DMCA
Learning Predictive Terrain Models for Legged Robot Locomotion
| Citations: | 13 - 0 self |
BibTeX
@MISC{Plagemann_learningpredictive,
author = {Christian Plagemann and Sebastian Mischke and Sam Prentice and Kristian Kersting and Nicholas Roy and Wolfram Burgard},
title = {Learning Predictive Terrain Models for Legged Robot Locomotion},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract — Legged robots require accurate models of their environment in order to plan and execute paths. We present a probabilistic technique based on Gaussian processes that allows terrain models to be learned and updated efficiently using sparse approximation techniques. The major benefit of our terrain model is its ability to predict elevations at unseen locations more reliably than alternative approaches, while it also yields estimates of the uncertainty in the prediction. In particular, our nonstationary Gaussian process model adapts its covariance to the situation at hand, allowing more accurate inference of terrain height at points that have not been observed directly. We show how a conventional motion planner can use the learned terrain model to plan a path to a goal location, using a terrain-specific cost model to accept or reject candidate footholds. In experiments with a real quadruped robot equipped with a laser range finder, we demonstrate the usefulness of our approach and discuss its benefits compared to simpler terrain models such as elevations grids. I.
Keyphrases
terrain model legged robot locomotion predictive terrain model abstract legged robot gaussian process real quadruped robot terrain height terrain-specific cost model nonstationary gaussian process model major benefit probabilistic technique accurate inference sparse approximation technique laser range finder candidate foothold learned terrain model goal location unseen location conventional motion planner elevation grid execute path alternative approach accurate model
