Fast and Efficient Locomotion via Learned Gait Transitions

Yuxiang Yang, Tingnan Zhang, Erwin Coumans, Jie Tan, Byron Boots

Keywords: Legged Locomotion, Hierarchical Control, Reinforcement Learning

Abstract: We focus on the problem of developing energy efficient controllers for quadrupedal robots. Animals can actively switch gaits at different speeds to lower their energy consumption. In this paper, we devise a hierarchical learning framework, in which distinctive locomotion gaits and natural gait transitions emerge automatically with a simple reward of energy minimization. We use evolutionary strategies (ES) to train a high-level gait policy that specifies gait patterns of each foot, while the low-level convex MPC controller optimizes the motor commands so that the robot can walk at a desired velocity using that gait pattern. We test our learning framework on a quadruped robot and demonstrate automatic gait transitions, from walking to trotting and to fly-trotting, as the robot increases its speed. We show that the learned hierarchical controller consumes much less energy across a wide range of locomotion speed than baseline controllers.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2104.04644/code)