Subteaming and Adaptive Formation Control for Coordinated Multi-Robot Navigation

Zihao Deng, Peng Gao, Williard Joshua Jose, Maggie Wigness, John G. Rogers III, Brian Reily, Christopher M. Reardon, Hao Zhang
Proceedings of The 9th Conference on Robot Learning, PMLR 305:2665-2677, 2025.

Abstract

Coordinated multi-robot navigation is essential for robots to operate as a team in diverse environments. During navigation, robot teams usually need to maintain specific formations, such as circular formations to protect human teammates at the center. However, in complex scenarios such as narrow corridors, rigidly preserving predefined formations can become infeasible. Therefore, robot teams must be capable of dynamically splitting into smaller subteams and adaptively controlling the subteams to navigate through such scenarios while preserving formations. To enable this capability, we introduce a novel method for SubTeaming and Adaptive Formation (STAF), which is built upon a unified hierarchical learning framework: (1) high-level deep graph cut for team splitting, (2) intermediate-level graph learning for facilitating coordinated navigation among subteams, and (3) low-level policy learning for controlling individual mobile robots to reach their goal positions while avoiding collisions. To evaluate STAF, we conducted extensive experiments in both indoor and outdoor environments using robotics simulations and physical robot teams. Experimental results show that STAF enables the novel capability for subteaming and adaptive formation control, and achieves promising performance in coordinated multi-robot navigation through challenging scenarios. More details are available on the project website: https://anonymous188.github.io/STAF/.

Cite this Paper

BibTeX
@InProceedings{pmlr-v305-deng25b, title = {Subteaming and Adaptive Formation Control for Coordinated Multi-Robot Navigation}, author = {Deng, Zihao and Gao, Peng and Jose, Williard Joshua and Wigness, Maggie and III, John G. Rogers and Reily, Brian and Reardon, Christopher M. and Zhang, Hao}, booktitle = {Proceedings of The 9th Conference on Robot Learning}, pages = {2665--2677}, year = {2025}, editor = {Lim, Joseph and Song, Shuran and Park, Hae-Won}, volume = {305}, series = {Proceedings of Machine Learning Research}, month = {27--30 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v305/main/assets/deng25b/deng25b.pdf}, url = {https://proceedings.mlr.press/v305/deng25b.html}, abstract = {Coordinated multi-robot navigation is essential for robots to operate as a team in diverse environments. During navigation, robot teams usually need to maintain specific formations, such as circular formations to protect human teammates at the center. However, in complex scenarios such as narrow corridors, rigidly preserving predefined formations can become infeasible. Therefore, robot teams must be capable of dynamically splitting into smaller subteams and adaptively controlling the subteams to navigate through such scenarios while preserving formations. To enable this capability, we introduce a novel method for SubTeaming and Adaptive Formation (STAF), which is built upon a unified hierarchical learning framework: (1) high-level deep graph cut for team splitting, (2) intermediate-level graph learning for facilitating coordinated navigation among subteams, and (3) low-level policy learning for controlling individual mobile robots to reach their goal positions while avoiding collisions. To evaluate STAF, we conducted extensive experiments in both indoor and outdoor environments using robotics simulations and physical robot teams. Experimental results show that STAF enables the novel capability for subteaming and adaptive formation control, and achieves promising performance in coordinated multi-robot navigation through challenging scenarios. More details are available on the project website: https://anonymous188.github.io/STAF/.} }
Endnote
%0 Conference Paper %T Subteaming and Adaptive Formation Control for Coordinated Multi-Robot Navigation %A Zihao Deng %A Peng Gao %A Williard Joshua Jose %A Maggie Wigness %A John G. Rogers III %A Brian Reily %A Christopher M. Reardon %A Hao Zhang %B Proceedings of The 9th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Joseph Lim %E Shuran Song %E Hae-Won Park %F pmlr-v305-deng25b %I PMLR %P 2665--2677 %U https://proceedings.mlr.press/v305/deng25b.html %V 305 %X Coordinated multi-robot navigation is essential for robots to operate as a team in diverse environments. During navigation, robot teams usually need to maintain specific formations, such as circular formations to protect human teammates at the center. However, in complex scenarios such as narrow corridors, rigidly preserving predefined formations can become infeasible. Therefore, robot teams must be capable of dynamically splitting into smaller subteams and adaptively controlling the subteams to navigate through such scenarios while preserving formations. To enable this capability, we introduce a novel method for SubTeaming and Adaptive Formation (STAF), which is built upon a unified hierarchical learning framework: (1) high-level deep graph cut for team splitting, (2) intermediate-level graph learning for facilitating coordinated navigation among subteams, and (3) low-level policy learning for controlling individual mobile robots to reach their goal positions while avoiding collisions. To evaluate STAF, we conducted extensive experiments in both indoor and outdoor environments using robotics simulations and physical robot teams. Experimental results show that STAF enables the novel capability for subteaming and adaptive formation control, and achieves promising performance in coordinated multi-robot navigation through challenging scenarios. More details are available on the project website: https://anonymous188.github.io/STAF/.
APA
Deng, Z., Gao, P., Jose, W.J., Wigness, M., III, J.G.R., Reily, B., Reardon, C.M. & Zhang, H.. (2025). Subteaming and Adaptive Formation Control for Coordinated Multi-Robot Navigation. Proceedings of The 9th Conference on Robot Learning, in Proceedings of Machine Learning Research 305:2665-2677 Available from https://proceedings.mlr.press/v305/deng25b.html.

Related Material