Abstract
The motion status recognition of the preceding vehicle in a long-distance region is a requirement for autonomous vehicles to make appropriate decisions and increase their comprehension of the environment. At present, the lane change behavior of the leading vehicle at a short distance is detected using stereo cameras and LiDAR. However, the short detection distance (about 100 m) does not meet the requirements of high-speed driving of autonomous vehicles on expressways; this is a fundamental problem limiting the development of autonomous vehicles exhibiting human-like behavior. In this paper, a comprehensive model consisting of a back-propagation (BP) neural network model optimized by a particle swarm optimization (PSO) algorithm, and a continuous identification model is developed based on the results of naturalistic on-road experiments using millimeter-wave radar data. By considering different time-to-lane crossings (TLCs), the PSO-BP neural network model is trained using real vehicle lane change data and implemented when the TLC of the leading vehicle is longer than 1.0 s. In contrast, when the TLC is less than 1 s, the continuous recognition model of the TLC is used. By comparison with the BP neural network model, the recognition accuracy rate of the proposed model is increased from 80% to 87% after the PSO optimization for a time window of 1.0 s; these results meet the recognition requirements of the autonomous driving systems for distant targets. The findings of this paper improve the cognitive competence and safety of autonomous driving systems.
Highlights
Autonomous driving systems have developed progressively and have been demonstrated by vehicle safety organizations to improve the safety of driving and reduce traffic collisions [1]–[3]
1.8% of the lane changes of the leading vehicle were not detected by the backpropagation neural network (BPNN) model when the time window was 1.0 s
The simulation results indicated that the recognition accuracy rate of the BPNN model increased from 80% to 87% after particle swarm optimization (PSO) optimization at to-lane crossings (TLCs) longer than 1.0 s
Summary
Autonomous driving systems have developed progressively and have been demonstrated by vehicle safety organizations to improve the safety of driving and reduce traffic collisions [1]–[3]. The lane change detection of preceding vehicles within a short distance range (about 100 m) is accurately identified using stereo cameras and LIDAR [9]–[11]. The determination of the time window is a key factor in the development of detection models of the vehicle lane change status [30]. The longer the time window, the larger the amount of gathered information is and the higher the recognition rate is, but the model cannot immediately determine the motion status of the vehicle.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
