A Testbed for Adaptive Human-Robot Collaboration

Abstract. This paper presents a novel method for developing and evaluating intelligent robot behavior for joint human-robot activities. We extended a physical simulation of an autonomous robot to interact with a second, human-controlled agent as in a computer game. We have conducted a user study to demonstrate the viability of the approach for adaptive human-aware planning for collaborative everyday activities. The paper presents the details of our simulation and its control for human subjects as well as results of the user study. 1 Motivation Robots that are to interact with humans need to be highly adaptive towards their environment. They have to adapt their behavior to different human individuals, have to respect social rules and respond to human expectations, react to unexpected human actions, and show a high degree of safety, even for unanticipated events. In our research we aim to develop adaptive, model-based planning and plan-execution mechanisms for autonomous robots that are ...

• Type: Journal
• Year: 2010
• Where: KI
• Authors: Alexandra Kirsch, Yuxiang Chen
• Keywords: Artificial Intelligence, Autonomous Robots, Human, KI 2010, Robots