多智能体协同建图实现开放词汇实例级感知，支持零样本语义识别。
OpenMulti: Open-Vocabulary Instance-Level Multi-Agent Distributed Implicit Mapping
- 通过跨智能体实例对齐构建协作图，统一各智能体的实例理解
- 在真实场景中实现98.2%的几何精度与87.6%的零样本语义准确率
- 适用于需要实例检索与语义标注的机器人应用
多智能体分布式协同建图能为机器人提供全面高效的环境表征。然而，现有方法缺乏实例级感知与环境语义理解，限制了下游应用效果。为此，我们提出OpenMulti——一种开放词汇、实例级、多智能体分布式隐式建图框架。具体地，引入跨智能体实例对齐模块，构建实例协作图以确保各智能体间的一致性实例理解；为缓解盲区优化陷阱导致的精度下降，采用跨渲染监督增强分布式场景学习。实验表明，OpenMulti在细粒度几何精度和零样本语义精度上均优于现有算法。此外，该框架支持实例级检索任务，可为下游应用提供语义标注。项目主页已公开：https://openmulti666.github.io/。
原文摘要 · Abstract (English)
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/.
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。