多智能体去中心化导航系统，支持多模态目标与多物体任务。
DM$^3$-Nav: Decentralized Multi-Agent Multimodal Multi-Object Semantic Navigation
- 无中央协调，通过临时通信交换局部地图和意图实现协作。
- 在HM3DSem数据集上性能媲美甚至超越集中式系统。
- 适用于真实办公室环境，仅依赖本地感知与计算部署。
我们提出DM$^3$-Nav，一个完全去中心化的多智能体语义导航系统，支持多模态开放词汇目标描述与多物体任务。在该设定中，去中心化意味着运行时不依赖中央协调器、全局地图聚合或共享全局状态。机器人自主运行并通过临时成对通信交换局部地图、目标状态和导航意图，无需同步。一种结合意图广播与距离加权前沿选择的隐式任务分配机制，在保持去中心化的同时减少冗余探索。在HM3DSem场景下使用HM3Dv0.2和GOAT-Bench数据集的评估表明，DM$^3$-Nav在性能上达到或超过集中式及共享地图基线，同时消除了集中式架构固有的单点故障。最后，我们在真实办公室环境中用两台移动机器人验证了该方法，展示了完全依赖车载感知与计算的成功部署。真实世界实验视频可在线查看：https://drive.google.com/file/d/1QiUSCn5rIvtuTUqtuXLPgmt6S8x9-MCZ/view?usp=drive_link
原文摘要 · Abstract (English)
We present DM$^3$-Nav, a fully decentralized multi-agent semantic navigation system supporting multimodal open-vocabulary goal specification and multi-object missions. In our setting, decentralization implies operation without a central coordinator, global map aggregation, or shared global state at runtime. Robots operate autonomously and coordinate through ad-hoc pairwise communication, exchanging local maps, goal status, and navigation intent without synchronization. An implicit task allocation mechanism combining intent broadcasting and distance-weighted frontier selection reduces redundant exploration while preserving decentralized operation. Evaluations on HM3DSem scenes using the HM3Dv0.2 and GOAT-Bench datasets demonstrate that DM$^3$-Nav matches or exceeds centralized and shared-map baselines while eliminating single points of failure inherent in centralized architectures. Finally, we validate our approach in a real-world office environment using two mobile robots, demonstrating successful deployment relying entirely on onboard sensing and computation. A video of our real-world experiments is available online: https://drive.google.com/file/d/1QiUSCn5rIvtuTUqtuXLPgmt6S8x9-MCZ/view?usp=drive_link
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。