Published in

Springer Tracts in Advanced Robotics, p. 507-522

DOI: 10.1007/978-3-540-68405-3_32

Links

Tools

Export citation

Search in Google Scholar

Using Motion Primitives in Probabilistic Sample-Based Planning for Humanoid Robots

Proceedings article published in 2008 by Kris K. Hauser, Timothy Bretl, Kensuke Harada, Jean-Claude Latombe
This paper is available in a repository.
This paper is available in a repository.

Full text: Download

Question mark in circle
Preprint: policy unknown
Upload
Question mark in circle
Postprint: policy unknown
Upload
Question mark in circle
Published version: policy unknown
Upload

Abstract

This paper presents a method of computing ecient 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 gen- erated oine. But rather than restrict motion to these primitives, it uses them to derive a sampling strategy for a probabilistic, sample-based planner. Results in sim- ulation on several dierent terrains demonstrate a reduction in planning time and a marked increase in motion quality.