Learning Torque Control for Quadrupedal Locomotion

TL;DR

This paper introduces a novel reinforcement learning framework that directly predicts joint torques for quadrupedal robots, improving robustness and performance over traditional position-based methods, and is validated through extensive sim-to-real experiments.

Contribution

It presents the first end-to-end learning torque control approach for quadrupedal locomotion, shifting from position-based to torque-based RL control.

Findings

Torque-based RL achieves higher rewards than position-based RL.

The method demonstrates robustness against external disturbances.

Successful sim-to-real transfer of the learned torque control.

Abstract

Reinforcement learning (RL) has become a promising approach to developing controllers for quadrupedal robots. Conventionally, an RL design for locomotion follows a position-based paradigm, wherein an RL policy outputs target joint positions at a low frequency that are then tracked by a high-frequency proportional-derivative (PD) controller to produce joint torques. In contrast, for the model-based control of quadrupedal locomotion, there has been a paradigm shift from position-based control to torque-based control. In light of the recent advances in model-based control, we explore an alternative to the position-based RL paradigm, by introducing a torque-based RL framework, where an RL policy directly predicts joint torques at a high frequency, thus circumventing the use of a PD controller. The proposed learning torque control framework is validated with extensive experiments, in which a quadruped is capable of traversing various terrain and resisting external disturbances while following user-specified commands. Furthermore, compared to learning position control, learning torque control demonstrates the potential to achieve a higher reward and is more robust to significant external disturbances. To our knowledge, this is the first sim-to-real attempt for end-to-end learning torque control of quadrupedal locomotion.