Open-World Novelty Detection, Characterization, and Accommodation

Open-world AI requires artificial agents to be able to handle novelties that arise during task performance, i.e., agents must detect novelties and characterize them in order to be able to accommodate them effectively, especially in cases where sudden changes to the environment make task accomplishment impossible without utilizing the novelty. In this project, we are developing algorithms for all aspects of a formal framework and implementation thereof in a cognitive agent for novelty handling and demonstrate the efficacy of the proposed methods in various open-world tasks, including a crafting task in Minecraft.

Keywords: novelty handling, fault detection, fault recovery, problem solving, life-long learning, diarc

Details

Towards Trusted Human-Like Artificial Teammates

Today's autonomous systems are still at the level of tools, not that of human-like teammates. In this project, we are developing algorithms and architectures that lay the foundations for future autonomous systems in mixed-initiative human-machine teams to be able to operate at human-like levels of interactivity and effectiveness. We are integrating measurements of neurophysiological signals from human teammates with multiple additional measurements and situational contextual information to classify various individual and team cognitive states. Classified cognitive states of all teammates are individually tracked and fused in real-time, and integrated into a shared mental model which uses advanced probabilistic "theory of mind" representations to capture team and task states with their associated uncertainties, and supports the decision- making and behavior adaptations of the autonomous artificial teammates.

Keywords: human-machine teaming, workload detection, physiological sensors, natural language understanding and tasking, epistemic planning, shared mental models, diarc

Details

Self-Assessment and Resilience

Long-term autonomous operation requires robots to be aware of their own performance and detect faults that might impede their goals. In this project, we are developing introspective algorithms for performance assessing under uncertainty, as well as fault detection and recovery in order to enable robots to become more resilient to perturbations in their environment.

Keywords: self-assessment, fault detection, fault recovery, resilience, autonomy, diarc

Details

A Unifying AI Architectural Framework for Developing Complex Autonomous Robotic Teammates

In this project we are developing a comprehensive AI architectural framework that is at once versatile, extensible, and scalable, and enables human-like mixed-initiative human-robot interactions at human-like levels of interactivity and effectiveness. The framework, based on our DIARC architecture, will allow AI researchers and roboticists to evaluate their component algorithms on a large number of robots without having to develop a complete architecture simply by adding their component to DIARC or substituting it for an existing DIARC component using standardized interfaces.

Keywords: diarc, architecture framework, human-machine teaming, algorithm evaluations

Details