Publikation
Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion
Nico Bohlinger; Jonathan Kinzel; Daniel Palenicek; Lukasz Antczak; Jan Peters
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2503.08375, Pages 1-8, arXiv, 2025.
Zusammenfassung
On-robot Reinforcement Learning is a promising
approach to train embodiment-aware policies for legged robots.
However, the computational constraints of real-time learning on
robots pose a significant challenge. We present a framework for
efficiently learning quadruped locomotion in just 8 minutes of
raw real-time training utilizing the sample efficiency and min-
imal computational overhead of the new off-policy algorithm
CrossQ. We investigate two control architectures: Predicting
joint target positions for agile, high-speed locomotion and Cen-
tral Pattern Generators for stable, natural gaits. While prior
work focused on learning simple forward gaits, our framework
extends on-robot learning to omnidirectional locomotion. We
demonstrate the robustness of our approach in different indoor
and outdoor environments and provide the videos and code for
our experiments at: https://nico-bohlinger.github.
io/gait_in_eight_website