Navigating Heat Exposure: Simulation of Route Planning Based on Visual Language Model Agents

2025-03-17

AI Summary

Existing thermal-adaptive path planning methods overlook inter-individual physiological variability and heterogeneous environmental perception, limiting their applicability to human-centered high-temperature pedestrian navigation. Method: This paper proposes a Vision-Language Model (VLM)-driven Persona-Perception-Planning-Memory (PPPM) framework—the first to jointly leverage street-view imagery and road-network topology. Built upon Gemini-2.0, it establishes an interpretable visual-language modeling paradigm via structured prompt engineering, enabling representation of eight thermally sensitive persona types and perception-driven path decision simulation. Contribution/Results: Validated against questionnaire surveys and field measurements, the framework achieves statistically significant alignment between simulated path preferences and empirical observations (p < 0.01). It processes single-route queries in 47.81 seconds at a cost of USD 0.006, enabling high-resolution thermal-response mobility analysis and supporting climate-resilient urban planning.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Heat exposure significantly influences pedestrian routing behaviors. Existing methods such as agent-based modeling (ABM) and empirical measurements fail to account for individual physiological variations and environmental perception mechanisms under thermal stress. This results in a lack of human-centred, heat-adaptive routing suggestions. To address these limitations, we propose a novel Vision Language Model (VLM)-driven Persona-Perception-Planning-Memory (PPPM) framework that integrating street view imagery and urban network topology to simulate heat-adaptive pedestrian routing. Through structured prompt engineering on Gemini-2.0 model, eight distinct heat-sensitive personas were created to model mobility behaviors during heat exposure, with empirical validation through questionnaire survey. Results demonstrate that simulation outputs effectively capture inter-persona variations, achieving high significant congruence with observed route preferences and highlighting differences in the factors driving agents decisions. Our framework is highly cost-effective, with simulations costing 0.006USD and taking 47.81s per route. This Artificial Intelligence-Generated Content (AIGC) methodology advances urban climate adaptation research by enabling high-resolution simulation of thermal-responsive mobility patterns, providing actionable insights for climate-resilient urban planning.

Problem

• Simulate heat-adaptive pedestrian routing using Vision Language Model.
• Address individual physiological and environmental perception under thermal stress.
• Provide cost-effective, high-resolution simulation for climate-resilient urban planning.

Innovation

• VLM-driven PPPM framework for heat-adaptive routing
• Integrates street view imagery and urban topology
• Cost-effective AIGC methodology for urban planning