用模仿学习让上万机器人高效避障，速度与精度均超越现有方法。
Deploying Ten Thousand Robots: Scalable Imitation Learning for Lifelong Multi-Agent Path Finding
- 设计通信模块和分步冲突解决机制，结合全局引导提升路径规划能力。
- 在10,000个机器人场景下，吞吐量比顶尖学习法高137.7%，比搜索法高16.0%。
- 已实测部署于10台真实机器人，适合大规模多机协同系统应用。
长期多智能体路径规划（LMAPF）需持续为不断获得新目标的多个智能体生成无碰撞路径。近期学习方法虽反应快，但性能仍难媲美最优搜索算法，尤其在大规模场景中。本文提出基于模仿学习的可扩展解决方案SILLM，引入新型通信模块、单步冲突消解及全局引导技术。借助现代GPU，SILLM兼具学习方法的快速推理与搜索方法的高质量解。在六张大规模地图（最多10,000个智能体）上，其平均吞吐量分别较最佳学习基线和搜索基线提升137.7%和16.0%。此外，该方案还超越了2023年机器人跑者联赛的冠军解法。最后，我们在模拟仓库环境中成功验证了10台真实机器人与100个虚拟机器人的部署效果。
原文摘要 · Abstract (English)
Lifelong Multi-Agent Path Finding (LMAPF) repeatedly finds collision-free paths for multiple agents that are continually assigned new goals when they reach current ones. Recently, this field has embraced learning-based methods, which reactively generate single-step actions based on individual local observations. However, it is still challenging for them to match the performance of the best search-based algorithms, especially in large-scale settings. This work proposes an imitation-learning-based LMAPF solver that introduces a novel communication module as well as systematic single-step collision resolution and global guidance techniques. Our proposed solver, Scalable Imitation Learning for LMAPF (SILLM), inherits the fast reasoning speed of learning-based methods and the high solution quality of search-based methods with the help of modern GPUs. Across six large-scale maps with up to 10,000 agents and varying obstacle structures, SILLM surpasses the best learning- and search-based baselines, achieving average throughput improvements of 137.7% and 16.0%, respectively. Furthermore, SILLM also beats the winning solution of the 2023 League of Robot Runners, an international LMAPF competition. Finally, we validated SILLM with 10 real robots and 100 virtual robots in a mock warehouse environment.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。