MBC: Multi-Brain Collaborative Control for Quadruped Robots

Hang Liu, Yi Cheng, Rankun Li, Xiaowen Hu, Linqi Ye, Houde Liu
Proceedings of The 8th Conference on Robot Learning, PMLR 270:3688-3704, 2025.

Abstract

In the field of locomotion task of quadruped robots, Blind Policy and Perceptive Policy each have their own advantages and limitations. The Blind Policy relies on preset sensor information and algorithms, suitable for known and structured environments, but it lacks adaptability in complex or unknown environments. The Perceptive Policy uses visual sensors to obtain detailed environmental information, allowing it to adapt to complex terrains, but its effectiveness is limited under occluded conditions, especially when perception fails. Unlike the Blind Policy, the Perceptive Policy is not as robust under these conditions. To address these challenges, we propose a MBC:Multi-Brain collaborative system that incorporates the concepts of Multi-Agent Reinforcement Learning and introduces collaboration between the Blind Policy and the Perceptive Policy. By applying this multi-policy collaborative model to a quadruped robot, the robot can maintain stable locomotion even when the perceptual system is impaired or observational data is incomplete. Our simulations and real-world experiments demonstrate that this system significantly improves the robot’s passability and robustness against perception failures in complex environments, validating the effectiveness of multi-policy collaboration in enhancing robotic motion performance.

Cite this Paper


BibTeX
@InProceedings{pmlr-v270-liu25f, title = {MBC: Multi-Brain Collaborative Control for Quadruped Robots}, author = {Liu, Hang and Cheng, Yi and Li, Rankun and Hu, Xiaowen and Ye, Linqi and Liu, Houde}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {3688--3704}, 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/liu25f/liu25f.pdf}, url = {https://proceedings.mlr.press/v270/liu25f.html}, abstract = {In the field of locomotion task of quadruped robots, Blind Policy and Perceptive Policy each have their own advantages and limitations. The Blind Policy relies on preset sensor information and algorithms, suitable for known and structured environments, but it lacks adaptability in complex or unknown environments. The Perceptive Policy uses visual sensors to obtain detailed environmental information, allowing it to adapt to complex terrains, but its effectiveness is limited under occluded conditions, especially when perception fails. Unlike the Blind Policy, the Perceptive Policy is not as robust under these conditions. To address these challenges, we propose a MBC:Multi-Brain collaborative system that incorporates the concepts of Multi-Agent Reinforcement Learning and introduces collaboration between the Blind Policy and the Perceptive Policy. By applying this multi-policy collaborative model to a quadruped robot, the robot can maintain stable locomotion even when the perceptual system is impaired or observational data is incomplete. Our simulations and real-world experiments demonstrate that this system significantly improves the robot’s passability and robustness against perception failures in complex environments, validating the effectiveness of multi-policy collaboration in enhancing robotic motion performance.} }
Endnote
%0 Conference Paper %T MBC: Multi-Brain Collaborative Control for Quadruped Robots %A Hang Liu %A Yi Cheng %A Rankun Li %A Xiaowen Hu %A Linqi Ye %A Houde Liu %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-liu25f %I PMLR %P 3688--3704 %U https://proceedings.mlr.press/v270/liu25f.html %V 270 %X In the field of locomotion task of quadruped robots, Blind Policy and Perceptive Policy each have their own advantages and limitations. The Blind Policy relies on preset sensor information and algorithms, suitable for known and structured environments, but it lacks adaptability in complex or unknown environments. The Perceptive Policy uses visual sensors to obtain detailed environmental information, allowing it to adapt to complex terrains, but its effectiveness is limited under occluded conditions, especially when perception fails. Unlike the Blind Policy, the Perceptive Policy is not as robust under these conditions. To address these challenges, we propose a MBC:Multi-Brain collaborative system that incorporates the concepts of Multi-Agent Reinforcement Learning and introduces collaboration between the Blind Policy and the Perceptive Policy. By applying this multi-policy collaborative model to a quadruped robot, the robot can maintain stable locomotion even when the perceptual system is impaired or observational data is incomplete. Our simulations and real-world experiments demonstrate that this system significantly improves the robot’s passability and robustness against perception failures in complex environments, validating the effectiveness of multi-policy collaboration in enhancing robotic motion performance.
APA
Liu, H., Cheng, Y., Li, R., Hu, X., Ye, L. & Liu, H.. (2025). MBC: Multi-Brain Collaborative Control for Quadruped Robots. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:3688-3704 Available from https://proceedings.mlr.press/v270/liu25f.html.

Related Material