Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion
This work addresses the challenge of robust and reactive robot locomotion for robotics researchers, offering a counterintuitive approach that simplifies sim-to-real transfer without dynamics randomization.
The paper tackles the problem of robotic locomotion by demonstrating that low-frequency motion control at 8 Hz can achieve robust and dynamic performance on a real ANYmal C quadruped, achieving a high heading velocity of 1.5 m/s and handling uneven terrain and perturbations.
Robotic locomotion is often approached with the goal of maximizing robustness and reactivity by increasing motion control frequency. We challenge this intuitive notion by demonstrating robust and dynamic locomotion with a learned motion controller executing at as low as 8 Hz on a real ANYmal C quadruped. The robot is able to robustly and repeatably achieve a high heading velocity of 1.5 m/s, traverse uneven terrain, and resist unexpected external perturbations. We further present a comparative analysis of deep reinforcement learning (RL) based motion control policies trained and executed at frequencies ranging from 5 Hz to 200 Hz. We show that low-frequency policies are less sensitive to actuation latencies and variations in system dynamics. This is to the extent that a successful sim-to-real transfer can be performed even without any dynamics randomization or actuation modeling. We support this claim through a set of rigorous empirical evaluations. Moreover, to assist reproducibility, we provide the training and deployment code along with an extended analysis at https://ori-drs.github.io/lfmc/.