A Car-Following Model Considering Missing Data Based on TransGAN Networks

Car-following behavior is closely related to the longitudinal control of the vehicle, affecting the safety of the vehicle and traffic flow stability. In order to interact with the preceding vehicle, the target vehicle usually collects the driving data of the preceding vehicle. However, data acquisition devices often face malfunctions caused by various unpredictable disruptions, resulting in missing value problems. This may cause the target vehicle to make wrong control decisions. Given this situation, a new car-following(CF) model considering missing data based on Transformer-Generative Adversarial Networks (TransGAN) is proposed. Firstly, Transformer Network with multi-head attention is used to deeply extract the potential features from incomplete vehicle state data, which can filter important information from the input and focus on these, while capturing long distance dependencies. Secondly, a Generative Adversarial Network is constructed. The Generator generates the future multi-step control states of the target vehicle based on the features extracted by Transformer Network. The Discriminator with a fully connected network is applied to simultaneously ensure the generation accuracy. Finally, our proposed model was trained and tested on a publicly available NGSIM I-80 dataset. Compared with other existing advanced works, our model can fit the actual control states of the target vehicle with higher accuracy under different data missing rates of the preceding vehicle, which demonstrates that the proposed method effectively improves the robustness of vehicle longitudinal car-following control under missing data.

I. Introduction

With the promotion of the Intelligent Connected environment, autonomous driving technology has achieved unprecedented development [1]. Compared with traditional vehicles, autonomous vehicles have a broader perception field of vision, and more advanced information processing capabilities [2], which can timely identify potential crises and make corresponding driving decisions. Moreover, autonomous vehicles can avoid most traffic accidents caused by human factors and significantly improve driving safety and traffic efficiency [3], [4]. In order to pass efficiently through complex traffic scene, autonomous vehicles need to understand the behavior of other traffic participants around them and interact with them. This enables autonomous vehicles to make reasonable and comfortable vehicle control strategies and avoid emergency response decisions [5]. In vehicle movement, the following is a common vehicle longitudinal control strategy [6]. When vehicles are lined up on a single lane, the rear vehicle follows the preceding vehicle. The optimized car-following operation not only improves the vehicle maneuverability but also mitigates traffic congestion and the risk of rear-end collisions [7]. Therefore, car-following behavior modeling is an indispensable part of automatic driving technology.