NarraGuide: an LLM-based Narrative Mobile Robot for Remote Place Exploration

2025-08-02

AI Summary

Existing telepresence robotic systems rely heavily on users’ prior knowledge, limiting their effectiveness for exploring unfamiliar environments. This paper proposes a location-aware, large language model (LLM)-driven mobile robot framework that tightly integrates high-precision localization with the narrative generation capabilities of LLMs, enabling spatially triggered, context-sensitive tour content synthesis and natural-language conversational interaction. Deployed in a real-world geology museum, the system supported 20 remote users in completing end-to-end guided exploration tasks. To our knowledge, this is the first work to introduce embodied, location-aware LLM-based narration into mobile robotics—establishing a novel paradigm for situation-adaptive, story-driven remote exploration. Evaluation demonstrates significant improvements in users’ environmental awareness, task completion rate, and immersion. The results validate both the technical feasibility and practical potential of LLM-augmented embodied narrative guidance.

Technology Category

• Intelligent Robots: Embodied AI
• Natural Language Processing: Safety and Robustness
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• 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: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Robotic telepresence enables users to navigate and experience remote environments. However, effective navigation and situational awareness depend on users' prior knowledge of the environment, limiting the usefulness of these systems for exploring unfamiliar places. We explore how integrating location-aware LLM-based narrative capabilities into a mobile robot can support remote exploration. We developed a prototype system, called NarraGuide, that provides narrative guidance for users to explore and learn about a remote place through a dialogue-based interface. We deployed our prototype in a geology museum, where remote participants (n=20) used the robot to tour the museum. Our findings reveal how users perceived the robot's role, engaged in dialogue in the tour, and expressed preferences for bystander encountering. Our work demonstrates the potential of LLM-enabled robotic capabilities to deliver location-aware narrative guidance and enrich the experience of exploring remote environments.

Problem

• Enhancing remote exploration with LLM-based narrative guidance
• Improving situational awareness in unfamiliar environments via robots
• Developing dialogue-based interfaces for location-aware robotic tours

Innovation

• LLM-based narrative mobile robot
• Location-aware dialogue interface
• Remote exploration guidance system