Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bohlinger, Nico, Peters, Jan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915477101477888
author Bohlinger, Nico
Peters, Jan
author_facet Bohlinger, Nico
Peters, Jan
contents We present a single, general locomotion policy trained on a diverse collection of 50 legged robots. By combining an improved embodiment-aware architecture (URMAv2) with a performance-based curriculum for extreme Embodiment Randomization, our policy learns to control millions of morphological variations. Our policy achieves zero-shot transfer to unseen real-world humanoid and quadruped robots.
format Preprint
id arxiv_https___arxiv_org_abs_2509_02815
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization
Bohlinger, Nico
Peters, Jan
Robotics
Machine Learning
We present a single, general locomotion policy trained on a diverse collection of 50 legged robots. By combining an improved embodiment-aware architecture (URMAv2) with a performance-based curriculum for extreme Embodiment Randomization, our policy learns to control millions of morphological variations. Our policy achieves zero-shot transfer to unseen real-world humanoid and quadruped robots.
title Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization
topic Robotics
Machine Learning
url https://arxiv.org/abs/2509.02815