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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yang, Chen, Junfan, Xue, Feng, Qiu, Jiabin, Li, Wenbin, Zhang, Qingrui, Wen, Ying, Pan, Wei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918006600237056
author Li, Yang
Chen, Junfan
Xue, Feng
Qiu, Jiabin
Li, Wenbin
Zhang, Qingrui
Wen, Ying
Pan, Wei
author_facet Li, Yang
Chen, Junfan
Xue, Feng
Qiu, Jiabin
Li, Wenbin
Zhang, Qingrui
Wen, Ying
Pan, Wei
contents 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 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 settings. (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}.
format Preprint
id arxiv_https___arxiv_org_abs_2502_09762
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AT-Drone: Benchmarking Adaptive Teaming in Multi-Drone Pursuit
Li, Yang
Chen, Junfan
Xue, Feng
Qiu, Jiabin
Li, Wenbin
Zhang, Qingrui
Wen, Ying
Pan, Wei
Robotics
Artificial Intelligence
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 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 settings. (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}.
title AT-Drone: Benchmarking Adaptive Teaming in Multi-Drone Pursuit
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2502.09762