A Study on Modeling of Driver's Braking Action to Avoid Rear-End Collision with Time Delay Neural Network

Toshiya Hirose, Masato Gokan, Nobuyo Kasuga, Toichi Sawada

研究成果: Article

8 引用 (Scopus)

抄録

Collision avoidance systems for rear-end collisions have been researched and developed. It is necessary to activate collision warnings and automatic braking systems with appropriate timing determined by a monitoring system of a driver's braking action. Although there are various systems to monitor driving behavior, this study aims to create a monitoring system using a driver model. This study was intended to construct a model of a driver's braking action with the Time Delay Neural Network (TDNN). An experimental scenario focuses on rear-end collisions on a highway, such as the driver of a host vehicle controlling the brake to avoid a collision into a leading vehicle in a stationary condition caused by a traffic jam. In order to examine the accuracy of the TDNN model, this study used four parameters: the number of learning, the number of neurons in the hidden layer, the sampling time with 0.01 second as a minimum value, and the number of the delay time. In addition, this study made a comparative review of the TDNN model and the Neural Network (NN) model to examine the accuracy of the TDNN model. It was found that (1) TDNN allows for establishing a model with higher repeatability of a driver's driving action, (2) when comparing with NN, the accuracy of the model was improved for TDNN, and (3) even if a driver repeatedly presses the brake pedal in a short time, TDNN can accurately simulate a complex braking action by a driver.

元の言語English
ジャーナルSAE International Journal of Passenger Cars - Mechanical Systems
7
発行部数3
DOI
出版物ステータスPublished - 2014

Fingerprint

Braking
Time delay
Neural networks
Brakes
Monitoring
Collision avoidance
Neurons
Sampling

ASJC Scopus subject areas

  • Automotive Engineering
  • Mechanical Engineering
  • Safety, Risk, Reliability and Quality
  • Modelling and Simulation

これを引用

@article{c5ba375842e643fdac9a1329da9dd469,
title = "A Study on Modeling of Driver's Braking Action to Avoid Rear-End Collision with Time Delay Neural Network",
abstract = "Collision avoidance systems for rear-end collisions have been researched and developed. It is necessary to activate collision warnings and automatic braking systems with appropriate timing determined by a monitoring system of a driver's braking action. Although there are various systems to monitor driving behavior, this study aims to create a monitoring system using a driver model. This study was intended to construct a model of a driver's braking action with the Time Delay Neural Network (TDNN). An experimental scenario focuses on rear-end collisions on a highway, such as the driver of a host vehicle controlling the brake to avoid a collision into a leading vehicle in a stationary condition caused by a traffic jam. In order to examine the accuracy of the TDNN model, this study used four parameters: the number of learning, the number of neurons in the hidden layer, the sampling time with 0.01 second as a minimum value, and the number of the delay time. In addition, this study made a comparative review of the TDNN model and the Neural Network (NN) model to examine the accuracy of the TDNN model. It was found that (1) TDNN allows for establishing a model with higher repeatability of a driver's driving action, (2) when comparing with NN, the accuracy of the model was improved for TDNN, and (3) even if a driver repeatedly presses the brake pedal in a short time, TDNN can accurately simulate a complex braking action by a driver.",
author = "Toshiya Hirose and Masato Gokan and Nobuyo Kasuga and Toichi Sawada",
year = "2014",
doi = "10.4271/2014-01-0201",
language = "English",
volume = "7",
journal = "SAE International Journal of Passenger Cars - Mechanical Systems",
issn = "1946-3995",
publisher = "SAE International",
number = "3",

}

TY - JOUR

T1 - A Study on Modeling of Driver's Braking Action to Avoid Rear-End Collision with Time Delay Neural Network

AU - Hirose, Toshiya

AU - Gokan, Masato

AU - Kasuga, Nobuyo

AU - Sawada, Toichi

PY - 2014

Y1 - 2014

N2 - Collision avoidance systems for rear-end collisions have been researched and developed. It is necessary to activate collision warnings and automatic braking systems with appropriate timing determined by a monitoring system of a driver's braking action. Although there are various systems to monitor driving behavior, this study aims to create a monitoring system using a driver model. This study was intended to construct a model of a driver's braking action with the Time Delay Neural Network (TDNN). An experimental scenario focuses on rear-end collisions on a highway, such as the driver of a host vehicle controlling the brake to avoid a collision into a leading vehicle in a stationary condition caused by a traffic jam. In order to examine the accuracy of the TDNN model, this study used four parameters: the number of learning, the number of neurons in the hidden layer, the sampling time with 0.01 second as a minimum value, and the number of the delay time. In addition, this study made a comparative review of the TDNN model and the Neural Network (NN) model to examine the accuracy of the TDNN model. It was found that (1) TDNN allows for establishing a model with higher repeatability of a driver's driving action, (2) when comparing with NN, the accuracy of the model was improved for TDNN, and (3) even if a driver repeatedly presses the brake pedal in a short time, TDNN can accurately simulate a complex braking action by a driver.

AB - Collision avoidance systems for rear-end collisions have been researched and developed. It is necessary to activate collision warnings and automatic braking systems with appropriate timing determined by a monitoring system of a driver's braking action. Although there are various systems to monitor driving behavior, this study aims to create a monitoring system using a driver model. This study was intended to construct a model of a driver's braking action with the Time Delay Neural Network (TDNN). An experimental scenario focuses on rear-end collisions on a highway, such as the driver of a host vehicle controlling the brake to avoid a collision into a leading vehicle in a stationary condition caused by a traffic jam. In order to examine the accuracy of the TDNN model, this study used four parameters: the number of learning, the number of neurons in the hidden layer, the sampling time with 0.01 second as a minimum value, and the number of the delay time. In addition, this study made a comparative review of the TDNN model and the Neural Network (NN) model to examine the accuracy of the TDNN model. It was found that (1) TDNN allows for establishing a model with higher repeatability of a driver's driving action, (2) when comparing with NN, the accuracy of the model was improved for TDNN, and (3) even if a driver repeatedly presses the brake pedal in a short time, TDNN can accurately simulate a complex braking action by a driver.

UR - http://www.scopus.com/inward/record.url?scp=84903390306&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903390306&partnerID=8YFLogxK

U2 - 10.4271/2014-01-0201

DO - 10.4271/2014-01-0201

M3 - Article

AN - SCOPUS:84903390306

VL - 7

JO - SAE International Journal of Passenger Cars - Mechanical Systems

JF - SAE International Journal of Passenger Cars - Mechanical Systems

SN - 1946-3995

IS - 3

ER -