ChatSUMO: Large Language Model for Automating Traffic Scenario Generation in Simulation of Urban MObility

TL;DR

ChatSUMO introduces an LLM-driven agent that automates SUMO traffic-scenario generation from natural-language prompts. It translates user descriptions into executable Python pipelines that fetch OpenStreetMap data, build networks, run SUMO, and analyze outputs. The system comprises an Input, Simulation Generation, Customization, and Analysis module, and uses Llama 3.1 to achieve Albany real-world simulations with an accuracy of $96\%$ in network reproduction. Experimental results show substantial time savings (about 1 minute vs. 15 minutes manual) and enable edge edits, traffic-light optimization, and vehicle-type edits, with measurable impacts on density, travel time, emissions, and fuel. Overall, ChatSUMO lowers barriers to traffic-simulation exploration and supports iterative, data-driven decision-making, with potential online deployment and real-time data integration.

Abstract

Large Language Models (LLMs), capable of handling multi-modal input and outputs such as text, voice, images, and video, are transforming the way we process information. Beyond just generating textual responses to prompts, they can integrate with different software platforms to offer comprehensive solutions across diverse applications. In this paper, we present ChatSUMO, a LLM-based agent that integrates language processing skills to generate abstract and real-world simulation scenarios in the widely-used traffic simulator - Simulation of Urban MObility (SUMO). Our methodology begins by leveraging the LLM for user input which converts to relevant keywords needed to run python scripts. These scripts are designed to convert specified regions into coordinates, fetch data from OpenStreetMap, transform it into a road network, and subsequently run SUMO simulations with the designated traffic conditions. The outputs of the simulations are then interpreted by the LLM resulting in informative comparisons and summaries. Users can continue the interaction and generate a variety of customized scenarios without prior traffic simulation expertise. For simulation generation, we created a real-world simulation for the city of Albany with an accuracy of 96\%. ChatSUMO also realizes the customizing of edge edit, traffic light optimization, and vehicle edit by users effectively.

Figures (6)

• Figure 1: ChatSUMO Framework
• Figure 2: Simulation Generation
• Figure 3: Edge Customization Experiment
• Figure 4: Traffic Light Adaptation
• Figure 5: Vehicle Type Proportion Edit with the ChatSUMO Interface.