Generalization of Heterogeneous Multi-Robot Policies via Awareness and Communication of Capabilities

Pierce Howell, Max Rudolph, Reza Joseph Torbati, Kevin Fu, Harish Ravichandar
Proceedings of The 7th Conference on Robot Learning, PMLR 229:2772-2790, 2023.

Abstract

Recent advances in multi-agent reinforcement learning (MARL) are enabling impressive coordination in heterogeneous multi-robot teams. However, existing approaches often overlook the challenge of generalizing learned policies to teams of new compositions, sizes, and robots. While such generalization might not be important in teams of virtual agents that can retrain policies on-demand, it is pivotal in multi-robot systems that are deployed in the real-world and must readily adapt to inevitable changes. As such, multi-robot policies must remain robust to team changes – an ability we call adaptive teaming. In this work, we investigate if awareness and communication of robot capabilities can provide such generalization by conducting detailed experiments involving an established multi-robot test bed. We demonstrate that shared decentralized policies, that enable robots to be both aware of and communicate their capabilities, can achieve adaptive teaming by implicitly capturing the fundamental relationship between collective capabilities and effective coordination. Videos of trained policies can be viewed at https://sites.google.com/view/cap-comm .

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-howell23a, title = {Generalization of Heterogeneous Multi-Robot Policies via Awareness and Communication of Capabilities}, author = {Howell, Pierce and Rudolph, Max and Torbati, Reza Joseph and Fu, Kevin and Ravichandar, Harish}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {2772--2790}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/howell23a/howell23a.pdf}, url = {https://proceedings.mlr.press/v229/howell23a.html}, abstract = {Recent advances in multi-agent reinforcement learning (MARL) are enabling impressive coordination in heterogeneous multi-robot teams. However, existing approaches often overlook the challenge of generalizing learned policies to teams of new compositions, sizes, and robots. While such generalization might not be important in teams of virtual agents that can retrain policies on-demand, it is pivotal in multi-robot systems that are deployed in the real-world and must readily adapt to inevitable changes. As such, multi-robot policies must remain robust to team changes – an ability we call adaptive teaming. In this work, we investigate if awareness and communication of robot capabilities can provide such generalization by conducting detailed experiments involving an established multi-robot test bed. We demonstrate that shared decentralized policies, that enable robots to be both aware of and communicate their capabilities, can achieve adaptive teaming by implicitly capturing the fundamental relationship between collective capabilities and effective coordination. Videos of trained policies can be viewed at https://sites.google.com/view/cap-comm .} }
Endnote
%0 Conference Paper %T Generalization of Heterogeneous Multi-Robot Policies via Awareness and Communication of Capabilities %A Pierce Howell %A Max Rudolph %A Reza Joseph Torbati %A Kevin Fu %A Harish Ravichandar %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-howell23a %I PMLR %P 2772--2790 %U https://proceedings.mlr.press/v229/howell23a.html %V 229 %X Recent advances in multi-agent reinforcement learning (MARL) are enabling impressive coordination in heterogeneous multi-robot teams. However, existing approaches often overlook the challenge of generalizing learned policies to teams of new compositions, sizes, and robots. While such generalization might not be important in teams of virtual agents that can retrain policies on-demand, it is pivotal in multi-robot systems that are deployed in the real-world and must readily adapt to inevitable changes. As such, multi-robot policies must remain robust to team changes – an ability we call adaptive teaming. In this work, we investigate if awareness and communication of robot capabilities can provide such generalization by conducting detailed experiments involving an established multi-robot test bed. We demonstrate that shared decentralized policies, that enable robots to be both aware of and communicate their capabilities, can achieve adaptive teaming by implicitly capturing the fundamental relationship between collective capabilities and effective coordination. Videos of trained policies can be viewed at https://sites.google.com/view/cap-comm .
APA
Howell, P., Rudolph, M., Torbati, R.J., Fu, K. & Ravichandar, H.. (2023). Generalization of Heterogeneous Multi-Robot Policies via Awareness and Communication of Capabilities. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:2772-2790 Available from https://proceedings.mlr.press/v229/howell23a.html.

Related Material