The User-Centric Geo-Experience: An LLM-Powered Framework for Enhanced Planning, Navigation, and Dynamic Adaptation

2025-07-09

AI Summary

Contemporary travel planning systems suffer from static design and fragmented functionality, rendering them ill-equipped to handle dynamic environmental changes and itinerary disruptions—leading to inaccurate “last-meter” navigation, misaligned intent interpretation, and delayed responses. To address these limitations, this paper proposes a user-centric geospatial experience framework featuring a tri-agent collaborative architecture: spatial semantic understanding, fine-grained navigation, and real-time disturbance response. The framework integrates grid-based spatial localization, map analytics, visual embeddings, and retrieval-augmented generation (RAG)-enhanced large language models to enable multimodal intent parsing and closed-loop decision-making. Experimental results demonstrate substantial improvements over baseline methods in query understanding accuracy (+18.7%), sub-meter navigation precision (+23.4%), and adaptability to unforeseen scenarios (e.g., route blockages or sudden weather events). The system effectively supports complex urban exploration and emergency mobility use cases.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Multiagent Systems: Multiagent Planning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Traditional travel-planning systems are often static and fragmented, leaving them ill-equipped to handle real-world complexities such as evolving environmental conditions and unexpected itinerary disruptions. In this paper, we identify three gaps between existing service providers causing frustrating user experience: intelligent trip planning, precision "last-100-meter" navigation, and dynamic itinerary adaptation. We propose three cooperative agents: a Travel Planning Agent that employs grid-based spatial grounding and map analysis to help resolve complex multi-modal user queries; a Destination Assistant Agent that provides fine-grained guidance for the final navigation leg of each journey; and a Local Discovery Agent that leverages image embeddings and Retrieval-Augmented Generation (RAG) to detect and respond to trip plan disruptions. With evaluations and experiments, our system demonstrates substantial improvements in query interpretation, navigation accuracy, and disruption resilience, underscoring its promise for applications from urban exploration to emergency response.

Problem

• Addressing static fragmented travel planning systems
• Improving precision last-100-meter navigation accuracy
• Enhancing dynamic itinerary adaptation disruptions

Innovation

• Grid-based spatial grounding for multi-modal queries
• Fine-grained guidance for last-100-meter navigation
• Image embeddings and RAG for disruption response