The Robotics Institute

Carnegie Mellon Robotics Institute

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract

As robots become more commonplace within so- ciety, the need for tools that enable non-robotics-experts to develop control algorithms, or policies, will increase. Learning from Demonstration (LfD) offers one promising approach, where the robot learns a policy from teacher task executions. In this work we present an algorithm that incorporates human teacher feedback to enable policy improvement from learner experience within an LfD framework. We present two imple- mentations of this algorithm, that differ in the sort of teacher feedback they provide. In the first implementation, called Binary Critiquing (BC), the teacher provides a binary indication that highlights poorly performing portions of the execution. In the second implementation, called Advice-Operator Policy Im- provement (A-OPI), the teacher provides a correction on poorly performing portions of the student execution. Most notably, these corrections are continuous-valued and appropriate for low level motion control action spaces. The algorithms are applied to validation domains, one simulated and one a Segway RMP platform. For both, policy performance is found to improve with teacher feedback. Specifically, with BC learner execution success and efficiency come to exceed teacher performance. With A-OPI task success and accuracy are shown to be similar or superior to the typical LfD approach of correcting behavior through more teacher demonstrations.

Keywords

learning robot motion control, learning from demonstration, teacher feedback

Notes

Sponsor: the Boeing Company. Carnegie-Mellon University in Qatar and the Qatar Foundation

Associated Lab(s) / Group(s): MultiRobot Lab

Associated Project(s): Treasure Hunt: Pickup Teams

Text Reference

Brenna Argall, Brett Browning, and Manuela Veloso, "Learning robot motion control from demonstration and human advice," the AAAI Spring Symposium, 2009.

BibTeX Reference

@inproceedings{Argall_2009_6994,
   author = "Brenna Argall and Brett Browning and Manuela Veloso",
   title = "Learning robot motion control from demonstration and human advice",
   booktitle = "the AAAI Spring Symposium",
   year = "2009",
}

The Robotics Institute

Menu