Header logo is

Learning locomotion over rough terrain using terrain templates

2009

Conference Paper

am


We address the problem of foothold selection in robotic legged locomotion over very rough terrain. The difficulty of the problem we address here is comparable to that of human rock-climbing, where foot/hand-hold selection is one of the most critical aspects. Previous work in this domain typically involves defining a reward function over footholds as a weighted linear combination of terrain features. However, a significant amount of effort needs to be spent in designing these features in order to model more complex decision functions, and hand-tuning their weights is not a trivial task. We propose the use of terrain templates, which are discretized height maps of the terrain under a foothold on different length scales, as an alternative to manually designed features. We describe an algorithm that can simultaneously learn a small set of templates and a foothold ranking function using these templates, from expert-demonstrated footholds. Using the LittleDog quadruped robot, we experimentally show that the use of terrain templates can produce complex ranking functions with higher performance than standard terrain features, and improved generalization to unseen terrain.

Author(s): Kalakrishnan, M. and Buchli, J. and Pastor, P. and Schaal, S.
Book Title: Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on
Pages: 167-172
Year: 2009

Department(s): Autonomous Motion
Research Project(s): Inverse Optimal Control
Bibtex Type: Conference Paper (inproceedings)

Cross Ref: p10333
Note: clmc
URL: http://www-clmc.usc.edu/publications/K/kalakrishnan-IROS2009.pdf

BibTex

@inproceedings{Kalakrishnan_IRSIIIC_2009,
  title = {Learning locomotion over rough terrain using terrain templates},
  author = {Kalakrishnan, M. and Buchli, J. and Pastor, P. and Schaal, S.},
  booktitle = {Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on},
  pages = {167-172},
  year = {2009},
  note = {clmc},
  doi = {},
  crossref = {p10333},
  url = {http://www-clmc.usc.edu/publications/K/kalakrishnan-IROS2009.pdf}
}