Learning a Distributed Hierarchical Locomotion Controller for Embodied Cooperation

Chuye Hong, Kangyao Huang, Huaping Liu
Proceedings of The 8th Conference on Robot Learning, PMLR 270:3500-3515, 2025.

Abstract

In this work, we propose a distributed hierarchical locomotion control strategy for whole-body cooperation and demonstrate the potential for migration into large numbers of agents. Our method utilizes a hierarchical structure to break down complex tasks into smaller, manageable sub-tasks. By incorporating spatiotemporal continuity features, we establish the sequential logic necessary for causal inference and cooperative behaviour in sequential tasks, thereby facilitating efficient and coordinated control strategies. Through training within this framework, we demonstrate enhanced adaptability and cooperation, leading to superior performance in task completion compared to the original methods. Moreover, we construct a set of environments as the benchmark for embodied cooperation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-hong25a, title = {Learning a Distributed Hierarchical Locomotion Controller for Embodied Cooperation}, author = {Hong, Chuye and Huang, Kangyao and Liu, Huaping}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {3500--3515}, 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/hong25a/hong25a.pdf}, url = {https://proceedings.mlr.press/v270/hong25a.html}, abstract = {In this work, we propose a distributed hierarchical locomotion control strategy for whole-body cooperation and demonstrate the potential for migration into large numbers of agents. Our method utilizes a hierarchical structure to break down complex tasks into smaller, manageable sub-tasks. By incorporating spatiotemporal continuity features, we establish the sequential logic necessary for causal inference and cooperative behaviour in sequential tasks, thereby facilitating efficient and coordinated control strategies. Through training within this framework, we demonstrate enhanced adaptability and cooperation, leading to superior performance in task completion compared to the original methods. Moreover, we construct a set of environments as the benchmark for embodied cooperation.} }
Endnote
%0 Conference Paper %T Learning a Distributed Hierarchical Locomotion Controller for Embodied Cooperation %A Chuye Hong %A Kangyao Huang %A Huaping 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-hong25a %I PMLR %P 3500--3515 %U https://proceedings.mlr.press/v270/hong25a.html %V 270 %X In this work, we propose a distributed hierarchical locomotion control strategy for whole-body cooperation and demonstrate the potential for migration into large numbers of agents. Our method utilizes a hierarchical structure to break down complex tasks into smaller, manageable sub-tasks. By incorporating spatiotemporal continuity features, we establish the sequential logic necessary for causal inference and cooperative behaviour in sequential tasks, thereby facilitating efficient and coordinated control strategies. Through training within this framework, we demonstrate enhanced adaptability and cooperation, leading to superior performance in task completion compared to the original methods. Moreover, we construct a set of environments as the benchmark for embodied cooperation.
APA
Hong, C., Huang, K. & Liu, H.. (2025). Learning a Distributed Hierarchical Locomotion Controller for Embodied Cooperation. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:3500-3515 Available from https://proceedings.mlr.press/v270/hong25a.html.

Related Material