Using LLMs to Generate Position Descriptions in Natural Language from Ultra-Wide Band Rangings Data
This paper presents LODYSEI, an ongoing project aiming at generating intelligible, intuitive and easy to memorize object position descriptions in natural language for blind people. We present preliminary results concerning the development and testing of an indoor localization system using Ultra-Wideband (UWB) technology, the evaluation of a voice recognition interface and the use of the localization information by a Large Language Model (LLM) in order to generate position descriptions in French.
Authors
- Anaëlle Hamon
- Laurence Redon
- Thierry Val (ORCID: https://orcid.org/0000-0002-5749-8570)
- Antonio Serpa (ORCID: https://orcid.org/0000-0003-2873-4543)
- Thierry Val
- Nadine Vigouroux
- Yoann Maraval
- Ramy Bteich
- Véronique Moriceau
Institutions
- Centre National de la Recherche Scientifique (FR)
- Université Toulouse III - Paul Sabatier (FR)
- Université Fédérale de Toulouse Midi-Pyrénées (FR)
- Institut National Polytechnique de Toulouse (FR)
- Université Toulouse-I-Capitole (FR)
- Institut de Recherche en Informatique de Toulouse (FR)
- Université Toulouse - Jean Jaurès (FR)
- Institut Polytechnique de Bordeaux (FR)
Publication Details
- Published
- 2025-10-12
- DOI
- https://doi.org/10.1145/3714394.3756297
- Primary Topic
- Hand Gesture Recognition Systems
- Type
- article
- Field-Weighted Citation Impact
- 0.00