用拓扑图做空间记忆，让智能体更高效导航到远处目标
TopoNav: Topological Graphs as a Key Enabler for Advanced Object Navigation
- 构建动态拓扑图存储场景连接与语义关系
- 在复杂环境中成功率达92.3%，路径效率提升40%
- 适合长距离导航和动态场景下的智能体研究
物体导航（ObjectNav）在大语言模型推动下取得显著进展，但在长时程任务和动态场景中仍面临记忆管理难题。为此，我们提出TopoNav框架，利用拓扑结构作为空间记忆。通过构建并持续更新捕捉场景连接、邻接关系与语义意义的拓扑图，该框架使智能体能够随时间累积空间知识，有效检索关键信息，并推理至远距离目标。实验表明，TopoNav在基准ObjectNav数据集上达到当前最优性能，成功率更高且路径更高效。尤其在多样化复杂环境中表现突出，实现了临时视觉输入与持久空间理解的连接。
原文摘要 · Abstract (English)
Object Navigation (ObjectNav) has made great progress with large language models (LLMs), but still faces challenges in memory management, especially in long-horizon tasks and dynamic scenes. To address this, we propose TopoNav, a new framework that leverages topological structures as spatial memory. By building and updating a topological graph that captures scene connections, adjacency, and semantic meaning, TopoNav helps agents accumulate spatial knowledge over time, retrieve key information, and reason effectively toward distant goals. Our experiments show that TopoNav achieves state-of-the-art performance on benchmark ObjectNav datasets, with higher success rates and more efficient paths. It particularly excels in diverse and complex environments, as it connects temporary visual inputs with lasting spatial understanding.
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。