Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion

Abstract

In this paper, we propose a locomotion training framework where a control policy and a state estimator are trained concurrently. The framework consists of a policy network which outputs the desired joint positions and a state estimation network which outputs estimates of the robot's states such as the base linear velocity, foot height, and contact probability. We exploit a fast simulation environment to train the networks and the trained networks are transferred to the real robot. The trained policy and state estimator are capable of traversing diverse terrains such as a hill, slippery plate, and bumpy road. We also demonstrate that the learned policy can run at up to 3.75 m/s on normal flat ground and 3.54 m/s on a slippery plate with the coefficient of friction of 0.22.

Accepted for IEEE Robotics and Automation Letters (RA-L) and ICRA 2022

References in corpus (3)

• Learning agile and dynamic motor skills for legged robots
• Multi-expert learning of adaptive legged locomotion
• Representation-Free Model Predictive Control for Dynamic Motions in Quadrupeds

Cited by in corpus (5)

• Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots
• Versatile Multi-Contact Planning and Control for Legged Loco-Manipulation
• Controlling the Solo12 Quadruped Robot with Deep Reinforcement Learning
• Learning Quadrupedal Locomotion for a Heavy Hydraulic Robot Using an Actuator Model
• Agile perceptive multi-skill locomotion for quadrupedal robots in the wild