Journal
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
Volume 10, Issue 12, Pages 3363-3369Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s13042-019-00923-8
Keywords
Lane-changing opportunity; K-ELM algorithm; Mandatory lane changing; Feature selection; Highway merging area
Categories
Funding
- National Natural Science Foundation of China [61573075, 2016ZXFB06002]
Ask authors/readers for more resources
Lane change maneuver on the highway is a complicated process. A quick and accurate decision for the maneuver is very important for a safe driving. This paper proposes a K-ELM (kernel extreme learning machine) based decision making method for mandatory lane changes. In this method, multiple driving variables that are essential for an accurate lane change are extracted and used as the inputs of an established K-ELM network to generate the right lane-changing decision. The K-ELM network is trained using a tenfold cross-validating approach with the vehicle trajectory data from the NGSIM (next generation simulation) data set on U.S. Highway 101 and Interstate 80. Simulation results demonstrate that the proposed method can generate the lane-changing decision with a 92.86% accuracy for merge events and a 94.36% accuracy for non-merge events. Compared with both the ELM and the SVM method, the proposed method is more accurate and faster in decision making.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available