Skip to content

Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion

Siddhant Gangapurwala, Luigi Campanaro and Ioannis Havoutis

Experiments performed on ANYmal C with a motion control frequency of 8 Hz.


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.

We additionally provide training and deployment code for the Low-Frequency Motion Control (LFMC) framework to assist reproducibility and rapid benchmarking.



  title = {Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion},
  author = {Gangapurwala, Siddhant and Campanaro, Luigi and Havoutis, Ioannis},
  url = {},
  publisher = {arXiv},  
  year = {2022},
  doi = {10.48550/ARXIV.2209.14887},