Abstract
A large number of fatalities are caused by the vehicle-pedestrian accidents. Under a potential conflict between the vehicle and jaywalking pedestrian, giving precedence to the pedestrian will be a proper decision taken by the driver to avoid collision. Field traffic data has been collected by video recording and image processing at two signalized crosswalks. Vehicle speed performance in the single vehicle-pedestrian encounter and platoon vehicle-pedestrian encounter were analyzed for understanding the driver behavior in the conflict process. Binary logit model was proposed to estimate the drivers' giving precedence influenced by the situational factors and the model was validated to predict the drivers' choices accurately. The vehicle speed, pedestrian speed, pedestrian lateral distance and the vehicle longitudinal distance to the conflict point were proved to affect the drivers' choices in platoon driving. The research results would hopefully be helpful to the design of intelligent vehicles and pedestrian protection systems by the knowledge-based decision making process.
Original language | English |
---|---|
Pages (from-to) | 1407-1414 |
Number of pages | 8 |
Journal | International Journal of Computational Intelligence Systems |
Volume | 4 |
Issue number | 6 |
DOIs | |
Publication status | Published - Dec 2011 |
Keywords
- binary logit model
- driver behavior
- jaywalking pedestrian
- knowledge-based decision making