用生成式智能体模拟真实行人行为，助力城市空间设计。
TravelAgent: Generative Agents in the Built Environment
- 将生成式智能体嵌入3D环境，模拟多场景下行人决策与行为。
- 100次模拟中完成率76%，覆盖1898步路径与多样化空间布局。
- 适合城市规划、空间认知研究者，可评估建筑布局合理性。
理解人在建成环境中的行为对打造以人为本的都市空间至关重要。传统方法如人工观察、问卷调查和简化仿真难以捕捉现实行为的复杂性与动态性。为此，我们提出TravelAgent，一种新型仿真平台，可模拟不同室内外环境中行人在多种情境下的导航与活动模式。TravelAgent将生成式智能体融入3D虚拟环境，使智能体能处理多模态感官输入，表现出类人决策、行为与适应能力。通过导航、路径寻找和自由探索实验，我们分析了100次模拟中1898个智能体步长的数据，整体任务完成率达76%。结合空间、语言和情感分析，揭示智能体如何感知、适应或难以应对所处环境与任务。研究显示TravelAgent在城市设计、空间认知研究及基于智能体建模方面具有潜力。我们讨论了部署生成式智能体评估与优化空间设计的关键挑战与机遇，提出TravelAgent作为模拟和理解人在建成环境中体验的新范式。
原文摘要 · Abstract (English)
Understanding human behavior in built environments is critical for designing functional, user centered urban spaces. Traditional approaches, such as manual observations, surveys, and simplified simulations, often fail to capture the complexity and dynamics of real world behavior. To address these limitations, we introduce TravelAgent, a novel simulation platform that models pedestrian navigation and activity patterns across diverse indoor and outdoor environments under varying contextual and environmental conditions. TravelAgent leverages generative agents integrated into 3D virtual environments, enabling agents to process multimodal sensory inputs and exhibit human-like decision-making, behavior, and adaptation. Through experiments, including navigation, wayfinding, and free exploration, we analyze data from 100 simulations comprising 1898 agent steps across diverse spatial layouts and agent archetypes, achieving an overall task completion rate of 76%. Using spatial, linguistic, and sentiment analyses, we show how agents perceive, adapt to, or struggle with their surroundings and assigned tasks. Our findings highlight the potential of TravelAgent as a tool for urban design, spatial cognition research, and agent-based modeling. We discuss key challenges and opportunities in deploying generative agents for the evaluation and refinement of spatial designs, proposing TravelAgent as a new paradigm for simulating and understanding human experiences in built environments.
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。