Research interests focus on developing reliable, highly autonomous systems (especially mobile robots) that operate in rich, uncertain environments. The goal is to create intelligent systems that can operate autonomously for long periods of time in unstructured, natural environments. This necessitates robots that can plan, effectively reason about uncertainty, diagnose and recover from unanticipated errors, reason about their limitations, and interact effectively and naturally with people and with other robots.

• Robust, Self-Reliant Behavior We are investigating methods for making mobile robots more robust and self-reliant by having them reason about their own capabilities and limitations and learn to become more proficient at achieving tasks. In particular, we are exploring the use of a hierarchy of models to efficiently generate robust plans, detecting and repairing models that are inaccurate, using simulation to understand the extent of the robot’s expertise under different contexts, and active learning from humans to create robust policies for achieving tasks.
• Human-Robot Social Interaction. The goal here is to make robots more useful and acceptable by enabling them to interact with humans using social rules and conventions. We are interested in socially acceptable navigation (e.g., passing in corridors, approaching people, riding in elevators, escorting visitors) and non-verbal signaling of internal robot state, such as emotion and attitude towards people or the task it is performing.In conjunction with members of the School of Drama, we are also developing conversation robots that are deployed in public spaces 24/7, including a “robot receptionist,” deployed in Newell-Simon Hall, that interacts with visitors and building inhabitants providing directions, weather information, and chats about its “personal life”, and a game-playing robot, deployed in Gates Hillman Center, that interacts with multiple people while playing Scrabble, chatting about the game and displaying different moods. Research issues include providing robots with character and personality, non-verbal communication, and personalizing human-robot interaction.

We are also investigating approaches to explaining robot behavior, including explaining why a policy is optimal and why expert data analysts perform better than novices.

• Multi-Robot Coordination. We are researching issues of how multiple, heterogeneous robots can coordinate to carry out high-level tasks, especially those that cannot be accomplished by a single robot. Issues include having the robots negotiate to dynamically form teams and assign tasks, monitoring each others performance, and adapting dynamically to changing situations. Current focus is on automated assembly of large structures, such as airplane wings.