Learning Decentralized Multi-Biped Control for Payload Transport

Bikram Pandit, Ashutosh Gupta, Mohitvishnu S. Gadde, Addison Johnson, Aayam Kumar Shrestha, Helei Duan, Jeremy Dao, Alan Fern
Proceedings of The 8th Conference on Robot Learning, PMLR 270:1021-1034, 2025.

Abstract

Payload transport over flat terrain via multi-wheel robot carriers is well-understood, highly effective, and configurable. In this paper, our goal is to provide similar effectiveness and configurability for transport over rough terrain that is more suitable for legs rather than wheels. For this purpose, we consider multi-biped robot carriers, where wheels are replaced by multiple bipedal robots attached to the carrier. Our main contribution is to design a decentralized controller for such systems that can be effectively applied to varying numbers and configurations of rigidly attached bipedal robots without retraining. We present a reinforcement learning approach for training the controller in simulation that supports transfer to the real world. Our experiments in simulation provide quantitative metrics showing the effectiveness of the approach over a wide variety of simulated transport scenarios. In addition, we demonstrate the controller in the real-world for systems composed of two and three Cassie robots. To our knowledge, this is the first example of a scalable multi-biped payload transport system.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-pandit25a, title = {Learning Decentralized Multi-Biped Control for Payload Transport}, author = {Pandit, Bikram and Gupta, Ashutosh and Gadde, Mohitvishnu S. and Johnson, Addison and Shrestha, Aayam Kumar and Duan, Helei and Dao, Jeremy and Fern, Alan}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {1021--1034}, 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/pandit25a/pandit25a.pdf}, url = {https://proceedings.mlr.press/v270/pandit25a.html}, abstract = {Payload transport over flat terrain via multi-wheel robot carriers is well-understood, highly effective, and configurable. In this paper, our goal is to provide similar effectiveness and configurability for transport over rough terrain that is more suitable for legs rather than wheels. For this purpose, we consider multi-biped robot carriers, where wheels are replaced by multiple bipedal robots attached to the carrier. Our main contribution is to design a decentralized controller for such systems that can be effectively applied to varying numbers and configurations of rigidly attached bipedal robots without retraining. We present a reinforcement learning approach for training the controller in simulation that supports transfer to the real world. Our experiments in simulation provide quantitative metrics showing the effectiveness of the approach over a wide variety of simulated transport scenarios. In addition, we demonstrate the controller in the real-world for systems composed of two and three Cassie robots. To our knowledge, this is the first example of a scalable multi-biped payload transport system.} }
Endnote
%0 Conference Paper %T Learning Decentralized Multi-Biped Control for Payload Transport %A Bikram Pandit %A Ashutosh Gupta %A Mohitvishnu S. Gadde %A Addison Johnson %A Aayam Kumar Shrestha %A Helei Duan %A Jeremy Dao %A Alan Fern %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-pandit25a %I PMLR %P 1021--1034 %U https://proceedings.mlr.press/v270/pandit25a.html %V 270 %X Payload transport over flat terrain via multi-wheel robot carriers is well-understood, highly effective, and configurable. In this paper, our goal is to provide similar effectiveness and configurability for transport over rough terrain that is more suitable for legs rather than wheels. For this purpose, we consider multi-biped robot carriers, where wheels are replaced by multiple bipedal robots attached to the carrier. Our main contribution is to design a decentralized controller for such systems that can be effectively applied to varying numbers and configurations of rigidly attached bipedal robots without retraining. We present a reinforcement learning approach for training the controller in simulation that supports transfer to the real world. Our experiments in simulation provide quantitative metrics showing the effectiveness of the approach over a wide variety of simulated transport scenarios. In addition, we demonstrate the controller in the real-world for systems composed of two and three Cassie robots. To our knowledge, this is the first example of a scalable multi-biped payload transport system.
APA
Pandit, B., Gupta, A., Gadde, M.S., Johnson, A., Shrestha, A.K., Duan, H., Dao, J. & Fern, A.. (2025). Learning Decentralized Multi-Biped Control for Payload Transport. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:1021-1034 Available from https://proceedings.mlr.press/v270/pandit25a.html.

Related Material