360CityArena：面向具身智能体的真实虚拟城市导航基准
360CityArena: A Realistic Virtual Urban Navigation Benchmark for Embodied Agents
查看机构详情
- The University of Tokyo（东京大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
研究人员提出基于东京秋叶原重建的360CityArena城市导航基准，评估具身智能体城市探索能力，发现最强模型Gemini 2.5 Flash表现远低于人类，为相关研究提供了挑战性测试平台。
中文摘要 AI 辅助
我们提出了360CityArena，这是一个用于在由360度视频构建的照片级真实环境中评估具身智能体城市探索能力的基准。现有的户外基准要么缺乏足够的照片真实感，要么复杂度不足，与真实世界的城市环境存在显著差距。360CityArena基于对日本东京秋叶原地区的真实重建构建，使用了602段覆盖85条街道的360度视频片段，包含175项由人工精心设计的任务。它涵盖三类任务：环境理解、路径推理和空间推理，覆盖了城市探索所需的基本能力，如定位、地标搜索、路径规划和关系空间推理，从而能够在真实城市场景中进行全面评估。我们使用最先进的基于大型多模态模型（LMM）的智能体进行评估，结果显示，即使是最强的模型Gemini 2.5 Flash，其表现也远低于人类水平（人类：77.3%，Gemini 2.5 Flash：17.1%），这表明在城市规模的具身导航和推理方面仍存在重大挑战。360CityArena为照片级真实的城市区域导航和空间推理提供了必要且具有挑战性的测试平台。
英文摘要
We present 360CityArena, a benchmark for evaluating the urban exploration capabilities of embodied agents within a photorealistic environment constructed from 360-degree videos. Existing outdoor benchmarks either lack sufficient photorealism or complexity, resulting in a considerable gap from real-world urban environments. 360CityArena is built on a realistic reconstruction of the Akihabara district in Tokyo, Japan, using 602 360-degree video segments covering 85 streets, and consists of 175 meticulously human-crafted tasks. It encompasses three task categories: Environment Understanding, Path Reasoning, and Spatial Reasoning, covering fundamental abilities required for urban exploration, such as localization, landmark search, path planning, and relational spatial reasoning, thereby enabling comprehensive evaluation in realistic urban scenes. Our evaluation using state-of-the-art LMM-based agents shows that even the strongest model, Gemini 2.5 Flash, performs far below human level (human: 77.3% vs. Gemini 2.5 Flash: 17.1%), revealing substantial challenges that remain in city-scale embodied navigation and reasoning. 360CityArena provides a necessary and challenging testbed for photorealistic urban-district navigation and spatial reasoning.
