Global motion planning under uncertain motion, sensing, and environment map

Kurniawati, Hanna, Bandyopadhyay, Tirthankar and Patrikalakis, Nicholas M. (2011). Global motion planning under uncertain motion, sensing, and environment map. In: Hugh Durrant-Whyte, Nicholas Roy and Pieter Abbeel, Robotics: Science and Systems VII. Robotics: Science and Systems VII, Los Angeles, CA, United States, (). 27-30 June 2011.

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
GlobalMotionPlanning.pdf Full text (open access) application/pdf 434.46KB 0
Author Kurniawati, Hanna
Bandyopadhyay, Tirthankar
Patrikalakis, Nicholas M.
Title of paper Global motion planning under uncertain motion, sensing, and environment map
Conference name Robotics: Science and Systems VII
Conference location Los Angeles, CA, United States
Conference dates 27-30 June 2011
Proceedings title Robotics: Science and Systems VII
Place of Publication Cambridge, MA, United States
Publisher MIT Press, Cambridge, Massachusetts, 2012
Publication Year 2011
Sub-type Fully published paper
Open Access Status
ISBN 0262517795
Editor Hugh Durrant-Whyte
Nicholas Roy
Pieter Abbeel
Total pages 8
Language eng
Abstract/Summary Motion planning that takes into account uncertainty in motion, sensing, and environment map, is critical for autonomous robots to operate reliably in our living spaces. Partially Observable Markov Decision Processes (POMDPs) is a principled and general framework for planning under uncertainty. Although recent development of point-based POMDPs have drastically increased the speed of POMDP planning, even the best POMDP planner today, fails to generate reasonable motion strategies when the environment map is not known exactly. This paper presents Guided Cluster Sampling (GCS), a new point-based POMDP planner for motion planning with uncertain motion, sensing, and environment map, when the robot has active sensing capability. It uses our observations that in this problem, the belief space B can be partitioned into a collection of much smaller sub-spaces, and an optimal policy can often be generated by sufficient sampling of a small subset of the collection. GCS samples B using two-stage cluster sampling, a subspace is sampled from the collection and then a belief is sampled from the subspace. It uses information from the set of sampled sub-spaces and sampled beliefs to guide subsequent sampling. Preliminary results suggest that GCS generates reasonable policies for motion planning problems with uncertain motion, sensing, and environment map, that are unsolvable by the best point-based POMDP planner today, within reasonable time. Furthermore, GCS handles POMDPs with continuous state, action, and observation spaces. We show that for a class of POMDPs that often occur in robot motion planning, GCS converges to the optimal policy, given enough time. To the best of our knowledge, this is the first convergence result for point-based POMDPs with continuous action space.
Keyword Motion planning under uncertainty
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status Non-UQ
Additional Notes

Version Filter Type
Citation counts: Google Scholar Search Google Scholar
Created: Tue, 15 Apr 2014, 16:39:32 EST by Ms Kimberley Nunes on behalf of Centre for Medical Diagnostic Technologies in Qld