Becoming Team Members: Identifying Interaction Patterns of Mutual Adaptation for Human-Robot Co-Learning

Area of Science:

• Human-Robot Interaction
• Artificial Intelligence
• Cognitive Science

Background:

• Effective teamwork relies on continuous collaborative learning among all members.
• Co-learning involves iterative stages of co-adaptation and communication.
• Understanding co-adaptation is crucial for advancing human-robot team performance.

Purpose of the Study:

• To develop a method for identifying recurring behaviors indicative of co-learning in human-robot teams.
• To investigate the co-adaptation stage of co-learning within a human-robot team context.
• To establish a research framework for studying co-adaptation in human-robot teams.

Main Methods:

• Designed a simplified computer simulation of an urban search and rescue task.
• A human participant collaborated with a virtual robot to rescue victims.
• Recorded and analyzed interaction patterns between the human and robot during the task.

Main Results:

• Identified specific interaction patterns reflecting behavioral adaptation between human and robot.
• Demonstrated that the simulated task environment facilitates the study of co-learning.
• Observed that greater participant adaptation led to improved robot learning and team performance.

Conclusions:

• The developed method and task environment enable the study of co-learning in human-robot teams.
• Identified interaction patterns provide a foundation for human-robot communication regarding co-adaptation.
• Future research will explore communication processes to further enhance co-learning in human-robot teams.