Learning robot motion control with demonstration and advice-operators

Brenna D. Argall, Brett Browning, Manuela Veloso

Research output: Chapter in Book/Report/Conference proceedingConference contribution

49 Scopus citations

Abstract

As robots become more commonplace within society, the need for tools to 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. Our interests lie with robot motion control policies which map world observations to continuous low-level actions. In this work, we introduce Advice-Operator Policy Improvement (A-OPI) as a novel approach for improving policies within LfD. Two distinguishing characteristics of the A-OPI algorithm are data source and continuous state-action space. Within LfD, more example data can improve a policy. In A-OPI, new data is synthesized from a student execution and teacher advice. By contrast, typical demonstration approaches provide the learner with exclusively teacher executions. A-OPI is effective within continuous state-action spaces because high level human advice is translated into continuous-valued corrections on the student execution. This work presents a first implementation of the AOPI algorithm, validated on a Segway RMP robot performing a spatial positioning task. A-OPI is found to improve task performance, both in success and accuracy. Furthermore, performance is shown to be similar or superior to the typical exclusively teacher demonstrations approach.

Original languageEnglish (US)
Title of host publication2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
Pages399-404
Number of pages6
DOIs
StatePublished - Dec 1 2008
Event2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS - Nice, France
Duration: Sep 22 2008Sep 26 2008

Publication series

Name2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS

Other

Other2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
CountryFrance
CityNice
Period9/22/089/26/08

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Learning robot motion control with demonstration and advice-operators'. Together they form a unique fingerprint.

  • Cite this

    Argall, B. D., Browning, B., & Veloso, M. (2008). Learning robot motion control with demonstration and advice-operators. In 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS (pp. 399-404). [4651020] (2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS). https://doi.org/10.1109/IROS.2008.4651020