The Robotics Institute
Search the site
RI | Publications | Policy-contingent abstraction for robust robot control

Text only version of this site

Policy-contingent abstraction for robust robot control
J. Pineau, G. Gordon, and S. Thrun
Conference on Uncertainty in Articifical Intelligence (UAI), August, 2003, pp. 477 - 484.

Jump to: Download | Abstract | Notes | Text Reference | BibTeX Reference

Download [Help]

Adobe portable document format (pdf) [279 KB]
Compressed postscript (ps.gz) [464 KB]

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

This paper presents a scalable control algorithm that enables a deployed mobile robot to make high-level control decisions under full consideration of its probabilistic belief. We draw on insights from the rich literature of structured robot controllers and hierarchical MDPs to propose PolCA, a hierarchical probabilistic control algorithm which learns both subtask-specific state abstractions and policies. The resulting controller has been successfully implemented onboard a mobile robotic assistant deployed in a nursing facility. To the best of our knowledge, this work is a unique instance of applying POMDPs to high-level robotic control problems.

Notes

Associated center: MRTC
Associated lab/group: Robot Learning Lab
Associated project: Personal Robotic Assistants For The Elderly

Number of pages: 8

Text Reference

J. Pineau, G. Gordon, and S. Thrun, "Policy-contingent abstraction for robust robot control," Conference on Uncertainty in Articifical Intelligence (UAI), August, 2003, pp. 477 - 484.

BibTeX Reference

@inproceedings{Pineau_2003_4827,
   author = "Joelle Pineau and Geoffrey Gordon and Sebastian Thrun",
   title = "Policy-contingent abstraction for robust robot control",
   booktitle = "Conference on Uncertainty in Articifical Intelligence (UAI)",
   month = "August",
   year = "2003",
   pages = "477 - 484"
}


The Robotics Institute is part of the School of Computer Science, Carnegie Mellon University.
For updates and comments, please see these instructions.
This page maintained by robotwebmaster@ri.cmu.edu