natural language. In this work, we show how…

Reference Resolution in Robotics: A Givenness Hierarchy Theoretic Approach (2017)

Tom Williams and Matthias Scheutz

As robots become increasingly prevalent in our society, it becomes increasingly important to endow them with natural language capabilities, including the ability to both understand and generate so-called referring expressions. In recent work, we have sought to enable referring expression understanding capabilities by leveraging the…

A Parallelized Dynamic Programming Approach to Zero Resource Spoken Term Discovery (2017)

Bradley Oosterveld and Richard Veale and Matthias Scheutz

Describes a method for zero resource spoken term discovery, the process of deriving a set of linguistic tokens from a spoken corpus with no transcription. Our approach makes use of the Acoustic DP-ngram algorithm, and parallelization using GPUs.

Keywords: speech

Beyond Moral Dilemmas: Exploring the Ethical Landscape in HRI (2017)

Thomas Arnold and Matthias Scheutz

This paper presents three areas for HRI ethics that can get lost in more attention-getting debates about killer robots or sex robots: tactile and proprioceptive modes of interaction, competing interests in concrete contexts for interaction, and group dynamics in decision-making.

Keywords: ethics, hri, moral

Intimacy, Bonding, and Sex Robots: Examining Empirical Results and Exploring Ethical Ramifications (2017)

Matthias Scheutz and Thomas Arnold

We present an expansion of our previous survey, the first systematic one of attitudes toward sexual interaction with robots. We find similar gender effects to what our first paper did, and we argue the results point toward intimacy as an critical area for HRI ethics to tackle, a broader area than sexuality alone.

Keywords: ethics, hri

Two Bots, One Brain: Component Sharing in Cognitive Robotic Architectures (2017)

Bradley Oosterveld and Luca Brusatin and Matthias Scheutz

Sumbission to the HRI 2017 video competition, provides a demonstration of how component sharing can be used in a multi robot configuration within DIARC.

Keywords: dia, multi, comm

The Pragmatic Parliament: A Framework for Socially-Appropriate Utterance Selection in Artificial Agents (2017)

Felix Gervits and Gordon Briggs and Matthias Scheutz

We introduce a framework for natural language generation in artificial agents that is sensitive to a variety of social and communicative goals. We show how these goals can be ranked and fused by use of a voting algorithm to modulate directive generation in various domains.

Keywords: prag, hri, comm

Spoken Instruction-Based One-Shot Object and Action Learning in a Cognitive Robotic Architecture (2017)

Matthias Scheutz and Evan Krause and Brad Oosterveld and Tyler Frasca and Robert Platt

We demonstrate how a robot can learn new knowledge about objects, objects parts, and actions from a single spoken instruction and use it immediately for performing tasks. We detail the modifications to several architectural components required to enable such fast learning.

Keywords: speech, dia, sem, prag, arch, vision, learn

Enabling Robots to Understand Indirect Speech Acts in Task-Based Interactions (2017)

Gordon Briggs and Tom Williams and Matthias Scheutz

An important open problem for enabling truly taskable robots is the lack of task-general natural language mechanisms within cognitive robot architectures that enable robots to understand typical forms of human directives and generate appropriate responses. In this paper, we first provide experimental evidence that humans tend to phrase…

Referring Expression Generation Under Uncertainty in Integrated Robot Architectures (2017)

Tom Williams and Matthias Scheutz

To engage in language-based social interaction with humans, robots must be able to refer to other agents, objects, and locations, also known as referring expression generation (REG). Unfortunately, classic REG algorithms like the Incremental Algorithm assume that information is certain, centralized, and easily accessible: assumptions…

Resolution of Referential Ambiguity in Human-Robot Dialogue Using Dempster-Shafer Theoretic Pragmatics (2017)

Tom Williams and Matthias Scheutz

Robots designed to interact with humans in realistic environments must be able to handle uncertainty with respect to the identities and properties of the people, places, and things found in their environments. When humans refer to these entities using under-specified language, robots must often generate clarification requests to…

Dissertation Briefing: Situated Natural Language Interaction in Uncertain and Open Worlds (2017)

Tom Williams

As intelligent robots become integrated into society, it becomes important for them to be capable of natural, human-like human-robot interaction (HRI). While there has been some progress on enabling natural-language based HRI (Mavridis, 2015), most natural language enabled robots rely on highly scripted interactions, keyword spotting,…

Mental Representations and Computational Modeling of Context-Specific Human Norm Systems (2017)

Vasanth Sarathy and Matthias Scheutz and Joseph Austerweil and Yoed Kenett and Mowafak Allaham and Bertram Malle

We describe initial experiments on human norm representations in which the context specificity of norms features prominently. We then provide a formal representation of norms and a machine learning algorithm to learn norms under uncertainty from these human data, while preserving their context specificity.

Keywords: learn, ethics, moral

Architectural Mechanisms for Handling Human Instructions for Open-World Mixed-Initiative Team Tasks and Goals (2017)

Kartik Talamadupula and Gordon Briggs and Matthias Scheutz and Subbarao Kambhampti

Future envisioned mixed-initiative human-robot teams will require increasingly autonomous and capable robotic team members who can interact with their human teammates in natural ways. The challenge is to develop an integrated cognitive robotic architecture that will enable effective, natural human-robot interactions. In this paper, we…

Better Than Average: Analyzing Distributions to Understand Robot Behavior in a Multi-agent Area Coverage Scenario (2017)

David Buckingham and Giordano B. S. Ferreira and Matthias Scheutz

Building robots, even for performing simple tasks, requires the designer to assess performance using various parameters. However, sometimes the best solution is not the one that performs best on average. Hence, other ways of evaluating performance are necessary. We ran a broad parameter sweep for an agent-based simulation of a robotic…

Keywords: multi, swarms

Investigating the Effects of Noise on a Cell-to-Cell Communication Mechanism for Structure Regeneration (2017)

Giordano B. S. Ferreira and Matthias Scheutz and Michael Levin

We changed our previous model of dynamic morphology discovery and repair to account for noise on cell-cell communication. We verified that the original model was not reliable against noise, we then proposed a simple mechanism by which cells needed confirmation from several packets in order to divide and position a cell in a missing location.

Keywords: cells, comm

Interpretable Apprenticeship Learning with Temporal Logic Specifications (2017)

Daniel Kasenberg and Matthias Scheutz

We consider the problem of inferring temporal logic specifications from agent behavior in stochastic domains. We formulate this as a multi-objective problem and use genetic programming to demonstrate the efficacy of our formluation.

Keywords: mc, norm

Referring Expression Generation Under Uncertainty: Algorithm and Evaluation Framework (2017)

Tom Williams and Matthias Scheutz

For situated agents to effectively engage in natural-language interactions with humans, they must be able to refer to entities such as people, locations, and objects. While classic referring expression generation (REG) algorithms like the Incremental Algorithm (IA) assume perfect, complete, and accessible knowledge of all referents, this…

Getting Help Without Asking: Stigmergic Planning for Human-robot Collaboration (2017)

David Buckingham and Matthias Scheutz

When a robot is unable to perform one or more actions that are necessary for accomplishing its goals, it should integrate into its plan the capacities of other agents. We consider a robot that recruits the help of a human without explicit communication.

Keywords: hri, multi

An Embodied Incremental Bayesian Model of Cross-Situational Word Learning (2017)

Sepideh Sadeghi and Matthias Scheutz and Evan Krause

We present an incremental Bayesian model of cross-situational word learning with limited access to past situations and demonstrate its superior performance compared to other baseline incremental models, especially in the presence of sensory noise in speech and object recognition. Then, we embed our model in a cognitive robotic…

Keywords: speech, sem, vision, learn

A Neural Field Model of Sequence Perception (2017)

Andrew Valenti and Bradley Oosterveld and Matthias Scheutz

We demonstrate how perception arises when the model learns to decode a sequence represented as a pattern of neural field activation, representing any mode of sensory input.

Keywords: speech, vision, learn

Differences in Interaction Patterns and Perception for Teleoperated and Autonomous Humanoid Robots (2017)

Maxwell Bennett and Tom Williams and Daria Thames and and Matthias Scheutz

As the linguistic capabilities of interactive robots advance, it becomes increasingly important to understand how humans will instruct robots through natural language. What is more, with the increased use of teleoperated humanoid robots, it is important to recognize whether any differences between instructions given to humans and to…

The Tactile Ethics of Soft Robotics: Designing Wisely for Human-Robot Interaction (2017)

Thomas Arnold and Matthias Scheutz

We explore unaddressed ethical questions that are arising for soft robotics design. We argue that intimacy and bonding instincts should be considered lest robots with bodies that invite touch, manipulate, deceive or harm the people that interact with them.

Keywords: ethics, hri

Creating POS Tagging and Dependency Parsing Experts via Topic Modeling (2017)

Atreyee Mukherjee and Sandra Kuebler and Matthias Scheutz

Part of speech (POS) taggers and dependency parsers tend to work well on homogeneous datasets but their performance suffers on datasets containing data from different genres. In our current work, we investigate how to create POS tagging and dependency parsing experts for heterogeneous data by employing topic modeling. We create topic…

Do We Need Emotionally Intelligent Articial Agents? First Results of Human Perceptions of Emotional Intelligence in Humans Compared to Robots (2017)

Lisa Fan and Matthias Scheutz and Monika Lohani and Marissa McCoy and Charlene Stokes

Humans are very apt at reading emotional signals in other humans and even artificial agents, which raises the question of whether artificial agents need to be emotionally intelligent to ensure effective social interactions. For artificial agents without emotional intelligence might generate behavior that is misinterpreted, unexpected,…

A Framework for developing and using shared mental models in human-agent teams (2017)

Matthias Scheutz and Scott DeLoach and Julie Adams

Converging evidence from psychology, human factors, management and organizational science, and other related fields suggests that humans working in teams employ shared mental models to represent and use pertinent information about the task, the equipment, the team members, and their roles. In particular, shared mental models are used to…

The State-of-the-Art in Autonomous Wheelchairs Controlled through Natural Language: A Survey (2017)

Tom Williams and Matthias Scheutz

Natural language is a flexible and powerful control modality which can transform a wheelchair from a vehicle into a genuine helper. While autonomous wheelchairs are increasingly designed to use natural language for control, most of them only handle a small number of rigid commands. To establish the state-of-the-art in language-enabled…

Joint Acquisition of Word Order and Word Referent in a Memory-Limited and Incremental Learner (2017)

Sepideh Sadeghi and Matthias Scheutz

We study the utility of joint acquisition of simple versions of word order and word meaning in early stages of acquisition in a memory-limited incremental model. Our results confirm previous simulation results from ideal learners suggesting that it is possible to jointly acquire word order and meanings and that learning is improved as…

Keywords: sem, learn

Exploring Coordination in Human-Robot Teams in Space (2017)

Felix Gervits and Charlotte Warne and Harrison Downs and Kathleen Eberhard and Matthias Scheutz

We introduce a novel experimental paradigm to study human-robot teaming in a space domain. The platform is unique in that it is scalable and customizable to various team configurations, allowing for the study of various dimensions of teaming within the same task domain.

Keywords: hri, dia, comm, mixed

Introducing Simulated Stem Cells into a Bio-Inspired Cell-Cell Communication Mechanism for Structure Regeneration (2017)

Giordano B. S. Ferreira and Matthias Scheutz and Michael Levin

Here we include simulated stem cells in a previous mechanism of dynamic morphology discovery and regeneration. We hypothesize that only these cells generate new morphology messages while differentiated cells only relay those messages. We showed that a ratio as small as 10% of stem cells was sufficient for fully regenerate a…

Keywords: cells, comm

Animal-Robot Interaction: The Role of Human Likeness on the Success of Dog-Robot Interactions (2017)

Maretta Morovitz and Megan Mueller and Matthias Scheutz

Animals, and specifically dogs, are present throughout our social spaces which nowadays are increasingly populated with technology. Past research has mostly investigated interactions between humans and robots, failing to address possible effects of this technology, on animals, such as canines, in homes and in particular the possible…

Strategies and Mechanisms to Enable Dialogue Agents to Respond Appropriately to Indirect Speech Acts (2017)

Gordon Briggs and Matthias Scheutz

Humans often use indirect speech acts (ISAs) when issuing directives. Much of the work in handling ISAs in computational dialogue architectures has focused on correctly identifying and handling the underlying non-literal meaning. There has been less attention devoted to how linguistic responses to ISAs might differ from those given to…

A High Level Language for Human Robot Interaction (2017)

Chitta Baral and Barry Lumpkin and Matthias Scheutz

Abstract Language processing and high level execution and control are functional capabilities that arise in the context of cognitive systems. In the context of human-robot interaction, natural language is considered a good communication medium as it allows humans with less training about the robot's internal language to be able to…

Spatial Referring Expression Generation for HRI: Algorithms and Evaluation Framework (2017)

Lars Kunze and Tom Williams and Nick Hawes and Matthias Scheutz

The ability to refer to entities such as objects, locations, and people is an important capability for robots designed to interact with humans. For example, a referring expression (RE) such as "Do you mean the box on the left?" might be used by a robot seeking to disambiguate between objects. In this paper, we present and evaluate…

AI in the Sky: How People Morally Evaluate Human and Machine Decisions in a Lethal Strike Dilemma (2017)

Bertram Malle and Stuti Thapa Magar and Matthias Scheutz

Even though morally competent artificial agents have yet to emerge in society, we need insights from empirical science into how people will respond to such agents and how these responses should inform agent design. Three survey studies presented participants with an artificial intelligence (AI) agent, an autonomous drone, or a human…

Learning Behavioral Norms in Uncertain and Changing Contexts (2017)

Vasanth Sarathy and Matthias Scheutz and Bertram Malle

We demonstrate a novel cognitive capability with which an agent can dynamically learn norms while being exposed to distinct contexts, recognizing the unique identity of each context and the norms that apply in it.

Keywords: learn, ethics, moral

The Reliability of Non-verbal Cues for Situated Reference Resolution and their Interplay with Language - Implications for Human Robot Interaction (2017)

Stephanie Gross and Brigitte Krenn and Matthias Scheutz

When uttering referring expressions in situated task descriptions, humans naturally use verbal and non-verbal channels to transmit information to their interlocutor. To develop mechanisms for robot architectures capable of resolving ob- ject references in such interaction contexts, we need to better understand the multi-modality of human…

Moral Robots (2017)

Scheutz, Matthias and Malle, Bertram

This chapter starts by looking at the empirical evidence for human expectations about moral robots and considers ways to implement them in robotic control systems. It considers three main options, all with their own advantages and disadvantages: implement ethical theories as proposed by philosophers; implement legal principles as…

Relational Enhancement: A Framework for Evaluating and Designing Human-Robot Relationship (2016)

Wilson, Jason and Arnold, Thomas and Scheutz, Matthias

Much existing work examining the ethical behaviors of robots does not consider the impact and effects of long- term human-robot interactions. A robot teammate, col- laborator or helper is often expected to increase task performance, individually or of the team, but little dis- cussion is usually devoted to how such a robot should balance…

Inevitable Psychological Mechanisms Triggered by Robot Appearance: Morality Included? (2016)

Malle, Bertram F. and Scheutz, Matthias

Certain stimuli in the environment reliably, and perhaps in- evitably, trigger human cognitive and behavioral responses. We suggest that the presence of such “trigger stimuli” in modern robots can have disconcerting consequences. We provide one new example of such consequences: a reversal of a pattern of moral judgments people make about…

Combining Agent-Based Modeling with Big Data Methods to Support Architectural and Urban Design (2016)

Scheutz, Matthias and Mayer, Thomas

Big Data analytics are increasingly used to discover potentially interesting patterns in large data sets. In this chapter, we discuss the potential of combining Big Data methods with those of agent-based simulations to support architectural and urban designs, for agent-based models allow for the generation of novel datasets to study…

Multi-modal referring expressions in human-human task descriptions and their implications for human-robot interaction (2016)

Gross, Stephanie and Krenn, Brigitte and and Scheutz, Matthias

Human instructors often refer to objects and actions involved in a task description using both linguistic and non-linguistic means of communication. Hence, for robots to engage in natural human-robot interactions, we need to better understand the various relevant aspects of human multi-modal task descriptions. We analyse reference…

Architectural Mechanisms for Situated Natural Language Understanding in Uncertain and Open Worlds (2016)

Tom Williams

As natural language capable robots and other agents become more commonplace, the ability for these agents to understand truly natural human speech is becoming increasingly important. What is more, these agents must be able to understand truly natural human speech in realistic scenarios, in which an agent may not have full certainty in…

Are we ready for sex robots? (2016)

Matthias Scheutz and Thomas Arnold

Sex robots are gaining a remarkable amount of attention in current discussions about technology and the future of human relationships. To help understand what kinds of relationships people will have with these robots, empirical data about people's views of sex robots is needed. We report the results of the first systematic survey that…

Situated Open World Reference Resolution for Human-Robot Dialogue (2016)

Tom Williams and Saurav Acharya and Stephanie Schreitter and Matthias Scheutz

A robot participating in natural dialogue with a human interlocutor may need to discuss, reason about, or initiate actions concerning dialogue-referenced entities. To do so, the robot must first identify or create new representations for those entities, a capability known as reference resolution. We previously presented algorithms for…

A Framework for Resolving Open-World Referential Expressions in Distributed Heterogeneous Knowledge Bases (2016)

Tom Williams and Matthias Scheutz

We present a domain-independent approach to reference resolution that allows a robotic or virtual agent to resolve references to entities (eg, objects and locations) found in open worlds when the information needed to resolve such references is distributed among multiple heterogeneous knowledge bases in its architecture. An agent using…

Inferring Higher-Order Affordances for more Natural Human-Robot Collaboration (2016)

Vasanth Sarathy

Helper robots will be critical in many sectors: helping our elderly and disabled in assisted living facilities, conducting search-and-rescue missions in unforgiving terrain to save human lives, assisting our astronauts on the space station, or even monitoring our surroundings to keep us safe from national security threats.

Keywords: hri, vision

Enabling Basic Normative HRI in a Cognitive Robotic Architecture (2016)

Vasanth Sarathy and Jason Wilson and Thomas Arnold and Matthias Scheutz

We propose a promising mechanism in an integrated robotic architecture for reasoning about the social and moral propriety of situations. This sort of normative mechanism is valuable especially in collaborative tasks where actions and situations could potentially be perceived as threatening and thus need a change in course of action to…

Keywords: hri, vision, arch, ethics, moral

Cognitive Affordance Representations in Uncertain Logic (2016)

Vasanth Sarathy

Natural human activities involve applying cognitive skills to use and manipulate objects around us, often several at a time, simultaneously and continuously. Consider the simple act of doodling, which requires several cognitive skills:(1) choosing how to grasp a pencil,(2) sequencing actions like drawing and erasing, and (3) reasoning…

Keywords: hri, vision

Cognitive Affordance Representations in Uncertain Logic (2016)

Vasanth Sarathy and Matthias Scheutz

We develop a formal rules-based probabilistic logical representational format for cognitive affordances. Our framework allows agents to make deductive and abductive inferences about functional and social affordances, collectively and dynamically, thereby allowing the agent to adapt to changing conditions.

Keywords: hri, vision

Analogical Generalization of Actions from Single Exemplars in a Robotic Architecture (2016)

Jason R. Wilson and Evan Krause and Matthias Scheutz and Morgan Rivers

Humans are often able to generalize knowledge learned from a single exemplar. We present a novel integration of mental simulation and analogical generalization algorithms into a cognitive robotic architecture that enables a similarly rudimentary generalization capability in robots. Specifically, we show how a robot can generate…

Keywords: learn, arch

Robot Assistance in Medication Management Tasks (2016)

Jason R. Wilson

A robot in the home of an elderly person providing assistive care will face many difficult decisions. I focus on a set of tasks that are very common and often stressful. Medication management tasks are ideal for a robot to assist in, but even a task with straightforward guidelines and goals can have numerous moral issues brought about by…

Relational Enhancement: A Framework for Evaluating and Designing Human-Robot Relationships (2016)

Jason R. Wilson and Thomas Arnold and Matthias Scheutz

Much existing work examining the ethical behaviors of robots does not consider the impact and effects of longterm human-robot interactions. A robot teammate, collaborator or helper is often expected to increase task performance, individually or of the team, but little discussion is usually devoted to how such a robot should balance the…

Dynamic Structure Discovery and Repair for 3D Cell Assemblages (2016)

Giordano B. S. Ferreira and Max Smiley and Matthias Scheutz and Mike Levin

We proposed a novel model of morphology discovery and repair based on cell-cell communication. We tested the mechanism against different rates of random cell death and showed that this mechanism was capable of maintaining a Planarian-like structure indefinitely.

Keywords: cells, comm

Feats Without Heroes: Norms, Means, and Ideal Robotic Action (2016)

Matthias Scheutz and Thomas Arnold

Autonomous systems may have extraordinary abilities that changes how people apply norms to them, for example self-sacrifice. This paper spells out how a system might decide on an extraordinary means to fulfill in a norm in context.

Keywords: ethics, hri, moral

Against the moral Turing test: accountable design and the moral reasoning of autonomous systems (2016)

Thomas Arnold and Matthias Scheutz

We argue in this paper that the idea of a "moral Turing test" is insufficient for an ethical evaluation of an autonomous system's behavior. We propose that verification, where the behavior of a system is designed for transparency and explicitly represents decision-making based on norms, is a better standard of evaluation.

Keywords: ethics, hri, moral

A Neural Field Model of Word Repetition effects in Early Time-Course ERPs in Spoken Word Perception (2016)

Andy Valenti and Michael Brady and Matthias Scheutz and Phillip Holcomb and He Pu

We demonstrate the dynamics of the model evolve to generate an event-related potential (ERP) associate with word repetition in speech and fit the waveform to human experimental data

Keywords: speech, learn, neural

Beyond Grasping - Perceiving Affordances Across Various Stages of Cognitive Development (2016)

Vasanth Sarathy and Matthias Scheutz

We demonstrate a flexible computational approach to affordance perception that is capable of handling different types of affordances learned through various stages of development and across varying contexts.

Keywords: hri, vision

Designing a Social Robot to Assist in Medication Sorting (2016)

Jason R. Wilson and Linda Tickle-Degnen and Matthias Scheutz

Being able to sort one's own medications is a critical self-management task for people with Parkinson's disease. We analyzed the medication sorting task and gathered design considerations. Then we developed an autonomous robot to assist in the task. We used guidelines provided by occupational therapists to determine the level of…

Reflections on the design challenges prompted by affect-aware socially assistive robots (2016)

Jason R. Wilson and Matthias Scheutz and Gordon Briggs

The rising interest in socially assistive robotics is, at least in part, stemmed by the aging population around the world. A lot of research and interest has gone into insuring the safety of these robots. However, little has been done to consider the necessary role of emotion in these robots and the potential ethical implications of…

A Logic-based Computational Framework for Inferring Cognitive Affordances (2016)

Vasanth Sarathy and Matthias Scheutz

We demonstrate a novel computational architecture for affordance perception. Our architecture allows robotic agents to reason that dirty knives are typically not used for cutting vegetables, even though they can functionally accomplish the task.

Keywords: hri, vision, arch

Autonomy and Dignity: Principles in Designing Effective Social Robots to Assist in the Care of Older Adults (2016)

Jason R. Wilson and Nah Young Lee and Annie Saechao and Matthias Scheutz

We introduce two key concepts for designing social robots to assist in the care of older adults: autonomy and personal dignity. These concepts are guiding ethical principles to occupational therapists. These principles provide a client-centric perspective to effective care that ensures the well-being of the individual and maintaining a…

Disfluent but effective? A quantitative study of disfluencies and conversational moves in team discourse (2016)

Felix Gervits and Kathleen Eberhard and Matthias Scheutz

We examine empirical data on grounding strategies and the use of disfluency in team discourse, and find that these abilities are crucial for team coordination and performance. We discuss how artificial agents can benefit from being able to handle and generate these dialogue features for more natural and effective interaction.

Keywords: hri, dia, comm, mixed

Team Communication as a Collaborative Process (2016)

Felix Gervits and Kathleen Eberhard and Matthias Scheutz

We report on the results of a corpus analysis aimed at exploring the various factors that influence communication and performance in a collaborative search task. We found that effective teams used specific communication strategies to improve coordination and to establish and maintain common ground, and that these strategies were affected by task constraints.

Keywords: dia, comm, mixed

A generalization of Bayesian inference in the Dempster-Shafer belief theoretic framework (2016)

J. N. Heendeni and K. Premaratne and M. N. Murthi and J. Uscinski and M. Scheutz

In the literature, two main views of Dempster-Shafer (DS) theory are espoused: DS theory as evidence (as described in Shafer's seminal book) and DS theory as a generalization of probability. These two views are not always consistent. In this paper, we employ the generalized probability view of DS theory to arrive at results that allow…

Resolution of Referential Ambiguity Using Dempster-Shafer Theoretic Pragmatics (2016)

Tom Williams and Matthias Scheutz

A major challenge for robots interacting with humans in realistic environments is handling robots' uncertainty with respect to the identities and properties of the people, places, and things found in their environments: a problem compounded when humans refer to these entities using underspecified language.

Which robot am I thinking about? The impact of action and appearance on people's evaluations of a moral robot (2016)

Bertram F. Malle and Matthias Scheutz and Jodi Forlizzi and John T. Voiklis

In three studies we found further evidence for a previously discovered Human-Robot (HR) asymmetry in moral judgments: that people blame robots more for inaction than action in a moral dilemma but blame humans more for action than inaction in the identical dilemma (where inaction allows four persons to die and action sacrifices one to save the four).

Going Beyond Command- Based Instructions: Extending Robotic Natural Language Interaction Capabilities (2015)

Tom Williams and Gordon Briggs and Brad Oosterveld and Matthias Scheutz

We propose novel mechanisms for inferring intentions from utterances and generating clarification requests that will allow robots to cope with a much wider range of task-based natural language interactions. We demonstrate the potential of these inference algorithms for natural human-robot interactions by running them as part of an…

Keywords: dia, sem, comm, parse

Sacrifice One For the Good of Many? People Apply Different Moral Norms to Human and Robot Agents (2015)

Bertram F. Malle and Matthias Scheutz and Thomas H. Arnold and John T. Voiklis and Corey Cusimano

Moral norms play an essential role in regulating human interaction. With the growing sophistication and proliferation of robots, it is important to understand how ordinary people apply moral norms to robot agents and make moral judgments about their behavior. We report the first comparison of people's moral judgments (of permissibility,…

Are Robots Ready for Administering Health Status Surveys: First Results from an HRI Study with Subjects with Parkinsons Disease (2015)

Priscilla Briggs and Matthias Scheutz and Linda Tickle-Degnen

Facial masking is a symptom of Parkinson's disease (PD) in which humans lose the ability to quickly create refined facial expressions. This difficulty of people with PD can be mistaken for apathy or dishonesty by their caregivers and lead to a breakdown in social relationships. We envision future "robot mediators" that could ease…

A Domain-Independent Model of Open-World Reference Resolution (2015)

Tom Williams and Matthias Scheutz

The ability to ground conversational referents is a key requirement for human dialogue. This process, known as reference resolution, has received much attention from both psycholinguists seeking to understand how humans process language and computer scientists seeking to improve the performance of language-capable agents.

Following Strategies Reduces Accidents, but Makes Outcomes Worse: Evidence from Simulated Treefrog Mating Scenarios (2015)

Giordano B. S. Ferreira and Matthias Scheutz

In this work we verified the influence of accidental encounters (i.e., when a female ends up mating with an undesirable male) in Treefrog mating scenarios. We verified the frequency and influence of those accidents on the outcomes of two mating selection strategies (named best-of-closest-n and minimum-threshold). After running a large…

Keywords: multi

A Model of Empathy to Shape Trolley Problem Moral Judgements (2015)

Jason R. Wilson and Matthias Scheutz

Moral judgements are a complex phenomenon that have gained a renewed interest in the research community. Many have proposed explanations for moral judgements, including utilitarian accounts and the Principle of Double Effect. Some also advocate for the critical role of emotional processes like empathy. However, developing a computational…

Planning for Serendipity (2015)

Tathagata Chakraborti and Gordon Briggs and Kartik Talamadupula and Yu Zhang1 and Matthias Scheutz and David Smith and Subbarao Kambhampati1

Recently there has been a lot of focus on human robot co-habitation issues that are often orthogonal to many aspects of human-robot teaming; e.g. on producing socially acceptable behaviors of robots and de-conflicting plans of robots and humans in shared environments. However, an interesting offshoot of these settings that has largely…

POWER: A Domain-Independent Algorithm for Probabilistic, Open-World Entity Resolution (2015)

Tom Williams and Matthias Scheutz

The problem of uniquely identifying an entity described in natural language, known as reference resolution, has become recognized as a critical problem for the field of robotics, as it is necessary in order for robots to be able to discuss, reason about, or perform actions involving any people, locations, or objects in their environments.

When Will People Regard Robots as Morally Competent Social Partners? (2015)

Bertram Malle and Matthias Scheutz

We propose that moral competence consists of five distinct but related elements: (1) having a system of norms; (2) mastering a moral vocabulary; (3) exhibiting moral cognition and affect; (4) exhibiting moral decision making and action; and (5) engaging in moral communication. We identify some of the likely triggers that may convince…

Towards More Natural Human-Robot Dialogue (2015)

Tom Williams

A primary goal of the field of Human-Robot Interaction is to allow for natural human-robot interactions, and thus robot architectures must eventually be able to understand truly natural human speech. And yet, despite the abundance of research devoted to language understanding, most robots capable of participating in linguistic…

Towards Situated Open World Reference Resolution (2015)

Tom Williams and Stephanie Schreitter and Saurav Acharya and Matthias Scheutz

Natural language dialogue provides the opportunity for truly natural human-robot interaction. A robot participating in natural language dialogue must identify or create new representations for referenced entities if it is to discuss, reason about, or perform actions involving that entity, a capability known as reference resolution.

Towards Morally Sensitive Action Selection for Autonomous Social Robots (2015)

Matthias Scheutz and Bertram Malle and Gordon Briggs

Autonomous social robots embedded in human societies have to be sensitive to human social interactions and thus to moral norms and principles guiding these interactions. Actions that violate norms can lead to the violator being blamed. Robots thus need to be able to anticipate possible norm violations and attempt to prevent them while they execute actions.

Networks of Social and Moral Norms in Human and Robot Agents (2015)

Bertram Malle and Matthias Scheutz and Joe Austerweil

The most intriguing and ethically challenging roles of robots in society are those of collaborator and social partner. We propose that such robots must have the capacity to learn, represent, activate, and apply social and moral norms—they must have a norm capacity. We offer a theoretical analysis of two parallel questions: what…

Investigating the Effects of Robot Affect and Embodiment on Attention and Natural Language of Human Teammates (2015)

Thomas Donahue and Matthias Scheutz

HRI studies investigating human-robot interactions in mixed initiative teams typically only look at macro-level behaviors. Yet, an investigation of micro-level behaviors such as eye gaze fixations, attentional shifts, communicative acts, and others is often necessary in order to determine the exact influence of robot behaviors on human cognitive processes.

When Robots Object: Evidence for the utility of verbal, but not necessarily spoken protest (2015)

Gordon Briggs, Ian McConnell, and Matthias Scheutz

Future autonomous robots will likely encounter situations in which humans end up commanding the robots to perform tasks that robot ought to object. A previous study showed that robot appearance does not seem to affect human receptiveness to robot protest produced in response to inappropriate human commands. However, this previous work…

"Sorry, I Can't Do That:" Developing Mechanisms to Appropriately Reject Directives in Human-Robot Interactions (2015)

Gordon Briggs and Matthias Scheutz

Future robots will need mechanisms to determine when and how it is best to reject directives that it receives from human interlocutors. In this paper, we briefly present initial work that has been done in the DIARC/ADE cognitive robotic architecture to enable a directive rejection and explanation mechanism, showing its operation in a simple HRI scenario.

Semantic Representation of Objects and Function (2015)

Vasanth Sarathy and Matthias Scheutz

We sketch a computational model for affordance that can represent complicated activities and can account for the dynamic and continuous nature of real-world scenarios.

Keywords: hri, vision

Gender, more so than Age, Modulates Positive Perceptions of Language-Based Human-Robot Interaction (2015)

Megan Strait and Priscilla Briggs and Matthias Scheutz

Prior work has shown that a robot which uses politeness modifiers in its speech is perceived more favorably by human interactants, as compared to a robot using more direct instructions. However, the findings to-date have been based soley on data aquired from the standard university pool, which may introduce biases into the results.

Covert Robot-Robot Communication: Human Perceptions and Implications for HRI (2015)

Tom Williams and Priscilla Briggs and Matthias Scheutz

As future human-robot teams are envisioned for a variety of application domains, researchers have begun to investigate how humans and robots can communicate effectively and naturally in the context of human-robot team tasks. While a growing body of work is focused on human-robot communication and human perceptions thereof, there is…

Preserving Dignity in Patient Caregiver Relationships Using Moral Emotions and Robots (2014)

Arkin, Ronald C., Scheutz, Matthias and Tickle-Degnen, Linda

This paper provides an overview of an ongoing NSF project that is intended to improve the long-term quality of care for patients suffering from early stage Parkinson's disease. Due to facial masking in the patient, a stigmatization often occurs in their relationship with the caregiver due to the inability to adequately perceive the patient's emotional state.

Virtual Machines: Nonreductionist Bridges Between the Functional and the Physical (2014)

Scheutz, Matthias

Various notions of supervenience have been proposed as a solution to the "mind-body problem" to account for the dependence of mental states on their realizing physical states. In this chapter, we view the mind-body problem as an instance of the more general problem of how a virtual machine (VM) can be implemented in other virtual or physical machines.

Artificial Emotions and Machine Consciousness (2014)

Scheutz, Matthias

The goal of this chapter is to present an overview of the work in AI on emotions and machine consciousness, with an eye toward answering these questions. Starting with a brief philosophical perspective on emotions and machine consciousness to frame the work, the chapter first focuses on artificial emotions, and then moves on to machine…

Using near infrared spectroscopy to index temporal changes in affect in realistic human-robot interactions (2014)

Megan Strait and Matthias Scheutz

Recent work in HRI found that prefrontal hemodynamic activity correlated with participants’ aversions to certain robots. Using a combination of brain-based objective measures and survey-based subjective measures, it was shown that increasing the presence (co-located vs. remote interaction) and human-likeness of the robot engaged greater…

Building a literal bridge between robotics and neuroscience using functional near infrared spectroscopy (2014)

Megan Strait and Matthias Scheutz

Functional near infrared spectroscopy (NIRS) is a promising new tool for research in human-robot interaction (HRI). The use of NIRS in HRI has already been demonstrated both as a means for investigating brain activity during human-robot interactions, as well as in the development of brain-robot interfaces that passively monitor a…

Let me tell you! Investigating the Effects of Robot Communication Strategies in Advice-Giving Situations based on Robot Appearance, Interaction Modality, and Distance (2014)

Megan Strait and Cody Canning and Matthias Scheutz

Recent proposals for how robots should talk to people when they give advice suggest that the same strategies humans employ with other humans are effective for robots as well. However, the evidence is exclusively based on people's observation of robot giving advice to other humans. Hence, it is not clear whether the results still apply…

NIRS-based BCIs: Reliability and Challenges (2014)

Megan Strait and Matthias Scheutz

Previously we contributed to the development of a brain-computer interface (Brainput) using functional near infrared spectroscopy (NIRS). This NIRS-based BCI was designed to improve performance on a human-robot team task by dynamically adapting a robot’s autonomy based on the person’s multitasking state. Two multitasking states…

Reliability of NIRS-based BCIs: a placebo-controlled replication and reanalysis of Brainput (2014)

Megan Strait and Cody Canning and Matthias Scheutz

Near-infrared spectroscopy (NIRS) brain–computer interfaces (BCIs) enable users to interact with their environment using only cognitive activities. This paper presents the results of a comparison of four methodological frameworks used to select a pair of tasks to control a binary NIRS-BCI; specifically, three novel personalized task…

Measuring Users' Responses to Humans, Robots, and Human-like Robots with Functional Near Infrared Spectroscopy (2014)

Megan Strait and Matthias Scheutz

The Uncanny Valley Hypothesis (UVH) describes the sudden change in a person's affect from affinity to aversion that is evoked by robots that border a human-like appearance. The portion of the human-likeness spectrum in which such aversion is posited to occur is referred to as the “uncanny valley”. However, evidence in support of the UVH…

Using functional near infrared spectroscopy to measure moral decision-making: effects of agency, emotional value, and monetary incentive (2014)

Megan Strait and Matthias Scheutz

The prefrontal cortex (PFC) has been investigated extensively with functional magnetic resonance imaging (fMRI) and identified as a neural substrate central to emotion regulation and decision-making, particularly in the context of utilitarian moral dilemmas. However, there are two important limitations to prior work: (1) fMRI imposes…

What we can and cannot (yet) do with functional near infrared spectroscopy (2014)

Megan Strait and Matthias Scheutz

Functional near infrared spectroscopy (NIRS) is a relatively new technique complimentary to EEG for the development of brain-computer interfaces (BCIs). NIRS-based systems for detecting various cognitive and affective states such as mental and emotional stress have already been demonstrated in a range of adaptive human–computer interaction (HCI) applications.

Modeling Blame to Avoid Positive Face Threats in Natural Language Generation (2014)

Gordon Briggs and Matthias Scheutz

Prior approaches to politeness modulation in natural language generation (NLG) often focus on manipulating factors such as the directness of requests that pertain to preserving the autonomy of the addressee (negative face threats), but do not have a systematic way of understanding potential impoliteness from inadvertently critical or…

Learning to Recognize Novel Objects in One Shot through Human-Robot Interactions in Natural Language Dialogues (2014)

Evan Krause and Michael Zillich and Tom Williams and Matthias Scheutz

Being able to quickly and naturally teach robots new knowledge is critical for many future open-world human-robot interaction scenarios. We present a novel approach to using natural language context for one-shot learning of visual objects, where the robot is immediately able to recognize the described object.

Keywords: vision

An Embodied Real-Time Model of Language-Guided Incremental Visual Search (2014)

Matthias Scheutz and Evan Krause and Sepideh Sadeghi

We demonstrate that the incremental presentations of linguistic search cues can speed up visual processing required in visual search. Furthermore, we show that, different from previous hypotheses, the same incremental processing configuration can explain all experimental conditions.

Keywords: vision, learn

Analogical Generalization of Activities from Single Demonstration (2014)

Jason R. Wilson and Matthias Scheutz

Learning new activities (i.e., sequences of actions possibly involving new objects) from single demonstrations is common for humans and would thus be very desirable for future robots as well. However, “one-shot activity learning” is currently still in its infancy and limited to just recording the observed objects and actions of the human demonstrator.

A Dempster-Shafer Theoretic Approach to Understanding Indirect Speech Acts (2014)

Tom Williams and Rafael C. Núñez and Gordon Briggs and Matthias Scheutz and Kamal Premaratne and Manohar N. Murthi

Understanding Indirect Speech Acts (ISAs) is an integral function of human understanding of natural language. Recent attempts at understanding ISAs have used rule-based approaches to map utterances to deep semantics. While these approaches have been successful in handling a wide range of ISAs, they do not take into account the…

Is Robot Telepathy Acceptable? Investigating Effects of Nonverbal Robot-Robot Communication on Human-Robot Interaction (2014)

Tom Williams and Priscilla Briggs and Nathaniel Pelz and Matthias Scheutz

Recent research indicates that other factors in addition to appearance may contribute to the “Uncanny Valley” effect, and it is possible that “uncanny actions” such as “robot telepathy” - the nonverbal exchange of information among multiple robots - could be one such factor. We thus specifically examine whether humans are negatively…

Moral Competence in Social Robots (2014)

Bertram F Malle and Matthias Scheutz

We propose that any robots that collaborate with, look after, or help humans—in short, social robots—must have moral competence. But what does moral competence consist of? We offer a framework for moral competence that attempts to be comprehensive in capturing capacities that make humans morally competent and that therefore represent…

"Think and Do the Right Thing" - A Plea for Morally Competent Autonomous Robots (2014)

Matthias Scheutz and Bertram F Malle

Autonomous robots are increasingly employed in human societies without any provisions for “moral behavior” (other than some implicit architectural protective measures such as to avoid collisions or to follow human orders). However, being part of human societies, these robots will inevitably face morally charged situations, if not moral…

Blame, What is it Good For? (2014)

Gordon Briggs

Blame is an vital social and cognitive mechanism that humans utilize in their interactions with other agents. In this paper, we discuss how blame-reasoning mechanisms are needed to enable future social robots to: (1) appropriately adapt behavior in the context of repeated and/or long-term interactions and relationships with other social…

Actions Speak Louder Than Looks: Does Robot Appearance Affect Human Reactions to Robot Protest and Distress? (2014)

Gordon Briggs and Bryce Gessell and Matthew Dunlap and Matthias Scheutz

People will eventually be exposed to robotic agents that may protest their commands for a wide range of reasons. We present an experiment designed to determine whether a robot's appearance has a significant effect on the amount of agency people ascribed to it and its ability to dissuade a human operator from forcing it to carry out a specific command.

The need for moral competency in autonomous agent architectures (2014)

Matthias Scheutz

Autonomous robots will have to have the capability to make decisions on their own to varying degrees. In this chapter, I will make the plea for developing moral capabilities deeply integrated into the control architectures of such autonomous agents, for I shall argue that any ordinary decision-making situation from daily life can be…

"Teach one, teach all" -- The explosive combination of instructible robots connected via cyber systems (2014)

Matthias Scheutz

Combining robotic architectures with cyber systems has enormous potential for future robotic applications because it enables the possibility of online sharing of all aspects of the robotic architecture: the knowledge contained in architectural components, the parameterization of these components, the very component algorithms, as well as the architectural layout.

How Robots Can Affect Human Behavior: Investigating the Effects of Robotic Displays of Protest and Distress (2014)

Gordon Briggs and Matthias Scheutz

The rise of military drones and other robots deployed in ethically-sensitive contexts has fueled interest in developing autonomous agents that behave ethically. The ability for autonomous agents to independently reason about situational ethics will inevitably lead to confrontations between robots and human operators regarding the…

Investigating Human Perceptions of Robot Capabilities in Remote Human-Robot Team Tasks based on First-Person Robot Video Feeds (2014)

Cody Canning and Thomas J. Donahue and Matthias Scheutz

It is well-known that a robot's appearance and its observable behavior can affect a human interactant's perceptions of the robot's capabilities and propensities in settings where humans and robots are co-located; for remote interactions the specific effects are less clear. Here, we use a remote interaction setting to investigate possible…

Modelling and Fusion of Imperfect Implication Rules (2014)

J. N. Heendeni and K. Premaratne and M. N. Murthi and M. Scheutz

In this paper, we develop a method to find the uncertain consequent by fusing the uncertain antecedent and the uncertain implication rule. In particular with Dempster-Shafer theoretic models utilized to capture the uncertainty intervals associated with the antecedent and the rule itself, we derive bounds on the confidence interval…

Coordination in Human-Robot Teams Using Mental Modeling and Plan Recognition (2014)

Kartik Talamadupula and Gordon Briggs and Tathagata Chakraborti and Matthias Scheutz and Subbarao Kambhampati

Beliefs play an important role in human-robot teaming scenarios, where the robots must reason about other agents' intentions and beliefs in order to inform their own plan generation process, and to successfully coordinate plans with the other agents. In this paper, we cast the evolving and complex structure of beliefs, and inference over…

Reactions of People with Parkinson's Disease to a Robot Interviewer (2014)

Priscilla Briggs and Matthias Scheutz and Linda Tickle-Degnen

In this paper, we outline plans to create a robot capable of ethical mediation of the relationship between people with Parkinson’s disease (PD) and their caregiver to alleviate discrimination due to facial masking, a symptom of PD. We also discuss the initial step in creating the mediator robot: assessing if people with PD would accept…

Ultra-Low Complexity Control for AdHoc Mobile Sensor Networks (2013)

Scheutz, Matthias

We introduce an ultra-low complexity decentralized control scheme for adhoc mobile sensor networks that can be used for a great variety of sensing tasks. Sensor networks using this control scheme are easy to configure, can operate completely autonomously without supervision, and automatically adapt to various environmental changes.

DS-Based Uncertain Implication Rules for Inference and Fusion Applications (2013)

Núñez, Rafael C. and Dabarera, Ranga and Scheutz, Matthias and Briggs, Gordon and Bueno, Otávio and Premaratne, Kamal and Murthi, Manohar N.

Numerous applications rely on implication rules either as models of causal relations among data, or as components of their reasoning and inference systems. Although mature and robust models of implication rules already exist for “perfect” (e.g., boolean) scenarios, there is still a need for improving implication rule models when the data…

Ultra-Low Complexity Control Mechanisms for Sensor Networks and Robotic Swarms (2013)

Scheutz, Matthias and Bauer, Peter

Biologically inspired swarms of autonomous robots have been used successfully in a variety of robotic applications ranging from various kinds of ground-based robots, to unmanned aerial vehicles. Typically, all of these systems use digital communications among swarm agents to implement their behavioral rules (e.g., because they need to…

Keywords: swarm robotics, ultra-low complexity swarms

Annotation of negotiation processes in joint-action dialogues (2013)

Tenbrink, Thora and Eberhard, Kathleen and Shi, Hui and Kuebler, Sandra and Scheutz, Matthias

Situated dialogic corpora are invaluable resources for understanding the complex relationship between language, perception, and action as they are based on naturalistic dialogue situations in which the interactants are given shared goals to be accomplished in the real world. In such situations, verbal interactions are intertwined with…

A NeuroRobotics Approach to Investigating Word Learning Behaviors (2013)

Richard Veale

This chapter presents two examples of how neurorobotics is being used to further understanding of word learning in the human infant. The chapter begins by presenting an example of how neurorobotics has been used to explore the synchrony constraint of word-referent association in young infants. The chapter then demonstrates the…

Linking Cognitive Tokens to Biological Signals: Dialogue Context Improves Neural Speech Recognizer Performance (2013)

Richard Veale and Gordon Briggs and Matthias Scheutz

Novel Mechanisms for Natural Human-Robot Interactions in the DIARC Architecture (2013)

Matthias Scheutz and Gordon Briggs and Rehj Cantrell and Evan Krause and Tom Williams and Richard Veale

Incrementally Biasing Visual Search Using Natural Language Input (2013)

Evan Krause and Rehj Cantrell and Ekaterina Potapova and Michael Zillich and Matthias Scheutz

Humans expect interlocutors both human and robot to resolve spoken references to visually-perceivable objects incrementally as the referents are verbally described. For this reason, tight integration of visual search with natural language processing, and real-time operation of both are requirements for natural interactions between humans and robots.

Keywords: prag, parse, vision

A PDP Model for Capturing N400 Effects in early L2 Learners during Bilingual Word Reading Tasks (2013)

Sepideh Sadeghi and Helen Pu and Matthias Scheutz and Phillip J. Holcomb and Katherine J. Midgley

We propose a computational account of the N400 ERP measure and verify our proposal in the context of a simple PDP model of early bilingual word acquisition as bilingual word acquisition tasks provide several well-established N400 effects that can be used for model validation.

Keywords: sem, learn

Grounding Natural Language References to Unvisited and Hypothetical Locations (2013)

Tom Williams and Rehj Cantrell and Gordon Briggs and Paul Schermerhorn and Matthias Scheutz

A Hybrid Architectural Approach to Understanding and Appropriately Generating Indirect Speech Acts (2013)

Gordon Briggs and Matthias Scheutz

Limitations of NIRS-based BCI for Realistic Applications in Human-Computer Interaction (2013)

Megan Strait and Cody Canning and Matthias Scheutz

Some Correlates of Agency Ascription and Emotional Value and their Effects on Decision-Making (2013)

Megan Strait and Gordon Briggs and Matthias Scheutz

Computational Mechanisms for Mental Models in Human-Robot Interaction (2013)

Matthias Scheutz

Saliency-guided neural prosthesis for visual attention: Design and simulation (2013)

Masatoshi Yoshida and Richard Veale

Recently the authors showed that a computational model of visual saliency could account for changes in gaze behavior of monkeys with damage in the primary visual cortex. Here we propose a neural prosthesis to restore eye gaze behavior by electrically stimulating the superior colliculus to drive visual attention.

A computational model of bilingual inhibitory control in a lexical decision task (2013)

Andrew Valenti and Matthias Scheutz

We model a cognitive process that is hypothesized to explain the language switching cost incurred by bilingual subjects when performing a lexical decision task

Keywords: neural

Exploring Male Spatial Placement Strategies in a Biologically Plausible Mating Task (2013)

Matthias Scheutz and Max Smiley and Sunny Boyd

The strategies employed by animals to choose mates can have significant consequences for individual fitness and also profoundly influence evolutionary processes. Female choice of mates has been a research focus, but males can also influence outcomes in many situations. We have developed an agent-based model to explore how internal and…

Functional Near-Infrared Spectroscopy in Human-Robot Interaction (2013)

Cody Canning and Matthias Scheutz

Functional near-infrared spectroscopy (fNIRS) is a promising new tool for research in human-robot interaction (HRI). The technology has already been used for brain-robot interfaces to affect robots' behaviors and as an evaluation tool for assessing brain activity during interactions. In this survey, we provide a comprehensive literature…

Modeling Uncertainty in First-Order Logic: A Dempster-Shafer Theoretic Approach (2013)

Rafael C. Núñez and Matthias Scheutz and Kamal Premaratne and Manohar N. Murthi

First order logic lies at the core of many methods in mathematics, philosophy, linguistics, and computer science. Although important efforts have been made to extend first order logic to the task of handling uncertainty, there is still a lack of a consistent and unified approach, especially within the Dempster-Shafer (DS) theory framework.

Systematic Integration of Cognitive and Robotic Architectures (2013)

Matthias Scheutz and Jack Harris and Paul Schermerhorn

Originally, progress towards the AI goal of building artificial agents with human-like intelligence was best seen in cognitive architecture research that focused on developing complete agents in a systematic, theory-driven way. Later, research in embodied AI and robotics turned away from this focus on higher-level cognition in favor of…

Classification of Localization Utterances using a Spatial Ontology (2012)

Elahi, Mohammad and Shi, Hui and Bateman, John and Eberhard, Kathleen and Scheutz, Matthias

Dialogue systems for spatially situated tasks need to provide referential descriptions of spatially located objects and understand such descriptions from users. To construct such dialogue systems, it is useful to investigate how humans describe object locations in their immediate environment and how they ask about object locations in remote envi- ronments.

Brainput: Enhancing Interactive Systems with Streaming fNIRS Brain Input (2012)

Solovey, Erin Treacy and Schermerhorn, Paul and Scheutz, Matthias and Sassaroli, Angelo and Fantini, Sergio and Jacob, Robert J.K.

This paper describes the Brainput system, which learns to identify brain activity patterns occurring during multitasking. It provides a continuous, supplemental input stream to an interactive human-robot system, which uses this information to modify its behavior to better support multitasking. This paper demonstrates that we can use…

Mapping the Landscape of Human-Level Artificial General Intelligence (2012)

Sam S. Adams and Itamar Arel and Joscha Bach and Robert Coop and Rod Furlan and Ben Goertzel and J. Storrs Hall and Alexei Samsonovich and Matthias Scheutz and Matthew Schlesinger and Stuart C. Shapiro and John Sowa

Credibility assessment and inference for fusion of hard and soft information (2012)

K. Premaratne and R. Núñez and T. Wickramarathne and M. Murthi and M. Pravia and S. Kuebler and M. Scheutz

Effectively combining multiple (and complementary) sources of information is becoming one of the most promising paths for increased accuracy and more detailed analysis in numerous applications. Neuroscience, business analytics, military intelligence, and sociology are among the areas that could significantly benefit from properly…

New Advances in Asynchronous Agent-based Scheduling (2012)

J. Harris and M. Scheutz

From Teleoperation to Autonomy: "Autonomizing" Non-Autonomous Robots (2012)

Brent Kievit-Kylar and Paul Schermerhorn and Matthias Scheutz

Many complex tasks such as search and rescue, explosive ordinance disposal, etc. that eventually will be performed by autonomous robots are still performed by human operators via teleoperation. Since the requirements of teleoperation are different from those of autonomous operation, design decisions of teleoperation platforms can make it…

What am I doing? Automatic Construction of an Agent's State-Transition Diagram through Introspection (2012)

C. Berzan and M. Scheutz

Infrastructures for implementing agent architectures are currently unaware of what tasks the implemented agent is performing. Such knowledge would allow the infrastructure to improve the agent's autonomy and reliability. For example, the infrastructure could detect abnormal system states, predict likely faults and take preventive…

A Computational PDP Model for Explaining Automatic Imitation (2012)

M. Scheutz and B. Bertenthal

Neural Circuits for Any-Time Phrase Recognition with Applications in Cognitive Models and Human-Robot Interaction (2012)

Richard Veale and Matthias Scheutz

Crossing Boundaries: Multi-Level Introspection in a Complex Robotic Architecture for Automatic Performance Improvements (2012)

Evan Krause and Paul Schermerhorn and Matthias Scheutz

Introspection mechanisms are employed in agent architectures to improve agent performance. However, there is currently no approach to introspection that makes automatic adjustments at multiple levels in the implemented agent system. Our novel multi-level introspection framework can be used to automatically adjust architectural…

Keywords: arch, vision

Tell Me When and Why to Do It!: Run-time Planner Model Updates via Natural Language Instruction (2012)

Rehj Cantrell and Kartik Talamadupula and Paul Schermerhorn and J. Benton and Subbarao Kambhampati and Matthias Scheutz

Robots are currently being used in and developed for critical HRI applications such as search and rescue. In these scenarios, humans operating under changeable and high-stress conditions must communicate effectively with autonomous agents, necessitating that such agents be able to respond quickly and effectively to rapidly-changing conditions and expectations.

Abstract Planning for Reactive Robots (2012)

Saket Joshi and Paul Schermerhorn and Roni Khardon and Matthias Scheutz

Machine Ethics, the Frame Problem, and Theory of Mind (2012)

Gordon Briggs

Multi-modal Belief Updates in Multi-Robot Human-Robot Dialogue Interaction (2012)

Gordon Briggs and Matthias Scheutz

Investigating the Effects of Robotic Displays of Protest and Distress (2012)

Gordon Briggs and Matthias Scheutz

Looking the Part: Social Status Cues Shape Race Perception (2012)

J.B. Freeman and A.M. Penner and A. Saperstein and M. Scheutz and N. Ambady

Adaptive Eye Gaze Patterns in Interactions with Human and Artificial Agents (2012)

Chen Yu and Paul Schermerhorn and Matthias Scheutz

Parallel Syntactic Annotation in CReST (2012)

Sandra Kuebler and Eric Baucom and Matthias Scheutz

Incremental Referent Grounding with NLP-Biased Visual Search (2012)

R. Cantrell and E. Potapova and E. Krause and M. Zillich and M. Scheutz

Human-robot interaction poses tight timing requirements on visual as well as natural language processing in order to allow for natural human-robot interaction. In particular, humans expect robots to incrementally resolve spoken references to visually perceivable objects as the referents are verbally described. We present an integrated…

Keywords: prag, parse, vision

What it is not to implement a computation: A critical analysis of Chalmers' notion of implemention (2012)

Matthias Scheutz

The Affect Dilemma for Artificial Agents: Should We Develop Affective Artificial Agents? (2012)

Matthias Scheutz

Auditory Habituation via Spike-Timing Dependent Plasticity in Recurrent Neural Circuits (2012)

Richard Veale and Matthias Scheutz

Actions Speak Louder than Words: Evaluating Parsers in the Context of Natural Language Understanding Systems for Human-Robot Interaction (2011)

S. Kuebler and R. Cantrell and M. Scheutz

Belief theoretic methods for soft and hard data fusion (2011)

T.L. Wickramarathne and K. Premaratne and M.N. Murthi and M. Scheutz and S. Kuebler and M. Pravia

In many contexts, one is confronted with the problem of extracting information from large amounts of different types soft data (e.g., text) and hard data (from e.g., physics-based sensing systems). In handling hard data, signal and data processing offers a wealth of methods related to modeling, estimation, tracking, and inference tasks.

Disentangling the Effects of Robot Affect, Embodiment, and Autonomy on Human Team Members in a Mixed-Initiative Task (2011)

Paul Schermerhorn and Matthias Scheutz

A Mismatch in the Human Realism of Face and Voice Produces an Uncanny Valley (2011)

Wade Mitchell and Kevin Szerszen and Amy Shirong Lu and Paul Schermerhorn and Matthias Scheutz and Karl MacDorman

Sensing Cognitive Multitasking for a Brain-Based Adaptive User Interface (2011)

Erin Treacy Solovey and Francine Lalooses and Krysta Chauncey and Douglas Weaver and Margarita Parasi and Matthias Scheutz and Angelo Sassaroli and Sergio Fantini and Paul Schermerhorn and Audrey Girouard and Robert J.K. Jacob

Multitasking has become an integral part of work environments, even though people are not well-equipped cognitively to handle numerous concurrent tasks effectively. Systems that support such multitasking may produce better performance and less frustration. However, without understanding the user's internal processes, it is difficult to…

Facilitating Mental Modeling in Collaborative Human-Robot Interaction through Adverbial Cues (2011)

Gordon Briggs and Matthias Scheutz

Planning for Agents with Changing Goals (2011)

Kartik Talamadupula and Paul Schermerhorn and J. Benton and Subbarao Kambhampati and Matthias Scheutz

Planning for Human-Robot Teaming (2011)

Kartik Talamadupula and Subbarao Kambhampati and Paul Schermerhorn and J. Benton and Matthias Scheutz

Learning Actions from Human-Robot Dialogues (2011)

Rehj Cantrell and Paul Schermerhorn and Matthias Scheutz

Temporal, Environmental, and Social Constraints of Word-Referent Learning in Young Infants: A Neurorobotic Model of Multimodal Habituation (2011)

Richard Veale and Paul Schermerhorn and Matthias Scheutz

Architectural Roles of Affect and How to Evaluate Them in Artificial Agents (2011)

Matthias Scheutz

Communicating, Interpreting, and Executing High-Level Instructions for Human-Robot Interaction (2011)

Nishant Trivedi and Pat Langley and Paul Schermerhorn and Matthias Scheutz

In this paper, we address the problem of communicating, interpreting, and executing complex yet abstract instructions to a robot team member. This requires specifying the tasks in an unambiguous manner, translating them into operational procedures, and carrying out those procedures in a persistent yet reactive manner. We report our…

Toward Humanlike Task-Based Dialogue Processing for Human Robot Interaction (2011)

Matthias Scheutz and Rehj Cantrell and Paul Schermerhorn

Evolution of Affect and Communication (2011)

Matthias Scheutz

An Overview of the SimWorld Agent-based Grid Experimentation System (2011)

Matthias Scheutz and Jack Harris

The Inherent Dangers of Unidirectional Emotional Bonds between Humans and Social Robots (2011)

Matthias Scheutz

A Dempster-Shafer Theoretic Evidence Updating Strategy for Non-Identical Frames of Discernment (2010)

T.L. Wickramarathne and K. Premaratne and M.N. Murthi and M. Scheutz

In many contexts, one is confronted with the problem of extracting information from large amounts of different types soft data (e.g., text) and hard data (from e.g., physics-based sensing systems). In handling hard data, signal and data processing offers a wealth of methods related to modeling, estimation, tracking, and inference tasks.

Um...I don't see any: The Function of Filled Pauses and Repairs (2010)

H. Nicholson and K. Eberhard and M. Scheutz

A Multi-Agent System Infrastructure for Large-Scale Autonomous Distributed Real-Time Intelligence Gathering Systems (2010)

Matthias Scheutz

Robust Natural Language Dialogues for Instruction Tasks (2010)

Matthias Scheutz

Being able to understand and carry out spoken natural instructions even in limited domains is extremely challenging for current robots. The difficulties are multifarious, ranging from problems with speech recognizers to difficulties with parsing disfluent speech or resolving references based on perceptual or task-based knowledge.

Investigating Multimodal Real-Time Patterns of Joint Attention in an HRI Word Learning Task (2010)

Chen Yu and Matthias Scheutz and Paul Schermerhorn

A Data-Driven Paradigm to Understand Multimodal Communication in Human-Human and Human-Robot Interaction (2010)

C. Yu and T.G. Smith and S. Hidaka and M. Scheutz and L.B. Smith

Robust Spoken Instruction Understanding for HRI (2010)

Rehj Cantrell and Matthias Scheutz and Paul Schermerhorn and Xuan Wu

The Indiana Cooperative Remote Search Task (CReST) Corpus (2010)

Kathleen Eberhard and Hannele Nicholson and Sandra Kuebler and Susan Gundersen and Matthias Scheutz

Using Logic to Handle Conflicts between System, Component, and Infrastructure Goals in Complex Robotic Architectures (2010)

Paul Schermerhorn and Matthias Scheutz

Adaptive Scheduling Algorithms for the Dynamic Distribution and Parallel Execution of Spatial Agent-Based Models (2010)

Matthias Scheutz and Jack Harris

Who needs time? Implicit timing is sufficient for some HRI tasks (2010)

Richard Veale and Matthias Scheutz

Towards a Conceptual and Methodological Framework for Determining Robot Believability (2010)

Robert Rose and Matthias Scheutz and Paul Schermerhorn

Integrating a Closed World Planner with an Open World Robot: A Case Study (2010)

Kartik Talamadupula and J. Benton and Paul Schermerhorn and Subbarao Kambhampati and Matthias Scheutz

How to pick the right one: Investigating tradeoffs among female mate choice strategies in treefrogs (2010)

Matthias Scheutz and Jack Harris and Sunny K. Boyd

Adding Context Information to Part Of Speech Tagging for Dialogues (2010)

Sandra Kubler and Matthias Scheutz and Eric Baucom and Ross Israel

Planning for Human-Robot Teaming in Open Worlds (2010)

Kartik Talamadupula and J. Benton and Subbarao Kambhampati and Paul Schermerhorn and Matthias Scheutz

The Inherent Dangers of Unidirectional Emotional Bonds between Humans and Social Robots (2009)

M. Scheutz

A Dempster-Shafer theoretic conditional approach to evidence updating for fusion of hard and soft data (2009)

K. Premaratne and M. Murthi and J. Zhang and M. Scheutz and P. Bauer

Symbolic control of attention: Tracking its temporal dynamics (2009)

B. Gibson and M. Scheutz, M and G. Davis

The Impact of Communication and Memory In Hive-based Foraging Agents (2009)

Paul Schermerhorn and Matthias Scheutz

What to do and how to do it: Translating Natural Language Directives into Temporal and Dynamic Logic Representation for Goal Management and Action Execution (2009)

Juraj Dzifcak and Matthias Scheutz and Chitta Baral and Paul Schermerhorn

Affective Goal and Task Selection for Social Robots (2009)

Matthias Scheutz and Paul Schermerhorn

The Utility of Affect in the Selection of Actions and Goals under Real-World Constraints (2009)

Paul Schermerhorn and Matthias Scheutz

Integrating a Closed World Planner with an Open World Robot: A Case Study (2009)

Kartik Talamadupula and J. Benton and Paul Schermerhorn and Rao Kambhampati and Matthias Scheutz

Validating a Real-Time Word Learning Model Tested in USARSim and on a Real Robot (2009)

Richard Veale and Paul Schermerhorn and Matthias Scheutz

A Humanoid-Robotic Replica in USARSim for HRI Experiments (2009)

Kyle Carter and Matthias Scheutz and Paul Schermerhorn

Dissociating Ideomotor and Spatial Compatibility (2009)

T. Boyer and M. Scheutz and B. Bertenthal

Gendered Voice and Robot Entities: Perceptions and Reactions of Male and Female Subjects (2009)

Charles Crowell and Matthias Scheutz and Paul Schermerhorn and Michael Villano

Finding and Exploiting Goal Opportunities in Real-time during Plan Execution (2009)

Paul Schermerhorn and J Benton and Matthias Scheutz and Kartik Talamadupula and Rao Kambhampati

Dynamic Robot Autonomy: Investigating the Effects of Robot Decision-Making in a Human-Robot Team Task (2009)

Paul Schermerhorn and Matthias Scheutz

Robot autonomy is of high relevance for HRI, in particular for interactions of humans and robots in mixed human-robot teams. In this paper, we investigate empirically the extent to which autonomy based on independent decision making and acting by the robot can affect the objective task performance of a mixed human-robot team while being…

Towards a Framework for Integrated Natural Language Processing Architectures for Social Robots (2008)

M. Scheutz and K. Eberhard

Artifical Life Simulations--Discovering Agent-Based Models (2008)

Matthias Scheutz

Physical parameter optimization in swarms of ultra-low complexity agents (2008)

Ryan Connaughton and Paul W. Schermerhorn and Matthias Scheutz

Physical agents (such as wheeled vehicles, UAVs, hovercraft, etc.) with simple control systems are often sensitive to changes in their physical design and control parameters. As such, it is crucial to evaluate the agent's control systems together with the agent's physical implementation. This can consequently lead to an explosion in the…

Empirical Investigations into the Believability of Robot Affect (2008)

Robert Rose and Matthias Scheutz and Paul Schermerhorn

The Limited Utility of Communication in Simple Organisms (2008)

Matthias Scheutz and Paul Schermerhorn

Robot Social Presence and Gender: Do Females View Robots Differently than Males? (2008)

Paul Schermerhorn and Matthias Scheutz and Charles R. Crowell

Social-psychological processes in humans will play an important role in long-term human-robot interactions. This study investigates people's perceptions of social presence in robots during (relatively) short interactions. Findings indicate that males tend to think of the robot as more human-like and accordingly show some evidence of…

Natural Language Interactions in Distributed Networks of Smart Devices (2008)

Paul Schermerhorn and Matthias Scheutz

Combinatorics meets processing power: Large-scale computational resources for BRIMS (2007)

K.A. Gluck and M. Scheutz and G. Gunzelmann and J. Harris and J. Kershner

First Steps toward Natural Human-Like HRI (2007)

Matthias Scheutz and Paul Schermerhorn and James Kramer and David Anderson

Robotic Development Environments for Autonomous Mobile Robots: A Survey (2007)

James Kramer and Matthias Scheutz

Incremental Natural Language Processing for HRI (2007)

Timothy Brick and Matthias Scheutz

Robots that interact with humans face-to-face using natural language need to be responsive to the way humans use language in those situations. We propose a psychologicallyinspired natural language processing system for robots which performs incremental semantic interpretation of spoken utterances, integrating tightly with the robot's…

Reflection and Reasoning Mechanisms for Failure Detection and Recovery in a Distributed Robotic Architecture for Complex Robots (2007)

James Kramer and Matthias Scheutz

Social, Physical, and Computational Tradeoffs in Collaborative Multi-agent Territory Exploration Tasks (2007)

Paul Schermerhorn and Matthias Scheutz

Real-time Hierarchical Swarms for Rapid Adaptive Multi-Level Pattern Detection and Tracking (2007)

Matthias Scheutz

In this paper, we introduce a hierarchical extension to the standard particle swarm optimization algorithm that allows swarms to cope better with dynamically changing fitness evaluations for a given parameter space. We present the formal framework and demonstrate the utility of the extension in an application system for dynamic face detection.

Speech and Action: Integration of Action and Language for Mobile Robots (2007)

Timothy Brick and Paul Schermerhorn and Matthias Scheutz

'Talk to me!': Enabling Communication between Robotic Architectures and their Implementing Infrastructures (2007)

James Kramer and Matthias Scheutz and Paul Schermerhorn

Investigating the Adaptiveness of Communication in Multi-Agent Behavior Coordination (2007)

Paul Schermerhorn and Matthias Scheutz

RADIC -- Towards a General Method for Integrating Reactive and Deliberative Layers (2007)

James Kramer and Matthias Scheutz

The Burden of Embodied Autonomy: Some Reflections on the Social and Ethical Implications of Autonomous Robots (2007)

M. Scheutz and C. Crowell

A Scalable, Robust, Ultra-Low Complexity Agent Swarm for Area Coverage and Interception Tasks (2006)

Scheutz, Matthias and Bauer, Peter

Simulations of biologically inspired swarms where agents jointly achieve tasks using local rules rather than global centralized or distributed control have demonstrated the high performance of agent swarms on a variety of tasks (such as surveillance, plume tracking, or target interception). However, most swarm systems rely on the…

Visual Attention and the Semantics of Space: Evidence for Two Forms of Symbolic Control (2006)

Scheutz, Matthias and Gibson, Bradley

In this paper, we investigate the functional differencesbetween word cues and arrow cues in a spatial cuingtask and provide a novel computational model fit to theempirical data that provides (1) a conceptually parsi-monious explanation of the observed differences and (2)evidence for the existence of two forms of symbolic at-tentional control.