Exploring the Potential of Large Language Models in Public Transportation: San Antonio Case Study

2025-01-07

AI Summary

This study addresses the low level of intelligence and limited AI adoption in public transit systems of medium- and small-sized cities. We present the first systematic investigation into deploying large language models (LLMs) within the San Antonio bus transit context. Our method introduces a GTFS-based traffic semantic understanding and response generation framework, integrating prompt engineering, multi-turn dialogue modeling, and inference with GPT-3.5/4-series models to build an extensible intelligent Q&A and decision-support prototype. Evaluation shows substantial improvements in traffic information retrieval accuracy (89%) and response completeness. We empirically validate LLM efficacy across real-time scheduling analysis, wait-time optimization, personalized route recommendation, and passenger satisfaction prediction. The work establishes a low-cost, highly adaptable AI empowerment paradigm for smart mobility in non-megacity settings, filling a critical research gap in systematic LLM applications to public transportation beyond mega-urban contexts.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: AI for Accessibility

Application Category

• 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
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The integration of large language models (LLMs) into public transit systems presents a transformative opportunity to enhance urban mobility. This study explores the potential of LLMs to revolutionize public transportation management within the context of San Antonio's transit system. Leveraging the capabilities of LLMs in natural language processing and data analysis, we investigate their capabilities to optimize route planning, reduce wait times, and provide personalized travel assistance. By utilizing the General Transit Feed Specification (GTFS) and other relevant data, this research aims to demonstrate how LLMs can potentially improve resource allocation, elevate passenger satisfaction, and inform data-driven decision-making in transit operations. A comparative analysis of different ChatGPT models was conducted to assess their ability to understand transportation information, retrieve relevant data, and provide comprehensive responses. Findings from this study suggest that while LLMs hold immense promise for public transit, careful engineering and fine-tuning are essential to realizing their full potential. San Antonio serves as a case study to inform the development of LLM-powered transit systems in other urban environments.

Problem

• Large Language Models
• Public Transportation Optimization
• Personalized Travel Recommendations

Innovation

• Large Language Models
• Public Transportation Optimization
• Data-Driven Decision Making