Timely and accurate identification of the driver's intention is considered helpful to avoid collisions. Driving in an on-road traffic situation makes it much more difficult to recognize the driving intention because of dynamic and uncertain information. However, the intentions can be inferred by the driver's behaviors as he prepares to execute an action. The current studies focus on classifying driving intentions into car-following and lane-changing. Therefore, a lane change intention recognition method was proposed in this study. A total of 10 on-road experiments on freeways were conducted to acquire time headway, driver's eye-motion data, steering angle and lane departure data. With these data, the typical features under free driving and lane change conditions were analyzed, respectively. The Back-Propagation Neural Networks method was applied in this study to achieve the driving intention classification function. The proposed model successfully recognized 95 intentions in 100 lane change behaviors. The recognition result of the model can fit the target output at a degree of 0.99. This model is useful for surrounding drivers to choose the safest route to avoid collisions in the vehicle-infrastructure technology.
A Recognition Model for Lane Change Intention Based on Neural Network
Second International Conference on Transportation Information and Safety ; 2013 ; Wuhan, China
ICTIS 2013 ; 125-130
2013-06-11
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
DRIVER INTENTION RECOGNITION METHOD BASED ON COMPREHENSIVE LANE-CHANGE ENVIRONMENT ASSESSMENT
British Library Conference Proceedings | 2014
|