LLM-Guided Indoor Navigation with Multimodal Map Understanding
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911014694420480 |
|---|---|
| author | Coffrini, Alberto Barsocchi, Paolo Furfari, Francesco Crivello, Antonino Ferrari, Alessio |
| author_facet | Coffrini, Alberto Barsocchi, Paolo Furfari, Francesco Crivello, Antonino Ferrari, Alessio |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11702 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM-Guided Indoor Navigation with Multimodal Map Understanding Coffrini, Alberto Barsocchi, Paolo Furfari, Francesco Crivello, Antonino Ferrari, Alessio Artificial Intelligence Computation and Language Machine Learning 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. |
| title | LLM-Guided Indoor Navigation with Multimodal Map Understanding |
| topic | Artificial Intelligence Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2503.11702 |