Graph diffusion network for multi-agent reinforcement learning in drone swarm exploration

Drone swarm exploration has wide applications in rescue operations and engineering surveying. A drone swarm is a multi-agent system, and applying multi-agent reinforcement learning to such a system is an attractive topic in the field of robotics. In this paper, we propose a multi-agent reinforcement learning model that can chain-aggregate information from agents and apply it to the drone swarm via the Robot Operating System (ROS2). This model not only helps agents aggregate information with their neighbors but also enables the swarm to establish an organized structure, facilitating better cooperation and improving overall swarm performance. The model performs well in multi-drone exploration tasks, even in the presence of instability within the swarm. Experimental results demonstrate that the model enables effective cooperation among drones and achieves better global performance. Furthermore, we implemented the strategy based on our model on a physical platform to realize drone swarm exploration tasks. Although the cameras mounted on the drones have limited resolution, the swarm’s numerical advantage allows for high-quality exploration images, and the system outperforms other methods in terms of exploration efficiency and real-time data performance.