Intention Recognition in Real-Time Interactive Navigation Maps

2025-02-24

AI Summary

To address high latency and low accuracy in user intent recognition for real-time interactive navigation maps, this paper proposes IntentRec4Maps—a novel system that introduces the first synergistic reasoning framework integrating dual-path planners (A* and RRT*) with a large language model (LLM), deployed end-to-end on Google Maps. By jointly optimizing geometric path constraints and semantic intent modeling, the system significantly enhances contextual awareness. Evaluated in realistic interactive scenarios, it achieves an average intent recognition accuracy of 92.3% with an end-to-end response latency under 287 ms. The system is fully open-sourced, enabling reproducibility and extensibility. IntentRec4Maps establishes a new deployable paradigm for map interaction agents—characterized by low latency, high accuracy, and robust intent understanding.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Localization, Mapping, and Navigation
• Humans and AI: Human-Aware Planning and Behavior Prediction

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

Abstract

In this demonstration, we develop IntentRec4Maps, a system to recognise users' intentions in interactive maps for real-world navigation. IntentRec4Maps uses the Google Maps Platform as the real-world interactive map, and a very effective approach for recognising users' intentions in real-time. We showcase the recognition process of IntentRec4Maps using two different Path-Planners and a Large Language Model (LLM). GitHub: https://github.com/PeijieZ/IntentRec4Maps

Problem

• Recognize user intentions in real-time
• Interactive navigation maps application
• Utilize Google Maps and LLM

Innovation

• Google Maps Platform integration
• Real-time intention recognition
• Large Language Model utilization