Terrain Traversal Cost Learning with Knowledge Transfer Between Multi-legged Walking Robot Gaits

Abstract

The terrain traversal abilities of multi-legged walking robots are affected by gaits, the walking patterns that enable adaptation to various operational environments. Fast and low-set gaits are suited to flat ground, while cautious and highset gaits enable traversing rough areas. A suitable gait can be selected using prior experience with a particular terrain type. However, experience alone is insufficient in practical setups, where the robot experiences each terrain with only one or just a few gaits and thus would infer novel gait-terrain interactions from insufficient data. Therefore, we use knowledge transfer to address unsampled gait-terrain interactions and infer the traversal cost for every gait. The proposed solution combines gaitterrain cost models using inferred gait-to-gait models projecting the robot experiences between different gaits. We implement the cost models as Gaussian Mixture regressors providing certainty to identify unknown terrains where knowledge transfer is desirable. The presented method has been verified in synthetic showcase scenarios and deployment with a real walking robot. The proposed knowledge transfer demonstrates improved cost prediction and selection of the appropriate gait for specific terrains.