Using motion primitives in probabilistic sample-based planning for humanoid robots

Published

Conference Paper

This paper presents a method of computing efficient and natural-looking motions for humanoid robots walking on varied terrain. It uses a small set of high-quality motion primitives (such as a fixed gait on flat ground) that have been generated offline. But rather than restrict motion to these primitives, it uses them to derive a sampling strategy for a probabilistic, sample-based planner. Results in simulation on several different terrains demonstrate a reduction in planning time and a marked increase in motion quality. © 2008 Springer-Verlag Berlin Heidelberg.

Full Text

Duke Authors

Cited Authors

  • Hauser, K; Bretl, T; Harada, K; Latombe, JC

Published Date

  • October 20, 2008

Published In

Volume / Issue

  • 47 /

Start / End Page

  • 507 - 522

Electronic International Standard Serial Number (EISSN)

  • 1610-742X

International Standard Serial Number (ISSN)

  • 1610-7438

International Standard Book Number 13 (ISBN-13)

  • 9783540684046

Digital Object Identifier (DOI)

  • 10.1007/978-3-540-68405-3_32

Citation Source

  • Scopus