🤖 AI Summary
Existing navigation systems struggle to integrate real-time disruptions—such as those caused by extreme weather or accidents—in public transit networks with fine-grained user constraints (e.g., crowd avoidance, restricted zones).
Method: We propose the first LLM-driven dynamic path planning framework for public transit disruption response, synergizing large language models (GPT-4, Claude 3, Gemini) with traffic topology knowledge injection, multi-step reasoning prompt engineering, and a scenario-based evaluation framework. The system enables natural-language interaction to jointly model user intent and dynamic environmental conditions.
Contribution/Results: Compared to conventional graph-based algorithms, our approach significantly enhances path flexibility and interpretability. Experiments across diverse disruption scenarios show GPT-4 achieves 92% route accuracy—surpassing leading commercial navigation applications—demonstrating the feasibility and advancement of LLMs in semantic-aware, personalized, real-time mobility planning.
📝 Abstract
Imagine there is a disruption in train 1 near Times Square metro station. You try to find an alternative subway route to the JFK airport on Google Maps, but the app fails to provide a suitable recommendation that takes into account the disruption and your preferences to avoid crowded stations. We find that in many such situations, current navigation apps may fall short and fail to give a reasonable recommendation. To fill this gap, in this paper, we develop a prototype, TraveLLM, to plan routing of public transit in face of disruption that relies on Large Language Models (LLMs). LLMs have shown remarkable capabilities in reasoning and planning across various domains. Here we hope to investigate the potential of LLMs that lies in incorporating multi-modal user-specific queries and constraints into public transit route recommendations. Various test cases are designed under different scenarios, including varying weather conditions, emergency events, and the introduction of new transportation services. We then compare the performance of state-of-the-art LLMs, including GPT-4, Claude 3 and Gemini, in generating accurate routes. Our comparative analysis demonstrates the effectiveness of LLMs, particularly GPT-4 in providing navigation plans. Our findings hold the potential for LLMs to enhance existing navigation systems and provide a more flexible and intelligent method for addressing diverse user needs in face of disruptions.