Anticipating Driver Actions via Deep Neural Networks and New Driver Personalization Technique through Transfer Learning

Sahim Kourkouss, Hideto Motomura, Koichi Emura, Eriko Ohdachi

2018

Abstract

Anticipating driving behaviours is a promising technology for novel advanced driver assistance systems. In recent years, predicting a driver’s future action became an important element to preventive safety technologies and has been advancing greatly contributing to a reduction in road accidents. In this paper, we propose a deep learning network that anticipates driving actions based on information of subject vehicle as well as surrounding vehicles and environment. By re-using a network trained on a great number of various drivers’ data with different driving behaviours and linking it to a particular driver with particular taste we propose a method that enables the anticipation of driving behaviours that can be tailored to each driver individually, leading to improved user experiences. We experimentally test our method for acceleration, deceleration and brake profile anticipation task using actual driving data. Our results demonstrate the effectiveness of our approach, achieving a great improvement when anticipating for individuals.

Paper Citation

in Harvard Style

Kourkouss S., Motomura H., Emura K. and Ohdachi E. (2018). Anticipating Driver Actions via Deep Neural Networks and New Driver Personalization Technique through Transfer Learning.In Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS, ISBN 978-989-758-293-6, pages 269-276. DOI: 10.5220/0006669002690276

in Bibtex Style

@conference{vehits18,
author={Sahim Kourkouss and Hideto Motomura and Koichi Emura and Eriko Ohdachi},
title={Anticipating Driver Actions via Deep Neural Networks and New Driver Personalization Technique through Transfer Learning},
booktitle={Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,},
year={2018},
pages={269-276},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006669002690276},
isbn={978-989-758-293-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,
TI - Anticipating Driver Actions via Deep Neural Networks and New Driver Personalization Technique through Transfer Learning
SN - 978-989-758-293-6
AU - Kourkouss S.
AU - Motomura H.
AU - Emura K.
AU - Ohdachi E.
PY - 2018
SP - 269
EP - 276
DO - 10.5220/0006669002690276