Policy Feedback for the Refinement of Learned Motion Control on a Mobile Robot

Brenna Argall, Brett Browning, and Manuela Veloso
International Journal of Social Robotics, Vol. 4, No. 4, December, 2012, pp. 383-395.


Abstract
Motion control is fundamental to mobile robots, and the associated challenge in development can be assisted by the incorporation of execution experience to increase policy robustness. In this work, we present an approach that updates a policy learned from demonstration with human teacher feedback. We contribute advice-operators as a feedback form that provides corrections on state-action pairs produced during a learner execution, and Focused Feedback for Mobile Robot Policies (F3MRP) as a framework for providing feedback to rapidly-sampled policies. Both are appropriate for mobile robot motion control domains. We present a general feedback algorithm in which multiple types of feedback, including advice-operators, are provided through the F3MRP framework, and shown to improve policies initially derived from a set of behavior examples. A comparison to providing more behavior examples instead of more feedback finds data to be generated in different areas of the state and action spaces, and feedback to be more effective at improving policy performance while producing smaller datasets.

Keywords
Robot learning, Mobile robots, Demonstration learning, Motion control

Notes
Sponsor: Boeing Corporation, BBNT Solutions, Qatar Foundation for Education, Science and Community Development
Associated Center(s) / Consortia: National Robotics Engineering Center
Associated Lab(s) / Group(s): MultiRobot Lab

Text Reference
Brenna Argall, Brett Browning, and Manuela Veloso, "Policy Feedback for the Refinement of Learned Motion Control on a Mobile Robot," International Journal of Social Robotics, Vol. 4, No. 4, December, 2012, pp. 383-395.

BibTeX Reference
@article{Argall_2012_7333,
   author = "Brenna Argall and Brett Browning and Manuela Veloso",
   title = "Policy Feedback for the Refinement of Learned Motion Control on a Mobile Robot",
   journal = "International Journal of Social Robotics",
   pages = "383-395",
   month = "December",
   year = "2012",
   volume = "4",
   number = "4",
}