# LLM-Guided Indoor Navigation with Multimodal Map Understanding

arXiv: https://arxiv.org/abs/2503.11702 · HTML: https://mlsanity.com/paper/2503.11702/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 11 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Builds on (most cited first, 3 of 3)

- [Enhancing the Travel Experience for People with Visual Impairments through Multimodal Interaction: NaviGPT, A Real-Time AI-Driven Mobile Navigation System](https://mlsanity.com/paper/2410.04005/) (2024)
- [Multimodal Large Language Model for Visual Navigation](https://mlsanity.com/paper/2310.08669/) (2023)
- [Towards Ubiquitous Indoor Positioning: Comparing Systems across Heterogeneous Datasets](https://mlsanity.com/paper/2109.09436/) (2021)

## Built on by (most cited first, 4 of 4)

- [NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities](https://mlsanity.com/paper/2509.16656/) (2025)
- [MapTrace: Scalable Data Generation for Route Tracing on Maps](https://mlsanity.com/paper/2512.19609/) (2025)
- [LLM-Guided Agentic Floor Plan Parsing for Accessible Indoor Navigation of Blind and Low-Vision People](https://mlsanity.com/paper/2604.23970/) (2026)
- [Floorplan2Guide: LLM-Guided Floorplan Parsing for BLV Indoor Navigation](https://mlsanity.com/paper/2512.12177/) (2025)

## Abstract (arXiv)

Indoor navigation presents unique challenges due to complex layouts and the unavailability of GNSS signals. Existing solutions often struggle with contextual adaptation, and typically require dedicated hardware. In this work, we explore the potential of a Large Language Model (LLM), i.e., ChatGPT, to generate natural, context-aware navigation instructions from indoor map images. We design and evaluate test cases across different real-world environments, analyzing the effectiveness of LLMs in interpreting spatial layouts, handling user constraints, and planning efficient routes. Our findings demonstrate the potential of LLMs for supporting personalized indoor navigation, with an average of 86.59% correct indications and a maximum of 97.14%. The proposed system achieves high accuracy and reasoning performance. These results have key implications for AI-driven navigation and assistive technologies.