Date: Thursday, February 1st, 2024

Time: 2:00 PM – 3:30 PM EST

Location: Montgomery-Knight Room 317, or Zoom

Jack Kolb

Robotics Ph.D. Student

Georgia Institute of Technology

Committee:

Dr. Karen M. Feigh (Advisor) – School of Aerospace Engineering, Georgia Institute of Technology

Dr. Sonia Chernova – School of Interactive Computing, Georgia Institute of Technology

Dr. Harish Ravichandar – School of Interactive Computing, Georgia Institute of Technology

Dr. Julie A. Adams – Department of Electrical Engineering and Computer Science, Oregon State University

Dr. Alan R. Wagner – Department of Aerospace Engineering, Pennsylvania State University

Abstract:

Robots are increasingly deployed to support individuals in high-workload or closely collaborative environments across various operational domains. However, limited research has explored how robots can actively leverage a user's cognitive state to personalize their support. In human-human teams, we consider our teammates' cognitive state and individual capabilities to guide team dynamics, enhancing team fluency and proactivity. Human cognition is challenging to define, measure, and influence, making the integration of user cognition into human-robot interactions non-trivial. This thesis explores how robots can incorporate their human teammates' cognitive states as an integral part of their planning and interactions. Specifically, this thesis contributes to defining and utilizing cognitive states by: 1) measuring and applying the user's cognitive skills to predict their future robot operation performance and facilitate role assignment, 2) monitoring the user's real-time cognitive workload to dynamically adapt the robot's level of autonomy in high-workload scenarios, and 3) estimating the user's belief state to assess their situation awareness and inform task-pertinent questions.