Work

Using LLMs to Generate Position Descriptions in Natural Language from Ultra-Wide Band Rangings Data

Year: 2025

Type: conference-paper

Abstract: 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.

DOI: 10.1145/3714394.3756297

Authors: Ramy Bteich, Anaëlle Hamon, Yoann Maraval, Véronique Moriceau, Antonio Serpa, Thierry Val, Adrien van den Bossche, Nadine Vigouroux, Laurence Redon

Institutions: Centre National de la Recherche Scientifique, Institut National Polytechnique de Toulouse, Institut de Recherche en Informatique de Toulouse, Université Toulouse - Jean Jaurès, Université de Toulouse

Language: English

Topic: Indoor and Outdoor Localization Technologies

Subfield: Electrical and Electronic Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: gold

OpenAlex ID: W7117453367

FWCI:

Cites: 2

Cited by:

Related to: