Adaptive Teaming in Multi-Drone Pursuit: Simulation, Training, and Deployment

2025-02-13

AI Summary

This paper addresses the “zero-prior-cooperation” challenge in multi-UAV cooperative pursuit—where UAVs must dynamically form adaptive teams without predefined formations or prior knowledge of teammates’ capabilities. To this end, we propose AT-MDP, the first adaptive teaming framework for continuous-action spaces, coupled with a distributed reinforcement learning algorithm. We further introduce the Unseen Drone Zoo evaluation paradigm to systematically assess generalization across heterogeneous teammates. Our approach integrates a high-fidelity simulation configurator, a lightweight edge training and deployment system, and is implemented on the Crazyflie physical platform. In a four-tier progressive simulation environment, our method achieves significantly higher cooperative success rates than baselines. Moreover, real-world experiments demonstrate successful multi-UAV adaptive pursuit, validating the framework’s effectiveness and robustness in sim-to-real transfer.

Technology Category

• Multiagent Systems: Teamwork
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Adaptive teaming, the ability to collaborate with unseen teammates without prior coordination, remains an underexplored challenge in multi-robot collaboration. This paper focuses on adaptive teaming in multi-drone cooperative pursuit, a critical task with real-world applications such as border surveillance, search-and-rescue, and counter-terrorism. We first define and formalize the extbf{A}daptive Teaming in extbf{M}ulti- extbf{D}rone extbf{P}ursuit (AT-MDP) problem and introduce AT-MDP framework, a comprehensive framework that integrates simulation, algorithm training and real-world deployment. AT-MDP framework provides a flexible experiment configurator and interface for simulation, a distributed training framework with an extensive algorithm zoo (including two newly proposed baseline methods) and an unseen drone zoo for evaluating adaptive teaming, as well as a real-world deployment system that utilizes edge computing and Crazyflie drones. To the best of our knowledge, AT-MDP framework is the first adaptive framework for continuous-action decision-making in complex real-world drone tasks, enabling multiple drones to coordinate effectively with unseen teammates. Extensive experiments in four multi-drone pursuit environments of increasing difficulty confirm the effectiveness of AT-MDP framework, while real-world deployments further validate its feasibility in physical systems. Videos and code are available at https://sites.google.com/view/at-mdp.

Problem

• adaptive teaming in multi-drone pursuit
• simulation, training, and deployment framework
• coordination with unseen teammates

Innovation

• Simulation configurator for drone teams
• Distributed training with algorithm zoo
• Edge computing for real-world deployment