Experience-Learning Inspired Two-Step Reward Method for Efficient Legged Locomotion Learning Towards Natural and Robust Gaits

Legged robots excel in navigating complex terrains, yet learning natural and robust motions in such environments remains challenging. Inspired by animals’ experience-based stepwise learning process, we propose a two-stage framework for legged robots to progressively learn naturally robust movements using a two-step reward method. Initially robots learn the fundamental gaits on flat terrains with gait-rewards and generating valuable motion data. Subsequently, leveraging learned motion experience, they adopt adversarial imitation learning to tackle challenging terrains with refined movements. Our method addresses the challenge of acquiring effective imitation data and facilitates the learning process under various gait parameters with ease. The effectiveness of this approach has been validated on both quadruped and hexapod robots, demonstrating naturally robust gaits in real-world applications.