Learning predictive terrain models for legged robot locomotion
- 1 September 2008
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3545-3552
- https://doi.org/10.1109/iros.2008.4651026
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.Keywords
This publication has 5 references indexed in Scilit:
- Multi-Level Surface Maps for Outdoor Terrain Mapping and Loop ClosingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Hybrid PRM Sampling with a Cost-Sensitive Adaptive StrategyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Gaussian process models for sensor-centric robot localisationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Data processing algorithms for generating textured 3D building facade meshes from laser scans an camera imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Probabilistic roadmaps for path planning in high-dimensional configuration spacesIEEE Transactions on Robotics and Automation, 1996