{"ID":2875794,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.01228","arxiv_id":"2509.01228","title":"OpenMulti: Open-Vocabulary Instance-Level Multi-Agent Distributed Implicit Mapping","abstract":"Multi-agent distributed collaborative mapping provides comprehensive and efficient representations for robots. However, existing approaches lack instance-level awareness and semantic understanding of environments, limiting their effectiveness for downstream applications. To address this issue, we propose OpenMulti, an open-vocabulary instance-level multi-agent distributed implicit mapping framework. Specifically, we introduce a Cross-Agent Instance Alignment module, which constructs an Instance Collaborative Graph to ensure consistent instance understanding across agents. To alleviate the degradation of mapping accuracy due to the blind-zone optimization trap, we leverage Cross Rendering Supervision to enhance distributed learning of the scene. Experimental results show that OpenMulti outperforms related algorithms in both fine-grained geometric accuracy and zero-shot semantic accuracy. In addition, OpenMulti supports instance-level retrieval tasks, delivering semantic annotations for downstream applications. The project website of OpenMulti is publicly available at https://openmulti666.github.io/.","short_abstract":"Multi-agent distributed collaborative mapping provides comprehensive and efficient representations for robots. However, existing approaches lack instance-level awareness and semantic understanding of environments, limiting their effectiveness for downstream applications. To address this issue, we propose OpenMulti, an...","url_abs":"https://arxiv.org/abs/2509.01228","url_pdf":"https://arxiv.org/pdf/2509.01228v1","authors":"[\"Jianyu Dou\",\"Yinan Deng\",\"Jiahui Wang\",\"Xingsi Tang\",\"Yi Yang\",\"Yufeng Yue\"]","published":"2025-09-01T08:15:53Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false}