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 - 2014/9
Y1 - 2014/9
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
SP - 1016
EP - 1026
JO - SAE International Journal of Passenger Cars - Mechanical Systems
JF - SAE International Journal of Passenger Cars - Mechanical Systems
SN - 1946-3995
IS - 3
ER -