# One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion

Source: [One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion](<https://www.sota2.com/research/paper/68fa7bc61e209131cea8a5d1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:48:24.291Z

Authors: Nico Bohlinger, Grzegorz Czechmanowski, Maciej Krupka, Piotr Kicki, Krzysztof Walas, Jan Peters, Davide Tateo

Published: 2024-09-10T09:44:15.000Z

## Abstract

Deep Reinforcement Learning techniques are achieving state-of-the-art results in robust legged locomotion. While there exists a wide variety of legged platforms such as quadruped, humanoids, and hexapods, the field is still missing a single learning framework that can control all these different embodiments easily and effectively and possibly transfer, zero or few-shot, to unseen robot embodiments. We introduce URMA, the Unified Robot Morphology Architecture, to close this gap. Our framework brings the end-to-end Multi-Task Reinforcement Learning approach to the realm of legged robots, enabling the learned policy to control any type of robot morphology. The key idea of our method is to allow the network to learn an abstract locomotion controller that can be seamlessly shared between embodiments thanks to our morphology-agnostic encoders and decoders. This flexible architecture can be seen as a potential first step in building a foundation model for legged robot locomotion. Our experiments show that URMA can learn a locomotion policy on multiple embodiments that can be easily transferred to unseen robot platforms in simulation and the real world.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Velocity tracking on ANYmal-D Real-world (physical hardware trials)](<https://www.sota2.com/research/sota/velocity-tracking-on-anymal-d-real-world-physical-hardware-trials.md>): Velocity tracking; ANYmal-D Real-world (physical hardware trials); eyaw (rad/s): 0.154.

- [Base velocity estimation on ANYmal Hardware (walking test)](<https://www.sota2.com/research/sota/base-velocity-estimation-on-anymal-hardware-walking-test.md>): Base velocity estimation; ANYmal Hardware (walking test); RMSE (X): 0.0863.

- [Autonomous Driving on CARLA Average over 31 vehicles (out-of-distribution)](<https://www.sota2.com/research/sota/autonomous-driving-on-carla-average-over-31-vehicles-out-of-distribution.md>): Autonomous Driving; CARLA Average over 31 vehicles (out-of-distribution); Average Driving Score (DS): 24.39.

- [Autonomous Driving on CARLA Vehicles (27 vehicles) (in-distribution)](<https://www.sota2.com/research/sota/autonomous-driving-on-carla-vehicles-27-vehicles-in-distribution.md>): Autonomous Driving; CARLA Vehicles (27 vehicles) (in-distribution); Average Driving Score (DS): 33.25.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2409.06366>)

[PDF](<https://arxiv.org/pdf/2409.06366.pdf>)
