AT-Drone: Benchmarking Adaptive Teaming in Multi-Drone Pursuit

Yang Li, Junfan Chen, Feng Xue, Jiabin Qiu, Wenbin Li, Qingrui Zhang, Ying Wen, Wei Pan
Proceedings of The 9th Conference on Robot Learning, PMLR 305:1144-1161, 2025.

Abstract

Adaptive teaming—the capability of agents to effectively collaborate with unfamiliar teammates without prior coordination—is widely explored in virtual video games but overlooked in real-world multi-robot contexts. Yet, such adaptive collaboration is crucial for real-world applications, including border surveillance, search-and-rescue, and counter-terrorism operations. To address this gap, we introduce AT-Drone, the first dedicated benchmark explicitly designed to facilitate comprehensive training and evaluation of adaptive teaming strategies in multi-drone pursuit scenarios. AT-Drone makes the following key contributions: (1) An adaptable simulation environment configurator that enables intuitive and rapid setup of adaptive teaming multi-drone pursuit tasks, including four predefined pursuit environments. (2) A streamlined real-world deployment pipeline that seamlessly translates simulation insights into practical drone evaluations using edge devices (such as Jetson Orin Nano) and Crazyflie drones. (3) A novel algorithm zoo integrated with a distributed training framework, featuring diverse algorithms explicitly tailored, for the first time, to multi-pursuer and multi-evader drone pursuit task. (4) Standardized evaluation protocols with newly designed unseen drone zoos, explicitly designed to rigorously assess the performance of adaptive teaming. Comprehensive experimental evaluations across four progressively challenging multi-drone pursuit scenarios confirm AT-Drone’s effectiveness in advancing adaptive teaming research. Real-world drone experiments further validate its practical feasibility and utility for realistic robotic operations. Videos, code and weights are available at \url{https://sites.google.com/view/at-drone}.

Cite this Paper

BibTeX
@InProceedings{pmlr-v305-li25a, title = {AT-Drone: Benchmarking Adaptive Teaming in Multi-Drone Pursuit}, author = {Li, Yang and Chen, Junfan and Xue, Feng and Qiu, Jiabin and Li, Wenbin and Zhang, Qingrui and Wen, Ying and Pan, Wei}, booktitle = {Proceedings of The 9th Conference on Robot Learning}, pages = {1144--1161}, 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/li25a/li25a.pdf}, url = {https://proceedings.mlr.press/v305/li25a.html}, abstract = {Adaptive teaming—the capability of agents to effectively collaborate with unfamiliar teammates without prior coordination—is widely explored in virtual video games but overlooked in real-world multi-robot contexts. Yet, such adaptive collaboration is crucial for real-world applications, including border surveillance, search-and-rescue, and counter-terrorism operations. To address this gap, we introduce AT-Drone, the first dedicated benchmark explicitly designed to facilitate comprehensive training and evaluation of adaptive teaming strategies in multi-drone pursuit scenarios. AT-Drone makes the following key contributions: (1) An adaptable simulation environment configurator that enables intuitive and rapid setup of adaptive teaming multi-drone pursuit tasks, including four predefined pursuit environments. (2) A streamlined real-world deployment pipeline that seamlessly translates simulation insights into practical drone evaluations using edge devices (such as Jetson Orin Nano) and Crazyflie drones. (3) A novel algorithm zoo integrated with a distributed training framework, featuring diverse algorithms explicitly tailored, for the first time, to multi-pursuer and multi-evader drone pursuit task. (4) Standardized evaluation protocols with newly designed unseen drone zoos, explicitly designed to rigorously assess the performance of adaptive teaming. Comprehensive experimental evaluations across four progressively challenging multi-drone pursuit scenarios confirm AT-Drone’s effectiveness in advancing adaptive teaming research. Real-world drone experiments further validate its practical feasibility and utility for realistic robotic operations. Videos, code and weights are available at \url{https://sites.google.com/view/at-drone}.} }
Endnote
%0 Conference Paper %T AT-Drone: Benchmarking Adaptive Teaming in Multi-Drone Pursuit %A Yang Li %A Junfan Chen %A Feng Xue %A Jiabin Qiu %A Wenbin Li %A Qingrui Zhang %A Ying Wen %A Wei Pan %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-li25a %I PMLR %P 1144--1161 %U https://proceedings.mlr.press/v305/li25a.html %V 305 %X Adaptive teaming—the capability of agents to effectively collaborate with unfamiliar teammates without prior coordination—is widely explored in virtual video games but overlooked in real-world multi-robot contexts. Yet, such adaptive collaboration is crucial for real-world applications, including border surveillance, search-and-rescue, and counter-terrorism operations. To address this gap, we introduce AT-Drone, the first dedicated benchmark explicitly designed to facilitate comprehensive training and evaluation of adaptive teaming strategies in multi-drone pursuit scenarios. AT-Drone makes the following key contributions: (1) An adaptable simulation environment configurator that enables intuitive and rapid setup of adaptive teaming multi-drone pursuit tasks, including four predefined pursuit environments. (2) A streamlined real-world deployment pipeline that seamlessly translates simulation insights into practical drone evaluations using edge devices (such as Jetson Orin Nano) and Crazyflie drones. (3) A novel algorithm zoo integrated with a distributed training framework, featuring diverse algorithms explicitly tailored, for the first time, to multi-pursuer and multi-evader drone pursuit task. (4) Standardized evaluation protocols with newly designed unseen drone zoos, explicitly designed to rigorously assess the performance of adaptive teaming. Comprehensive experimental evaluations across four progressively challenging multi-drone pursuit scenarios confirm AT-Drone’s effectiveness in advancing adaptive teaming research. Real-world drone experiments further validate its practical feasibility and utility for realistic robotic operations. Videos, code and weights are available at \url{https://sites.google.com/view/at-drone}.
APA
Li, Y., Chen, J., Xue, F., Qiu, J., Li, W., Zhang, Q., Wen, Y. & Pan, W.. (2025). AT-Drone: Benchmarking Adaptive Teaming in Multi-Drone Pursuit. Proceedings of The 9th Conference on Robot Learning, in Proceedings of Machine Learning Research 305:1144-1161 Available from https://proceedings.mlr.press/v305/li25a.html.

Related Material