Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization

• URL: http://arxiv.org/abs/2509.02815v1
• Date: Tue, 02 Sep 2025 20:32:02 GMT
• Title: Multi-Embodiment Locomotion at Scale with extreme Embodiment Randomization
• Authors: Nico Bohlinger, Jan Peters,
• Abstract summary: We present a single, general locomotion policy trained on a diverse collection of 50 legged robots.<n>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.
• Score: 16.640420524594443
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control [34.056581843277904]
  We introduce an iterative generalist-specialist distillation framework that produces a single unified policy that controls multiple humanoids.<n>We conducted experiments on five different robots in simulation and four in real-world settings.
  arXiv  Detail & Related papers  (2026-02-03T00:58:29Z)
• Towards Embodiment Scaling Laws in Robot Locomotion [33.13851164282621]
  Cross-embodiment generalization underpins the vision of building generalist embodied agents for any robot.<n>We investigate embodiment scaling laws, the hypothesis that increasing the number of training embodiments improves generalization to unseen ones.<n>We procedurally generate 1,000 embodiments with topological, geometric, and joint-level kinematic variations, and train policies on random subsets.
  arXiv  Detail & Related papers  (2025-05-09T03:25:43Z)
• The One RING: a Robotic Indoor Navigation Generalist [58.30694487843546]
  RING (Robotic Indoor Navigation Generalist) is an embodiment-agnostic policy that turns any mobile robot into an effective indoor semantic navigator.<n>Trained entirely in simulation, RING leverages large-scale randomization over robot embodiments to enable robust generalization to many real-world platforms.
  arXiv  Detail & Related papers  (2024-12-18T23:15:41Z)
• One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion [18.556470359899855]
  We introduce URMA, the Unified Robot Morphology Architecture.<n>Our framework brings the end-to-end Multi-Task Reinforcement Learning approach to the realm of legged robots.<n>We show that URMA can learn a locomotion policy on multiple embodiments that can be easily transferred to unseen robot platforms.
  arXiv  Detail & Related papers  (2024-09-10T09:44:15Z)
• Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation [49.03165169369552]
  By training a single policy across many different kinds of robots, a robot learning method can leverage much broader and more diverse datasets. We propose CrossFormer, a scalable and flexible transformer-based policy that can consume data from any embodiment. We demonstrate that the same network weights can control vastly different robots, including single and dual arm manipulation systems, wheeled robots, quadcopters, and quadrupeds.
  arXiv  Detail & Related papers  (2024-08-21T17:57:51Z)
• Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer [68.10957584496866]
  We propose a method that uses continuous robot evolution to efficiently transfer the policy to each target robot. The robot evolution tree allows the robot evolution paths to be shared, so our approach can significantly outperform naive one-to-one policy transfer.
  arXiv  Detail & Related papers  (2024-05-06T14:52:23Z)
• Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment [88.06408322210025]
  We study the problem of adapting on-the-fly to novel scenarios during deployment.<n>Our approach, RObust Autonomous Modulation (ROAM), introduces a mechanism based on the perceived value of pre-trained behaviors.<n>We demonstrate that ROAM enables a robot to adapt rapidly to changes in dynamics both in simulation and on a real Go1 quadruped.
  arXiv  Detail & Related papers  (2023-11-02T08:22:28Z)
• Universal Morphology Control via Contextual Modulation [52.742056836818136]
  Learning a universal policy across different robot morphologies can significantly improve learning efficiency and generalization in continuous control. Existing methods utilize graph neural networks or transformers to handle heterogeneous state and action spaces across different morphologies. We propose a hierarchical architecture to better model this dependency via contextual modulation.
  arXiv  Detail & Related papers  (2023-02-22T00:04:12Z)
• REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer [57.045140028275036]
  We consider the problem of transferring a policy across two different robots with significantly different parameters such as kinematics and morphology. Existing approaches that train a new policy by matching the action or state transition distribution, including imitation learning methods, fail due to optimal action and/or state distribution being mismatched in different robots. We propose a novel method named $REvolveR$ of using continuous evolutionary models for robotic policy transfer implemented in a physics simulator.
  arXiv  Detail & Related papers  (2022-02-10T18:50:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.