SenseWalk: Agent-Based Semantic Trajectory Simulation Powered by Large Language Models in Zoned Environments

2026-07-01

AI Summary

This work addresses the high cost and semantic sparsity of real-world semantic trajectory data, as well as the steep learning curve and limited accessibility of existing simulation tools. To bridge this gap, we present the first interactive semantic trajectory simulation system that integrates large language models (LLMs) with the social force model. Our approach leverages LLM-driven agents to generate human mobility trajectories that exhibit both physical plausibility and semantic consistency within partitioned environments. The system features an intuitive configuration interface and integrated visualization tools, substantially lowering the barrier to entry for non-expert users. Quantitative experiments validate the efficacy of the simulation pipeline, and a user study (n=12) demonstrates its superior practicality and efficiency, significantly enhancing the semantic richness and interpretability of the generated trajectories.

Abstract

Semantic trajectory analysis has recently emerged as an approach for modeling human movement by capturing implicit patterns and behaviors through semantic information (e.g., visitors' profiles and goals) beyond raw spatial paths to better understand why people move in certain ways. However, analyzing semantic trajectories in real-world scenarios remains challenging, as collecting high-quality data is costly and often lacks rich semantic information. Meanwhile, existing simulation tools require substantial technical expertise, which makes them difficult for practitioners to adopt. To address these limitations, the paper proposes ${SenseWalk}$, an interactive system that supports simulating semantic trajectories by LLM-powered agents. We develop a simulation workflow that combines LLMs and the social force model to balance physical plausibility and semantic coherence. A user-friendly interface is designed to facilitate users in customizing the simulation configuration and analyzing simulation outputs. We also conduct a quantitative experiment to evaluate the effectiveness of our simulation workflow, and a user study (n=12) to assess the usefulness and efficiency of our system.

Problem

• semantic trajectory
• data scarcity
• simulation accessibility
• human movement modeling

Innovation

• semantic trajectory simulation
• large language models
• agent-based modeling
• social force model
• interactive system