Abstract
Lane-changing (LC) is a critical task for autonomous driving, especially in complex dynamic environments. Numerous automatic LC algorithms have been proposed. This topic, however, has not been sufficiently addressed in existing on-road manoeuvre decision methods. Therefore, this paper presents a novel LC decision (LCD) model that gives autonomous vehicles the ability to make human-like decisions. This method combines a deep autoencoder (DAE) network with the XGBoost algorithm. First, a DAE is utilized to build a robust multivariate reconstruction model using time series data from multiple sensors; then, the reconstruction error of the DAE trained with normal data is analysed for LC identification (LCI) and training data extraction. Then, to address the multi-parametric and nonlinear problem of the autonomous LC decision-making process, an XGBoost algorithm with Bayesian parameter optimization is adopted. Meanwhile, to fully train our learning model with large-scale datasets, we proposed an online training strategy that updates the model parameters with data batches. The experimental results illustrate that the DAE-based LCI model is able to accurately identify the LC behaviour of vehicles. Furthermore, with the same input features, the proposed XGBoost-based LCD model achieves better performance than other popular approaches. Moreover, a simulation experiment is performed to verify the effectiveness of the decision model.
Highlights
Autonomous driving, which is an emerging and rapidly growing field, exhibits enormous potential to improve driving safety and transportation system efficiency and is the future direction for the development of vehicles [1]–[3]
The fast development of depth sensors and machine learning methods have given a considerable boost to the self-driving research, making high-level LC decisions that conform to social norms is difficult, especially when vehicles are driving in complex dynamic environments [8], [9]
2) To address the multi-parameter and nonlinear problems in the autonomous LC decision-making process, we propose a novel LCD model based on XGBoost and apply the Bayesian optimization algorithm to identify the optimal hyperparameters of XGBoost
Summary
Autonomous driving, which is an emerging and rapidly growing field, exhibits enormous potential to improve driving safety and transportation system efficiency and is the future direction for the development of vehicles [1]–[3]. This study seeks to establish a novel LCD model for AVs by introducing deep learning and machine learning methods, improving the existing research and addressing the existing problems in LC behaviour identification and LC decision making for AVs. The main contributions of our work are summarized as follows: 1) We introduce the deep autoencoder (DAE) network to capture nonlinear correlations in the multivariate sensor data while providing a robust signal reconstruction. Based on the above analysis of the road structure in straight and curved sections, the distances dL and dR between the ego vehicle and the left and right lanes, respectively, vehicle speed vx , acceleration ax , lateral velocity vy, lateral acceleration ay, yaw angular velocity ω, and yaw angle φ are utilized as the input features in the prediction model to identify the vehicle driving behaviours, determine the start and end time points of an LC and extract the decision-making data. When the reconstruction error exceeds the alarm threshold, the vehicle begins to enter the LC state from the stable LK state, and this point is the boundary that divides the following two states: LK and LC
Sign-in/Register to view highlights & summary 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.
