Optimizing search engines using clickthrough data
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
A short introduction to learning with kernels
Advanced lectures on machine learning
Feature selection, L1 vs. L2 regularization, and rotational invariance
ICML '04 Proceedings of the twenty-first international conference on Machine learning
An Interior-Point Method for Large-Scale l1-Regularized Logistic Regression
The Journal of Machine Learning Research
Journal of Artificial Intelligence Research
Compliant quadruped locomotion over rough terrain
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Compliant quadruped locomotion over rough terrain
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Optimization and learning for rough terrain legged locomotion
International Journal of Robotics Research
Learning, planning, and control for quadruped locomotion over challenging terrain
International Journal of Robotics Research
Comprehensive summary of the Institute for Human and Machine Cognition's experience with LittleDog
International Journal of Robotics Research
Supporting locomotive functions of a six-legged walking robot
International Journal of Applied Mathematics and Computer Science - SPECIAL SECTION: Efficient Resource Management for Grid-Enabled Applications
Learning of grasp selection based on shape-templates
Autonomous Robots
Hi-index | 0.00 |
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.