Zehao Wang, Jianpeng Yao, Yuping Wang, Yiping Li, Jiaqi Li, Zhixu Li, Kanghoon Lee, Jinfeng Wang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26852 · open-access PDF
L’apprentissage renforcé permet aux robots mobiles de prendre des décisions de navigation rapides et évolutives dans des environnements partagés par l’homme restreints. Cependant, l’extension directe des approches d’un seul robot aux paramètres de plusieurs robots ne permet souvent pas d’assurer la sécurité et l’efficacité, en particulier dans les scénarios d’occlusion et d’out-of-distribution (OOD), où les robots individuels peuvent ignorer les risques potentiels ou faire des prédictions inexactes.
Machine translation (Meta M2M100); the English original follows.
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 co
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26852, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange