Learning to Generate Cost-to-Go Functions for Efficient Motion Planning

Jinwook Huh, Galen Xing, Ziyun Wang, Volkan Isler, Daniel D. Lee

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Traditional motion planning can be computationally burdensome for practical robots, due to extensive collision checking and considerable iterative propagation of cost values. We present a novel neural network architecture which can directly generate the cost-to-go (c2g) function for a given configuration space and a goal configuration. The output of the network is a continuous function whose gradient in configuration space can be directly used to generate trajectories in motion planning without the need for protracted iterations or extensive collision checking. This higher order function (i.e. a function generating another function) representation lies at the core of our motion planning architecture, c2g-HOF, which can take a workspace as input, and generate the cost-to-go function over the configuration space map (C-map). Simulation results for 2D and 3D environments show that c2g-HOF can be orders of magnitude faster at execution time than methods which explore the configuration space during execution. We also present an implementation of c2g-HOF which generates trajectories for robot manipulators directly from an overhead image of the workspace.

Original languageEnglish (US)
Title of host publicationSpringer Proceedings in Advanced Robotics
PublisherSpringer Science and Business Media B.V.
Pages555-565
Number of pages11
DOIs
StatePublished - 2021
Externally publishedYes

Publication series

NameSpringer Proceedings in Advanced Robotics
Volume19
ISSN (Print)2511-1256
ISSN (Electronic)2511-1264

Bibliographical note

Publisher Copyright:
© 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Fingerprint

Dive into the research topics of 'Learning to Generate Cost-to-Go Functions for Efficient Motion Planning'. Together they form a unique fingerprint.

Cite this