Newest papers

CoopUQ: Robust Multi-Robot Social Navigation via Uncertainty-Aware Cooperative Forecasting

Zehao Wang, Jianpeng Yao, Yuping Wang, Yiping Li, Jiaqi Li, Zhixu Li, Kanghoon Lee, Jinfeng Wang, Cong Liu, Zhaowei Tan, Jinkyoo Park, Jiachen Li · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26852 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

El aprendizaje reforzado permite a los robots móviles tomar decisiones de navegación rápidas y escalables en entornos limitados compartidos por humanos. No obstante, la extensión directa de los enfoques de un solo robot a la configuración de varios robots a menudo no garantiza la seguridad y la eficiencia, especialmente en escenarios de occlusiones y fuera de distribución (OOD), donde los robots individuales pueden ignorar riesgos potenciales o hacer predicciones inexactas. El aprovechamiento de la cooperación de forma efectiva para tanto la predicción como la navegación sigue siendo un gran desafío. Proponemos CoopUQ, un marco de navegación social multi-robot que enlaza la previsión de ocupación cooperativa consciente de la incertidumbre y la toma de decisiones robustas. CoopUQ predice los mapas de ocupación

Machine translation (Meta M2M100); the English original follows.

Abstract

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 uncertainty to guide policy via constrained multi-agent reinforcement learning, where the cost penalizes navigation through regions predicted to be occupied or highly uncertain. This design enables the policy to adapt its risk sensitivity under distribution shifts. Experimental results across multiple Unity3D-based simulation environments with both in-distribution and OOD settings, including diverse layouts, pedestrian densities, and rushing behavior, demonstrate improved prediction performance and safety over representative baselines. Real-robot experiments further demonstrate its robustness across various scenes. Our code and videos are available at https://coopuq.github.io/.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Robustness (evolution), Occupancy grid mapping, Reinforcement learning, Scalability, Pedestrian

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange