图神经网络在去中心化无标签运动规划中的泛化能力
Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning
AI总结：
本文针对去中心化无标签运动规划问题，提出基于图神经网络学习的策略，结合模仿学习与强化学习，在100个机器人上训练后可泛化至500个机器人，平均性能超越现有方法8.6%。
摘要：
无标签运动规划涉及将一组机器人分配到目标位置，同时确保避免碰撞，旨在最小化总行驶距离。该问题是多机器人系统在探索、监视和运输等应用中的基本构建模块。我们在去中心化场景下解决该问题，其中每个机器人仅知道其 k 个最近机器人和 k 个最近目标的位置。该场景结合了组合分配和连续空间运动规划的元素，对传统集中式方法提出了显著的可扩展性挑战。为克服这些挑战，我们提出了一种通过图神经网络（GNN）学习的去中心化策略。该 GNN 使机器人能够确定（1）向邻居传达什么信息，以及（2）如何将接收到的信息与局部观测相结合以进行决策。我们使用模仿学习训练 GNN，以集中式匈牙利算法作为专家策略，并进一步使用强化学习进行微调以避免碰撞并提升性能。大量实证评估证明了我们方法的可扩展性和有效性。在 100 个机器人上训练的 GNN 策略可泛化到多达 500 个机器人的场景，平均优于最先进解决方案 8.6%，并显著超越贪心去中心化方法。这项工作为在可扩展性至关重要的场景中解决多机器人协调问题奠定了基础。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
