Bridge the Gap: Enhancing Quadruped Locomotion with Vertical Ground Perturbations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Stasica, Maximilian, Bick, Arne, Bohlinger, Nico, Mohseni, Omid, Fritzsche, Max Johannes Alois, Hübler, Clemens, Peters, Jan, Seyfarth, André
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912649002876928
author Stasica, Maximilian
Bick, Arne
Bohlinger, Nico
Mohseni, Omid
Fritzsche, Max Johannes Alois
Hübler, Clemens
Peters, Jan
Seyfarth, André
author_facet Stasica, Maximilian
Bick, Arne
Bohlinger, Nico
Mohseni, Omid
Fritzsche, Max Johannes Alois
Hübler, Clemens
Peters, Jan
Seyfarth, André
contents Legged robots, particularly quadrupeds, excel at navigating rough terrains, yet their performance under vertical ground perturbations, such as those from oscillating surfaces, remains underexplored. This study introduces a novel approach to enhance quadruped locomotion robustness by training the Unitree Go2 robot on an oscillating bridge - a 13.24-meter steel-and-concrete structure with a 2.0 Hz eigenfrequency designed to perturb locomotion. Using Reinforcement Learning (RL) with the Proximal Policy Optimization (PPO) algorithm in a MuJoCo simulation, we trained 15 distinct locomotion policies, combining five gaits (trot, pace, bound, free, default) with three training conditions: rigid bridge and two oscillating bridge setups with differing height regulation strategies (relative to bridge surface or ground). Domain randomization ensured zero-shot transfer to the real-world bridge. Our results demonstrate that policies trained on the oscillating bridge exhibit superior stability and adaptability compared to those trained on rigid surfaces. Our framework enables robust gait patterns even without prior bridge exposure. These findings highlight the potential of simulation-based RL to improve quadruped locomotion during dynamic ground perturbations, offering insights for designing robots capable of traversing vibrating environments.
format Preprint
id arxiv_https___arxiv_org_abs_2510_13488
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bridge the Gap: Enhancing Quadruped Locomotion with Vertical Ground Perturbations
Stasica, Maximilian
Bick, Arne
Bohlinger, Nico
Mohseni, Omid
Fritzsche, Max Johannes Alois
Hübler, Clemens
Peters, Jan
Seyfarth, André
Robotics
Legged robots, particularly quadrupeds, excel at navigating rough terrains, yet their performance under vertical ground perturbations, such as those from oscillating surfaces, remains underexplored. This study introduces a novel approach to enhance quadruped locomotion robustness by training the Unitree Go2 robot on an oscillating bridge - a 13.24-meter steel-and-concrete structure with a 2.0 Hz eigenfrequency designed to perturb locomotion. Using Reinforcement Learning (RL) with the Proximal Policy Optimization (PPO) algorithm in a MuJoCo simulation, we trained 15 distinct locomotion policies, combining five gaits (trot, pace, bound, free, default) with three training conditions: rigid bridge and two oscillating bridge setups with differing height regulation strategies (relative to bridge surface or ground). Domain randomization ensured zero-shot transfer to the real-world bridge. Our results demonstrate that policies trained on the oscillating bridge exhibit superior stability and adaptability compared to those trained on rigid surfaces. Our framework enables robust gait patterns even without prior bridge exposure. These findings highlight the potential of simulation-based RL to improve quadruped locomotion during dynamic ground perturbations, offering insights for designing robots capable of traversing vibrating environments.
title Bridge the Gap: Enhancing Quadruped Locomotion with Vertical Ground Perturbations
topic Robotics
url https://arxiv.org/abs/2510.13488