A Caltech Library Service

Learning to Plan Near-Optimal Collision-Free Paths

Ho, Alex W. and Fox, Geoffrey C. (1990) Learning to Plan Near-Optimal Collision-Free Paths. In: Proceedings of the Fifth Distributed Memory Computing Conference, 1990. IEEE , Piscataway, NJ, pp. 131-139. ISBN 0-8186-2113-3.

[img] PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


A new approach to find a near-optimal collision-free path is presented. The path planner is an implementation of the adaptive error back-propagation algorithm which learns to plan “good”, if not optimal, collision-free paths from human-supervised training samples. Path planning is formulated as a classification problem in which class labels are uniquely mapped onto the set of maneuverable actions of a robot or vehicle. A multi-scale representational scheme maps physical problem domains onto an arbitrarily chosen fixed size input layer of an error back-propagation network. The mapping does not only reduce the size of the computation domain, but also ensures applicability of a trained network over a wide range of problem sizes. Parallel implementation of the neural network path planner on hypercubes or Transputers based on Parasoft EXPRESS is simple and efficient, Simulation results of binary terrain navigation indicate that the planner performs effectively in unknown environment in the test cases.

Item Type:Book Section
Related URLs:
URLURL TypeDescription
Additional Information:© 1990 IEEE. This study is based on research work supported by the Joint Tactical Fusion Program Manager.
Funding AgencyGrant Number
Joint Tactical Fusion ProgramUNSPECIFIED
Record Number:CaltechAUTHORS:20170626-173626448
Persistent URL:
Official Citation:A. W. Ho and G. C. Fox, "Learning to Plan Near-Optimal Collision-Free Paths," Proceedings of the Fifth Distributed Memory Computing Conference, 1990., 1990, pp. 131-139. doi: 10.1109/DMCC.1990.555374
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:78584
Deposited By: Kristin Buxton
Deposited On:27 Jun 2017 19:56
Last Modified:15 Nov 2021 17:41

Repository Staff Only: item control page