HOLA-Drone: Hypergraphic Open-ended Learning for Zero-Shot Multi-Drone Cooperative Pursuit

TL;DR

This paper introduces HOLA-Drone, a novel learning algorithm for multi-drone cooperation that adapts to unseen partners in pursuit scenarios, demonstrating superior coordination in simulations and real-world tests.

Contribution

HOLA-Drone is the first to apply hypergraphic open-ended learning to zero-shot multi-drone cooperation, enabling adaptive coordination with unseen drone teammates.

Findings

HOLA-Drone outperforms baseline methods in unseen partner coordination.

Experimental results show effective real-world deployment.

The approach generalizes well to different drone teammate pools.

Abstract

Zero-shot coordination (ZSC) is a significant challenge in multi-agent collaboration, aiming to develop agents that can coordinate with unseen partners they have not encountered before. Recent cutting-edge ZSC methods have primarily focused on two-player video games such as OverCooked!2 and Hanabi. In this paper, we extend the scope of ZSC research to the multi-drone cooperative pursuit scenario, exploring how to construct a drone agent capable of coordinating with multiple unseen partners to capture multiple evaders. We propose a novel Hypergraphic Open-ended Learning Algorithm (HOLA-Drone) that continuously adapts the learning objective based on our hypergraphic-form game modeling, aiming to improve cooperative abilities with multiple unknown drone teammates. To empirically verify the effectiveness of HOLA-Drone, we build two different unseen drone teammate pools to evaluate their performance in coordination with various unseen partners. The experimental results demonstrate that HOLA-Drone outperforms the baseline methods in coordination with unseen drone teammates. Furthermore, real-world experiments validate the feasibility of HOLA-Drone in physical systems. Videos can be found on the project homepage~\url{https://sites.google.com/view/hola-drone}.