Lane-Change Detection
Autonomous driving and ADAS (advanced driver-assistance systems) are proposed as a solution to decrease car crashes. Even if you drive safely, if other drivers change a lane dangerously, you cannot avoid a crash. We focus on Lane-Change Detection and propose a method to detect it automatically. We use real traffic data and construct an estimation model by using machine learning techniques.
The main contribution of this work is to propose a new feature using a potential field that changes the distribution depending on the relative number of adjacent vehicles. Previous researches have considered only some of limited situations, for example, that the preceding vehicle is slower than the target vehicle. Therefore, degradation of the detection performance can occur under conditions that were not considered. On the other hand, the new feature we propose is able to describe general lane-changing situations by applying a dynamic potential model.
Our proposed method generates the potential field that changes the drift direction depending on the relative velocity, and the relative angle with respect to adjacent vehicles as shown in the below figure.
If the preceding vehicle drives with the same velocity as the target, the potential field does not drift in any direction. However, the drifted potential field is generated toward the target when the preceding vehicle is slower than the target. Otherwise, if the preceding vehicle is faster than the target, the potential field drifting forward does not interfere with the target. By using the proposed method, it is possible to understand the surrounding traffic conditions. As the result, the performance of lane-change detection can be improved.
This work was published in the following papers.
Hanwool Woo, Yonghoon Ji, Hitoshi Kono, Yusuke Tamura, Yasuhide Kuroda, Takashi Sugano, Yasunori Yamamoto, Atsushi Yamashita and Hajime Asama: "Lane-Change Detection Based on Vehicle-Trajectory Prediction", IEEE Robotics and Automation Letters (RA-L), Vol.2, No.2, pp.1109-1116, April 2017. [doi:10.1109/LRA.2017.2660543]
Hanwool Woo, Yonghoon Ji, Hitoshi Kono, Yusuke Tamura, Yasuhide Kuroda, Takashi Sugano, Yasunori Yamamoto, Atsushi Yamashita and Hajime Asama: "Automatic Detection Method of Lane-Changing Intentions Based on Relationship with Adjacent Vehicles Using Artificial Potential Fields", International Journal of Automotive Engineering (IJAE), Vol.7, No.4, pp.127-134, November 2016. [doi:10.20485/jsaeijae.7.4_127]