SenseWalk: Agent-Based Semantic Trajectory Simulation Powered by Large Language Models in Zoned Environments
2026-07-01 • Human-Computer Interaction
Human-Computer InteractionArtificial Intelligence
AI summaryⓘ
The authors created SenseWalk, a system that helps simulate how people move by combining story-like details about people with realistic movement patterns. They use advanced language models and a social force model to make the simulated movements both believable and meaningful. The system is designed to be easy to use, allowing users to customize settings and study the results. The authors tested the system with experiments and user feedback to show it works well and is helpful.
semantic trajectoryLLM (Large Language Model)social force modelhuman movement simulationuser interfacesimulation workflowsemantic informationquantitative experimentuser study
Authors
Ziyue Lin, Xinhang Xie, Kangyi Wang, Siming Chen
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.