A Spatial-Temporal Graph Neural Network-Based Human-Like Lane Changing Decision Model for the Autonomous Vehicle

Lane changing decision (LCD) is an essential procedure for the operation of an autonomous vehicle (AV). The modeling of LCD is more complex and has more challenges compared with the modeling of car-following behaviors, because it needs to consider more about the interactions among the target lane-changing vehicle and its surrounding traffic environment. It would be a potential and effective solution for an AV to make the LCD by mimicking the LCD behavior of a human driver. Therefore, this study proposed a spatial-temporal graph neural network (STGNN)-based LCD model for AVs, which learns the LCD from the naturalistic driving data. Specifically, a graph structure describing the relationship between the target lane-changing vehicle and those nearby vehicles was constructed. And then, the graph structured data were generated from the trajectory data which were from a naturalistic driving dataset named “Ubiquitous Traffic Eyes”. Those preprocessed and transformed data would feed into the STGNN model. Furtherly, the STGNN-based LCD model was built up based on the Recurrent Neural Network, which integrated the Graph Attention Networks (GAT) and the Gate Recurrent Unit (GRU). GAT was used to capture the spatial features, while GRU was responsible for the temporal features. And thus, the proposed model enhances spatial-temporal feature capture in LCD. Using the field data, the proposed STGNN-based LCD model was trained, tested, validated, and compared. And it achieves 86.5% accuracy in the validation, surpassing the LSTM-based model. To some extent, it indicated that the proposed model provides an alternative way for the AV to imitate the human drivers' lane-changing decision correctly.

I. Introduction

Humans in the driving tasks are getting assistance or replacement with the application and development of Autonomous Vehicle (A V) techniques. Integrated with the connectivity, AVs are upgraded to the Connected and Autonomous Vehicles (CAVs) capable of communicating with the surrounding vehicles and infrastructures. Driving decision is one of the critical driving tasks. There are three levels of driving decisions including operational level (e.g., brake, pedal), tactical level (e.g., lane-keeping, lane-changing), and strategic level (e.g., routing) [1]. In the tactical level, the lateral control decision (lane-changing) is much more complex than the longitudinal control decision (car-following or lane-keeping) [2]. Because a lane-changing decision (LCD) needs to consider not only the willingness of driver/system but also the impact from multiple surrounding objects. Besides, to conduct a good lane change decision, it has to achieve both macroscopic level benefits (including traffic safety, traffic efficiency, etc. [3]) and the microscopic level benefits (including minimizing speed fluctuation, increasing the ride comfort, etc. [4]). It adds challenges to the modeling of the LCD for an AV.