Learning Coordinated Terrain-Adaptive Locomotion by Imitating a Centroidal Dynamics Planner

Abstract

Dynamic quadruped locomotion over challenging terrains with precise foot placements is a hard problem for both optimal control methods and Reinforcement Learning (RL). Non-linear solvers can produce coordinated constraint satisfying motions, but often take too long to converge for online application. RL methods can learn dynamic reactive controllers but require carefully tuned shaping rewards to produce good gaits and can have trouble discovering precise coordinated movements. Imitation learning circumvents this problem and has been used with motion capture data to extract quadruped gaits for flat terrains. However, it would be costly to acquire motion capture data for a very large variety of terrains with height differences. In this work, we combine the advantages of trajectory optimization and learning methods and show that terrain adaptive controllers can be obtained by training policies to imitate trajectories that have been planned over procedural terrains by a non-linear solver. We show that the learned policies transfer to unseen terrains and can be fine-tuned to dynamically traverse challenging terrains that require precise foot placements and are very hard to solve with standard RL.

Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors

“…It should be possible to merge and grow datasets over time with recordings that target behaviors that the skill modules struggle with. Datasets could also be enriched with other sources than MoCap such as trajectory optimization over procedural terrains [52,53].…”

LSTP: Long Short-Term Motion Planning for Legged and Legged-Wheeled Systems

“…Similarly, researchers tackled the locomotion problem using Reinforcement Learning (RL) methods [8], [9]. Despite the unprecedented robustness and impressive field deployments, RL methods still struggle to achieve precise and coordinated foot placement required to negotiate terrains such as stepping stones [6], [10].…”