[论文] CoopUQ: Robust Multi-Robot Social Navigation via Uncertainty-Aware Coo...

论文概要

研究领域: ML 作者: Zehao Wang, Jianpeng Yao, Yuping Wang, Yiping Li, Jiaqi Li, Zhixu Li, Kanghoon Lee, Jinfeng Wang, Cong Liu, Zhaowei Tan, Jinkyoo Park, Jiachen Li 发布时间: 2026-10-19 arXiv: 2610.26852

中文摘要

强化学习使人机共享环境中的快速导航决策成为可能，但将单机器人方法扩展到多机器人场景往往在遮挡和分布外（OOD）场景下失效。我们提出CoopUQ——桥接不确定性感知的协作占据预测与鲁棒决策的多机器人社交导航框架。CoopUQ通过跨机器人时空特征融合预测未来占据栅格地图，并利用预测不确定性通过约束多agent强化学习引导策略，代价函数惩罚穿越预测为已占据或高度不确定的区域。在多个Unity3D仿真环境（含多样化布局和行人群密度）中的实验表明预测性能和安全性均优于基线。真实机器人实验进一步验证了鲁棒性。

原文摘要

Reinforcement learning enables mobile robots to make fast and scalable navigation decisions in constrained human-shared environments. However, directly extending single-robot approaches to multi-robot settings often fails to ensure safety and efficiency, especially under occlusions and out-of-distribution (OOD) scenarios, where individual robots may overlook potential risks or make inaccurate predictions. Leveraging cooperation effectively for both prediction and navigation remains a major challenge. We propose CoopUQ, a multi-robot social navigation framework that bridges uncertainty-aware cooperative occupancy forecasting and robust decision making. CoopUQ predicts future occupancy grid maps through cross-robot spatiotemporal feature fusion and further leverages forecasts and their uncer...

#论文 #arXiv #ML #小凯