Neural Graph Control Barrier Functions Guided Distributed Collision-avoidance Multi-agent Control

Songyuan Zhang, Kunal Garg, Chuchu Fan
Proceedings of The 7th Conference on Robot Learning, PMLR 229:2373-2392, 2023.

Abstract

We consider the problem of designing distributed collision-avoidance multi-agent control in large-scale environments with potentially moving obstacles, where a large number of agents are required to maintain safety using only local information and reach their goals. This paper addresses the problem of collision avoidance, scalability, and generalizability by introducing graph control barrier functions (GCBFs) for distributed control. The newly introduced GCBF is based on the well-established CBF theory for safety guarantees but utilizes a graph structure for scalable and generalizable decentralized control. We use graph neural networks to learn both neural a GCBF certificate and distributed control. We also extend the framework from handling state-based models to directly taking point clouds from LiDAR for more practical robotics settings. We demonstrated the efficacy of GCBF in a variety of numerical experiments, where the number, density, and traveling distance of agents, as well as the number of unseen and uncontrolled obstacles increase. Empirical results show that GCBF outperforms leading methods such as MAPPO and multi-agent distributed CBF (MDCBF). Trained with only $16$ agents, GCBF can achieve up to $3$ times improvement of success rate (agents reach goals and never encountered in any collisions) on $<500$ agents, and still maintain more than $50%$ success rates for $>\!1000$ agents when other methods completely fail.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-zhang23h, title = {Neural Graph Control Barrier Functions Guided Distributed Collision-avoidance Multi-agent Control}, author = {Zhang, Songyuan and Garg, Kunal and Fan, Chuchu}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {2373--2392}, 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/zhang23h/zhang23h.pdf}, url = {https://proceedings.mlr.press/v229/zhang23h.html}, abstract = {We consider the problem of designing distributed collision-avoidance multi-agent control in large-scale environments with potentially moving obstacles, where a large number of agents are required to maintain safety using only local information and reach their goals. This paper addresses the problem of collision avoidance, scalability, and generalizability by introducing graph control barrier functions (GCBFs) for distributed control. The newly introduced GCBF is based on the well-established CBF theory for safety guarantees but utilizes a graph structure for scalable and generalizable decentralized control. We use graph neural networks to learn both neural a GCBF certificate and distributed control. We also extend the framework from handling state-based models to directly taking point clouds from LiDAR for more practical robotics settings. We demonstrated the efficacy of GCBF in a variety of numerical experiments, where the number, density, and traveling distance of agents, as well as the number of unseen and uncontrolled obstacles increase. Empirical results show that GCBF outperforms leading methods such as MAPPO and multi-agent distributed CBF (MDCBF). Trained with only $16$ agents, GCBF can achieve up to $3$ times improvement of success rate (agents reach goals and never encountered in any collisions) on $<500$ agents, and still maintain more than $50%$ success rates for $>\!1000$ agents when other methods completely fail.} }
Endnote
%0 Conference Paper %T Neural Graph Control Barrier Functions Guided Distributed Collision-avoidance Multi-agent Control %A Songyuan Zhang %A Kunal Garg %A Chuchu Fan %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-zhang23h %I PMLR %P 2373--2392 %U https://proceedings.mlr.press/v229/zhang23h.html %V 229 %X We consider the problem of designing distributed collision-avoidance multi-agent control in large-scale environments with potentially moving obstacles, where a large number of agents are required to maintain safety using only local information and reach their goals. This paper addresses the problem of collision avoidance, scalability, and generalizability by introducing graph control barrier functions (GCBFs) for distributed control. The newly introduced GCBF is based on the well-established CBF theory for safety guarantees but utilizes a graph structure for scalable and generalizable decentralized control. We use graph neural networks to learn both neural a GCBF certificate and distributed control. We also extend the framework from handling state-based models to directly taking point clouds from LiDAR for more practical robotics settings. We demonstrated the efficacy of GCBF in a variety of numerical experiments, where the number, density, and traveling distance of agents, as well as the number of unseen and uncontrolled obstacles increase. Empirical results show that GCBF outperforms leading methods such as MAPPO and multi-agent distributed CBF (MDCBF). Trained with only $16$ agents, GCBF can achieve up to $3$ times improvement of success rate (agents reach goals and never encountered in any collisions) on $<500$ agents, and still maintain more than $50%$ success rates for $>\!1000$ agents when other methods completely fail.
APA
Zhang, S., Garg, K. & Fan, C.. (2023). Neural Graph Control Barrier Functions Guided Distributed Collision-avoidance Multi-agent Control. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:2373-2392 Available from https://proceedings.mlr.press/v229/zhang23h.html.

Related Material