Efficient behavior learning in human–robot collaboration. Issue 5 (June 2018)

• Record Type: Journal Article
• Authors: Munzer, Thibaut; Toussaint, Marc; Lopes, Manuel
• Is Part Of: Autonomous robots. Volume 42:Issue 5(2018)
• Page Start: 1103
• Page End: 1115
• Publication Date: 2018-06
• Subjects: Interactive learning -- Human–robot collaboration -- Relational learning
• DOI: 10.1007/s10514-017-9674-5
• Languages: English
• ISSNs: 0929-5593

Abstract

Abstract We present a novel method for a robot to interactively learn, while executing, a joint human–robot task. We consider collaborative tasks realized by a team of a human operator and a robot helper that adapts to the human's task execution preferences. Different human operators can have different abilities, experiences, and personal preferences so that a particular allocation of activities in the team is preferred over another. Our main goal is to have the robot learn the task and the preferences of the user to provide a more efficient and acceptable joint task execution. We cast concurrent multi-agent collaboration as a semi-Markov decision process and show how to model the team behavior and learn the expected robot behavior. We further propose an interactive learning framework and we evaluate it both in simulation and on a real robotic setup to show the system can effectively learn and adapt to human expectations.