Multi-parameter prediction of drivers' lane-changing behaviour with neural network model

• Published in: Applied ergonomics Vol. 50; pp. 207 - 217
• Main Authors: Peng, Jinshuan, Guo, Yingshi, Fu, Rui, Yuan, Wei, Wang, Chang
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.09.2015; Elsevier Science Ltd
• Subjects: Adult; Automobile driving; Automobile Driving - psychology; Automobile Driving - statistics & numerical data; Ergonomics; Eye Movements; Female; Head Movements; Human factors research; Humans; Lane change prediction; Male; Middle Aged; Motion; Naturalistic driving experiment; Neural network model; Neural networks; Neural Networks (Computer); Predictions; Safety systems; Time Factors; Traffic accidents & safety; Transportation research; Neural network model; Naturalistic driving experiment; Lane change prediction
• ISSN: 0003-6870; 1872-9126
• DOI: 10.1016/j.apergo.2015.03.017

Accurate prediction of driving behaviour is essential for an active safety system to ensure driver safety. A model for predicting lane-changing behaviour is developed from the results of naturalistic on-road experiment for use in a lane-changing assistance system. Lane changing intent time window is determined via visual characteristics extraction of rearview mirrors. A prediction index system for left lane changes was constructed by considering drivers' visual search behaviours, vehicle operation behaviours, vehicle motion states, and driving conditions. A back-propagation neural network model was developed to predict lane-changing behaviour. The lane-change-intent time window is approximately 5 s long, depending on the subjects. The proposed model can accurately predict drivers' lane changing behaviour for at least 1.5 s in advance. The accuracy and time series characteristics of the model are superior to the use of turn signals in predicting lane-changing behaviour. •We conducted a lane change experiment under real road environment.•Lane changing intent time window is about 5 s.•Vehicle motion states, driving conditions and head movements information were chosen to predict lane changing behaviours.•The improved neural network detects 85% of lane changes 1.5 s in advance.