多智能体在城市级户外环境协作找安全会合点并导航避障。
Sentinel: Embodied Cooperative Spatial Reasoning and Planning
- 用大模型沟通+经典算法导航，实现动态协作规划
- 3-5个智能体在14个城市场景中平均更快会合、路径更短
- 适合研究多智能体协同导航与具身AI的开发者
本文研究去中心化具身智能体在城市级户外环境中，面对动态环境约束时的协作空间智能。我们提出Sentinel Challenge基准，要求多个去中心化智能体通过自然语言通信，在大型户外场景中协商一个共同安全且便利的会合点。每个智能体随后需避开巡逻的动态哨兵，利用提供粗略空间信息的工具安全导航。为此，我们提出CoSaR（协作空间推理与规划）框架，将基础模型的高层沟通与规划能力与经典空间导航算法的精度相结合。CoSaR使智能体能够交换情境更新，推理动态空间约束，并协同重规划路径。在包含3-5个智能体的14个城市场景中评估显示，CoSaR consistently 实现更快会合、更短路径长度和更高安全性。结果表明，动态通信与空间推理的融合对鲁棒多智能体协作至关重要。通过定义这一新场景并提供可扩展基准，我们旨在为具身多智能体系统的协作空间智能发展奠定基础。代码与挑战已开源：https://github.com/UMass-Embodied-AGI/Sentinel。
原文摘要 · Abstract (English)
In this work, we study Cooperative Spatial Intelligence, the ability of decentralized embodied agents to coordinate effectively under dynamic environmental constraints across city-scale outdoor domains. We introduce Sentinel Challenge, a benchmark where multiple decentralized embodied agents must communicate in natural language to agree on a mutually safe and convenient meeting point within large, city-scale outdoor environments. Each agent must then navigate safely while avoiding dynamic sentinels patrolling the area, using a tool that provides coarse spatial information. To address this, we propose CoSaR (Cooperative Spatial Reasoning and Planning), a framework that bridges the high-level communication and planning abilities of foundation models with the precision of classical spatial navigation algorithms. CoSaR enables agents to exchange situational updates, reason over evolving spatial constraints, and collaboratively replan trajectories. Evaluated across 14 city-level scenes with 3-5 agents, CoSaR consistently leads to faster gathering, shorter path lengths, and improved safety. Our results demonstrate that integrating dynamic communication with spatial reasoning is essential for robust multi-agent cooperation. By formalizing this new setting and providing a scalable benchmark, we aim to build a foundation for advancing cooperative spatial intelligence in embodied multi-agent systems. Code and challenge are available at https://github.com/UMass-Embodied-AGI/Sentinel.
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。