Motion planning under uncertainty for robotic tasks with long time horizons

Kurniawati, Hanna, Du, Yanzhu, Hsu, David and Lee, Wee Sun (2011) Motion planning under uncertainty for robotic tasks with long time horizons. International Journal of Robotics Research, 30 3: 308-323. doi:10.1177/0278364910386986

Author Kurniawati, Hanna
Du, Yanzhu
Hsu, David
Lee, Wee Sun
Title Motion planning under uncertainty for robotic tasks with long time horizons
Journal name International Journal of Robotics Research   Check publisher's open access policy
ISSN 0278-3649
Publication date 2011-03-01
Sub-type Article (original research)
DOI 10.1177/0278364910386986
Open Access Status Not yet assessed
Volume 30
Issue 3
Start page 308
End page 323
Total pages 16
Place of publication London, United Kingdom
Publisher Sage
Language eng
Formatted abstract
Motion planning with imperfect state information is a crucial capability for autonomous robots to operate reliably in uncertain and dynamic environments. Partially observable Markov decision processes (POMDPs) provide a principled general framework for planning under uncertainty. Using probabilistic sampling, point-based POMDP solvers have drastically improved the speed of POMDP planning, enabling us to handle moderately complex robotic tasks. However, robot motion planning tasks with long time horizons remains a severe obstacle for even the fastest point-based POMDP solvers today. This paper proposes Milestone Guided Sampling (MiGS), a new point-based POMDP solver, which exploits state space information to reduce effective planning horizons. MiGS samples a set of points, called milestones, from a robot's state space and constructs a simplified representation of the state space from the sampled milestones. It then uses this representation of the state space to guide sampling in the belief that space and tries to capture the essential features of the belief space with a small number of sampled points. Preliminary results are very promising. We tested MiGS in simulation on several difficult POMDPs that model distinct robotic tasks with long time horizons in both 2-D and 3-D environments. These POMDPs are impossible to solve with the fastest point-based solvers today, but MiGS solved them in a few minutes.
Keyword Motion planning under uncertainty
Robot motion planning
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status Non-UQ
Additional Notes Fully published conference paper

Document type: Journal Article
Sub-type: Article (original research)
Collection: School of Information Technology and Electrical Engineering Publications
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 33 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 45 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 15 Apr 2014, 06:48:11 EST by Ms Kimberley Nunes on behalf of Centre for Medical Diagnostic Technologies in Qld