ViPER: Visibility-based Pursuit-Evasion via Reinforcement Learning

Yizhuo Wang, Yuhong Cao, Jimmy Chiun, Subhadeep Koley, Mandy Pham, Guillaume Adrien Sartoretti
Proceedings of The 8th Conference on Robot Learning, PMLR 270:4188-4200, 2025.

Abstract

In visibility-based pursuit-evasion tasks, a team of mobile pursuer robots with limited sensing capabilities is tasked with detecting all evaders in a multiply-connected planar environment, whose map may or may not be known to pursuers beforehand. This requires tight coordination among multiple agents to ensure that the omniscient and potentially arbitrarily fast evaders are guaranteed to be detected by the pursuers. Whereas existing methods typically rely on a relatively large team of agents to clear the environment, we propose ViPER, a neural solution that leverages a graph attention network to learn a coordinated yet distributed policy via multi-agent reinforcement learning (MARL). We experimentally demonstrate that ViPER significantly outperforms other state-of-the-art non-learning planners, showcasing its emergent coordinated behaviors and adaptability to more challenging scenarios and various team sizes, and finally deploy its learned policies on hardware in an aerial search task.

Cite this Paper

BibTeX
@InProceedings{pmlr-v270-wang25k, title = {ViPER: Visibility-based Pursuit-Evasion via Reinforcement Learning}, author = {Wang, Yizhuo and Cao, Yuhong and Chiun, Jimmy and Koley, Subhadeep and Pham, Mandy and Sartoretti, Guillaume Adrien}, booktitle = {Proceedings of The 8th Conference on Robot Learning}, pages = {4188--4200}, 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/wang25k/wang25k.pdf}, url = {https://proceedings.mlr.press/v270/wang25k.html}, abstract = {In visibility-based pursuit-evasion tasks, a team of mobile pursuer robots with limited sensing capabilities is tasked with detecting all evaders in a multiply-connected planar environment, whose map may or may not be known to pursuers beforehand. This requires tight coordination among multiple agents to ensure that the omniscient and potentially arbitrarily fast evaders are guaranteed to be detected by the pursuers. Whereas existing methods typically rely on a relatively large team of agents to clear the environment, we propose ViPER, a neural solution that leverages a graph attention network to learn a coordinated yet distributed policy via multi-agent reinforcement learning (MARL). We experimentally demonstrate that ViPER significantly outperforms other state-of-the-art non-learning planners, showcasing its emergent coordinated behaviors and adaptability to more challenging scenarios and various team sizes, and finally deploy its learned policies on hardware in an aerial search task.} }
Endnote
%0 Conference Paper %T ViPER: Visibility-based Pursuit-Evasion via Reinforcement Learning %A Yizhuo Wang %A Yuhong Cao %A Jimmy Chiun %A Subhadeep Koley %A Mandy Pham %A Guillaume Adrien Sartoretti %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-wang25k %I PMLR %P 4188--4200 %U https://proceedings.mlr.press/v270/wang25k.html %V 270 %X In visibility-based pursuit-evasion tasks, a team of mobile pursuer robots with limited sensing capabilities is tasked with detecting all evaders in a multiply-connected planar environment, whose map may or may not be known to pursuers beforehand. This requires tight coordination among multiple agents to ensure that the omniscient and potentially arbitrarily fast evaders are guaranteed to be detected by the pursuers. Whereas existing methods typically rely on a relatively large team of agents to clear the environment, we propose ViPER, a neural solution that leverages a graph attention network to learn a coordinated yet distributed policy via multi-agent reinforcement learning (MARL). We experimentally demonstrate that ViPER significantly outperforms other state-of-the-art non-learning planners, showcasing its emergent coordinated behaviors and adaptability to more challenging scenarios and various team sizes, and finally deploy its learned policies on hardware in an aerial search task.
APA
Wang, Y., Cao, Y., Chiun, J., Koley, S., Pham, M. & Sartoretti, G.A.. (2025). ViPER: Visibility-based Pursuit-Evasion via Reinforcement Learning. Proceedings of The 8th Conference on Robot Learning, in Proceedings of Machine Learning Research 270:4188-4200 Available from https://proceedings.mlr.press/v270/wang25k.html.

Related Material