Vol.35 No.2(2000.6)
Research Report

A Neural Network Based Model for Adaptive Cruise Control Use on Driver Behavior
Hiroshi Ohno

The paper describes a driver model for adaptive cruise control (ACC) based on the feedback-error learning scheme. The focus of the study is on the adaptation process of driving behavior using ACC. The developed simulation model is needed for predicting the control performance of a skilled driver using ACC. In the experiments we used a fixed-base driving simulator (DS) installed ACC. Headway time when lane-changing in a row, FFT analysis of steering angle, and lateral deviation were investigated as the driving characteristics during ACC use and manual driving. The simulated results of the lateral deviation were compared with the experimental results and showed that the performance of the ACC was better than that of manual driving.