IDAS: Intelligent Driving Assistance System Using RAG

In the fast-growing automotive technology sector, it has become increasingly clear that there is a need for cars with smarter and more interactive systems. This article presents the Intelligent Driving Assistance System (IDAS), an artificial intelligence system that enables the driver to use voice c...

Full description

Saved in:
Bibliographic Details
Main Authors: Hernandez-Salinas Bernardo, Juan Terven, E. A. Chavez-Urbiola, Diana-Margarita Cordova-Esparza, Julio-Alejandro Romero-Gonzalez, Amadeo Arguelles, Ilse Cervantes
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Open Journal of Vehicular Technology
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10643289/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832582303556042752
author Hernandez-Salinas Bernardo
Juan Terven
E. A. Chavez-Urbiola
Diana-Margarita Cordova-Esparza
Julio-Alejandro Romero-Gonzalez
Amadeo Arguelles
Ilse Cervantes
author_facet Hernandez-Salinas Bernardo
Juan Terven
E. A. Chavez-Urbiola
Diana-Margarita Cordova-Esparza
Julio-Alejandro Romero-Gonzalez
Amadeo Arguelles
Ilse Cervantes
author_sort Hernandez-Salinas Bernardo
collection DOAJ
description In the fast-growing automotive technology sector, it has become increasingly clear that there is a need for cars with smarter and more interactive systems. This article presents the Intelligent Driving Assistance System (IDAS), an artificial intelligence system that enables the driver to use voice commands to access various features of a car. The primary component of IDAS is a Large Language Model (LLM), which, through retrieval augmented generation (RAG), can efficiently read and understand the car manual for immediate context-based aid. In addition, this system incorporates speech recognition and speech synthesis capabilities, it can understand commands given in multiple languages, improving user experiences among diverse driver communities. Our results show a minimum response time of one second for the pipeline using GPT-4o-mini and Mistral Nemo.
format Article
id doaj-art-5f1132325fe240da8c92948912e83938
institution Kabale University
issn 2644-1330
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of Vehicular Technology
spelling doaj-art-5f1132325fe240da8c92948912e839382025-01-30T00:04:09ZengIEEEIEEE Open Journal of Vehicular Technology2644-13302024-01-0151139116510.1109/OJVT.2024.344744910643289IDAS: Intelligent Driving Assistance System Using RAGHernandez-Salinas Bernardo0Juan Terven1https://orcid.org/0000-0001-6662-0390E. A. Chavez-Urbiola2https://orcid.org/0000-0002-1938-8610Diana-Margarita Cordova-Esparza3https://orcid.org/0000-0002-5657-7752Julio-Alejandro Romero-Gonzalez4https://orcid.org/0000-0001-7257-7595Amadeo Arguelles5Ilse Cervantes6https://orcid.org/0000-0003-3478-9241Instituto Politecnico Nacional, CICATA, Querétaro, MexicoInstituto Politecnico Nacional, CICATA, Querétaro, MexicoInstituto Politecnico Nacional, CICATA, Querétaro, MexicoFacultad de Informatica, Universidad Autónoma de Queretaro, Queretaro, MexicoFacultad de Informatica, Universidad Autónoma de Queretaro, Queretaro, MexicoInstituto Politecnico Nacional, Centro de Investigacion en Computacion, Mexico City, MexicoInstituto Politecnico Nacional, CICATA, Querétaro, MexicoIn the fast-growing automotive technology sector, it has become increasingly clear that there is a need for cars with smarter and more interactive systems. This article presents the Intelligent Driving Assistance System (IDAS), an artificial intelligence system that enables the driver to use voice commands to access various features of a car. The primary component of IDAS is a Large Language Model (LLM), which, through retrieval augmented generation (RAG), can efficiently read and understand the car manual for immediate context-based aid. In addition, this system incorporates speech recognition and speech synthesis capabilities, it can understand commands given in multiple languages, improving user experiences among diverse driver communities. Our results show a minimum response time of one second for the pipeline using GPT-4o-mini and Mistral Nemo.https://ieeexplore.ieee.org/document/10643289/Artificial intelligencehuman-computer interactionintelligent agentslarge language modelsretrieval augmented generation (RAG)
spellingShingle Hernandez-Salinas Bernardo
Juan Terven
E. A. Chavez-Urbiola
Diana-Margarita Cordova-Esparza
Julio-Alejandro Romero-Gonzalez
Amadeo Arguelles
Ilse Cervantes
IDAS: Intelligent Driving Assistance System Using RAG
IEEE Open Journal of Vehicular Technology
Artificial intelligence
human-computer interaction
intelligent agents
large language models
retrieval augmented generation (RAG)
title IDAS: Intelligent Driving Assistance System Using RAG
title_full IDAS: Intelligent Driving Assistance System Using RAG
title_fullStr IDAS: Intelligent Driving Assistance System Using RAG
title_full_unstemmed IDAS: Intelligent Driving Assistance System Using RAG
title_short IDAS: Intelligent Driving Assistance System Using RAG
title_sort idas intelligent driving assistance system using rag
topic Artificial intelligence
human-computer interaction
intelligent agents
large language models
retrieval augmented generation (RAG)
url https://ieeexplore.ieee.org/document/10643289/
work_keys_str_mv AT hernandezsalinasbernardo idasintelligentdrivingassistancesystemusingrag
AT juanterven idasintelligentdrivingassistancesystemusingrag
AT eachavezurbiola idasintelligentdrivingassistancesystemusingrag
AT dianamargaritacordovaesparza idasintelligentdrivingassistancesystemusingrag
AT julioalejandroromerogonzalez idasintelligentdrivingassistancesystemusingrag
AT amadeoarguelles idasintelligentdrivingassistancesystemusingrag
AT ilsecervantes idasintelligentdrivingassistancesystemusingrag