Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning
This work addresses scalability challenges in multi-robot coordination for applications like exploration and surveillance, though it is incremental as it builds on existing GNN and imitation learning techniques.
The paper tackles decentralized unlabeled motion planning for multi-robot systems by proposing a Graph Neural Network (GNN) policy that enables robots to communicate and make decisions based on local observations, achieving an 8.6% average improvement over state-of-the-art solutions and scaling from 100 to 500 robots.
Unlabeled motion planning involves assigning a set of robots to target locations while ensuring collision avoidance, aiming to minimize the total distance traveled. The problem forms an essential building block for multi-robot systems in applications such as exploration, surveillance, and transportation. We address this problem in a decentralized setting where each robot knows only the positions of its $k$-nearest robots and $k$-nearest targets. This scenario combines elements of combinatorial assignment and continuous-space motion planning, posing significant scalability challenges for traditional centralized approaches. To overcome these challenges, we propose a decentralized policy learned via a Graph Neural Network (GNN). The GNN enables robots to determine (1) what information to communicate to neighbors and (2) how to integrate received information with local observations for decision-making. We train the GNN using imitation learning with the centralized Hungarian algorithm as the expert policy, and further fine-tune it using reinforcement learning to avoid collisions and enhance performance. Extensive empirical evaluations demonstrate the scalability and effectiveness of our approach. The GNN policy trained on 100 robots generalizes to scenarios with up to 500 robots, outperforming state-of-the-art solutions by 8.6\% on average and significantly surpassing greedy decentralized methods. This work lays the foundation for solving multi-robot coordination problems in settings where scalability is important.