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

Nico Bohlinger, Grzegorz Czechmanowski, Maciej Piotr Krupka, Piotr Kicki, Krzysztof Walas, Jan Peters, Davide Tateo
Proceedings of The 8th Conference on Robot Learning, PMLR 270:3356-3378, 2025.

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. To close this gap, we introduce URMA, the Unified Robot Morphology Architecture. 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 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-bohlinger25a, title = {One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion}, author = {Bohlinger, Nico and Czechmanowski, Grzegorz and Krupka, Maciej Piotr and Kicki, Piotr and Walas, Krzysztof and Peters, Jan and Tateo, Davide}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {3356--3378}, year = {2025}, editor = {Agrawal, Pulkit and Kroemer, Oliver and Burgard, Wolfram}, volume = {270}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v270/main/assets/bohlinger25a/bohlinger25a.pdf}, url = {https://proceedings.mlr.press/v270/bohlinger25a.html}, 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. To close this gap, we introduce URMA, the Unified Robot Morphology Architecture. 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 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.} }
Endnote
%0 Conference Paper %T One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion %A Nico Bohlinger %A Grzegorz Czechmanowski %A Maciej Piotr Krupka %A Piotr Kicki %A Krzysztof Walas %A Jan Peters %A Davide Tateo %B Proceedings of The 8th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Pulkit Agrawal %E Oliver Kroemer %E Wolfram Burgard %F pmlr-v270-bohlinger25a %I PMLR %P 3356--3378 %U https://proceedings.mlr.press/v270/bohlinger25a.html %V 270 %X 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. To close this gap, we introduce URMA, the Unified Robot Morphology Architecture. 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 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.
APA
Bohlinger, N., Czechmanowski, G., Krupka, M.P., Kicki, P., Walas, K., Peters, J. & Tateo, D.. (2025). One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:3356-3378 Available from https://proceedings.mlr.press/v270/bohlinger25a.html.

Related Material