CaltechAUTHORS
  A Caltech Library Service

Learning an Optimal Sampling Distribution for Efficient Motion Planning

Cheng, Richard and Shankar, Krishna and Burdick, Joel W. (2020) Learning an Optimal Sampling Distribution for Efficient Motion Planning. In: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE , Piscataway, NJ, pp. 7485-7492. ISBN 9781728162126. https://resolver.caltech.edu/CaltechAUTHORS:20210216-103002378

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20210216-103002378

Abstract

Sampling-based motion planners (SBMP) are commonly used to generate motion plans by incrementally constructing a search tree through a robot’s configuration space. For high degree-of-freedom systems, sampling is often done in a lower-dimensional space, with a steering function responsible for local planning in the higher-dimensional configuration space. However, for highly-redundant sytems with complex kinematics, this approach is problematic due to the high computational cost of evaluating the steering function, especially in cluttered environments. Therefore, having an efficient, informed sampler becomes critical to online robot operation. In this study, we develop a learning-based approach with policy improvement to compute an optimal sampling distribution for use in SBMPs. Motivated by the challenge of whole-body planning for a 31 degree-of-freedom mobile robot built by the Toyota Research Institute, we combine our learning-based approach with classical graph-search to obtain a constrained sampling distribution. Over multiple learning iterations, the algorithm learns a probability distribution weighting areas of low-cost and high probability of success, which a graph search algorithm then uses to obtain an optimal sampling distribution for the robot. On challenging motion planning tasks for the robot, we observe significant computational speed-up, fewer edge evaluations, and more efficient paths with minimal computational overhead. We show the efficacy of our approach with a number of experiments in whole-body motion planning.


Item Type:Book Section
Related URLs:
URLURL TypeDescription
https://doi.org/10.1109/IROS45743.2020.9341245DOIArticle
https://ieeexplore.ieee.org/document/9341245PublisherArticle
ORCID:
AuthorORCID
Cheng, Richard0000-0001-8301-9169
Additional Information:© 2020 IEEE.
Record Number:CaltechAUTHORS:20210216-103002378
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20210216-103002378
Official Citation:R. Cheng, K. Shankar and J. W. Burdick, "Learning an Optimal Sampling Distribution for Efficient Motion Planning," 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA, 2020, pp. 7485-7492, doi: 10.1109/IROS45743.2020.9341245
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:108063
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:16 Feb 2021 18:44
Last Modified:16 Feb 2021 18:44

Repository Staff Only: item control page