Learning locomotion over rough terrain using terrain templates

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.

Authors

• Mrinal Kalakrishnan
• Jonas Buchli
• Peter Pastor
• Stefan Schaal

Keywords

• Legged locomotion
• USA Councils
• Intelligent robots
• Biomedical computing
• Foot
• Leg
• Neuroscience
• Biomedical engineering
• Humans
• Biological control systems
• Rough Terrain
• Learning Locomotion
• Length Scale
• Combination Of Features
• Landforms
• Reward Function
• Work Domain
• Problem Difficulty
• Use Of Templates
• Ranking Function
• Linear Combination Of Features
• Quadruped Robot
• Training Data
• Support Vector Machine
• Center Of Mass
• Input Vector
• Reachable
• Weight Vector
• Radial Basis Function
• Regularization Parameter
• Expert Demonstrations
• Linear Classifier
• Template Library
• Body Clearance
• Medium Scale
• Proportional-integral-derivative
• Inertial Measurement Unit
• Smallest Scale
• Control Architecture
• Stability Margin