Building a human-like car-following model that can accurately simulate drivers’ car-following behaviors is helpful to the development of driving assistance systems and autonomous driving. Recent studies have shown the advantages of applying reinforcement learning methods in car-following modeling. However, a problem has remained where it is difficult to manually determine the reward function. This paper proposes a novel car-following model based on generative adversarial imitation learning. The proposed model can learn the strategy from drivers’ demonstrations without specifying the reward. Gated recurrent units was incorporated in the actor-critic network to enable the model to use historical information. Drivers’ car-following data collected by a test vehicle equipped with a millimeter-wave radar and controller area network acquisition card was used. The participants were divided into two driving styles by K-means with time-headway and time-headway when braking used as input features. Adopting five-fold cross-validation for model evaluation, the results show that the proposed model can reproduce drivers’ car-following trajectories and driving styles more accurately than the intelligent driver model and the recurrent neural network-based model, with the lowest average spacing error (19.40%) and speed validation error (5.57%), as well as the lowest Kullback-Leibler divergences of the two indicators used for driving style clustering.

Effective driver distraction detection (DDD) can significantly improve driving safety. Inspired by the definition of driver distraction, this work aims to detect driver distraction based on the true driver’s focus of attention (TDFoA). This is accomplished based on two stages, the prediction of TDFoA and DDD based on the driver’s focus of attention (DFoA) and the TDFoA. However, this process is challenging due to the complex and dynamic traffic environment, momentary glimpses not related to the TDFoA in normal driving, the interference of noise (information unrelated to the TDFoA), the ignoring of multi-scale information from driving scenarios, and the variability of thresholds used to distinguish between driver distraction and non-distraction. To solve these problems, we design a deep 3D residual network with attention mechanism and encoder-decoder (D3DRN-AMED) based on successive frames with convolution LSTM for the prediction of TDFoA, where successive frames are used to eliminate the impact of momentary glimpses. The convolution LSTM achieves the transition of features in successive frames, considering the historical variation of driving scenarios. Attention mechanism based on soft thresholding is inserted into the D3DRN-AMED as nonlinear transformation layers to eliminate the noise-related features, and the encoder-decoder module is introduced to extract multi-scale features. A method based on a neural network is then proposed to detect driver distraction according to the difference or similarity between DFoA and TDFoA, which can accurately detect driver distraction without determining the threshold. Experimental results show that the proposed method can effectively detect driver distraction.

Comfort is a significant factor that affects passengers’ choice of autonomous vehicles. The comfort of an autonomous vehicle is largely determined by its control algorithm. Therefore, if the comfort of passengers can be predicted based on factors that affect comfort and the control algorithm can be adjusted, it can be beneficial to improve the comfort of autonomous vehicles. In view of this, in the present study, a human-driven experiment was carried out to simulate the typical driving state of a future autonomous vehicle. In the experiment, vehicle motion parameters and the comfort evaluation results of passengers with different physiological characteristics were collected. A single-factor analysis method and binary logistic regression analysis model were used to determine the factors that affect the evaluation results of passenger comfort. A passenger comfort prediction model was established based on the bidirectional long short-term memory network model. The results demonstrate that the accuracy of the passenger comfort prediction model reached 84%, which can provide a theoretical basis for the adjustment of the control algorithm and path trajectory of autonomous vehicles.

The low user acceptability of advanced driver assistance systems (ADASs) is one of the fundamental problems limiting their wider adoption. One of the key factors affecting the frequency of warning signals is the standard warning thresholds set in ADASs, which may not be compatible with all drivers owing to various driver characteristics affecting their cognition of risk, such as comfort, skill, and experience. The present study focuses on the lane change warning (LCW) system to evaluate driving styles according to the perception of lane change risk, and determine appropriate warning thresholds corresponding to the different driving styles. A theoretical lane change warning model is established to calculate the deceleration required for the rear approaching vehicle in the target lane. The results of risk assessment experiments conducted on an actual expressway using 15 proficient drivers are employed to evaluate the risk cognitions of the participants, where the participants are divided into four different driving styles according to their adaptive warning thresholds, which are denoted as very low threshold, low threshold, medium threshold, and high threshold driving styles. Signal detection theory is then employed to determine lane change warning thresholds appropriate to the different driving styles. Our results clearly demonstrate the disparate perceptions of lane change risk for the different drivers. Therefore, the LCW system should adopt different warning thresholds for different drivers according to their driving style. The findings provide evidence supporting the exploitation of driving styles for adopting different warning thresholds in the LCW system to enhance its user acceptability.

Accurate identification of pedestrian crossing intention is of great significance to the safe and efficient driving of future fully automated vehicles in the city. This paper focuses on pedestrian intention recognition on the basis of pedestrian detection and tracking. A large number of natural crossing sequence data of pedestrians and vehicles are first collected by a laser scanner and HD camera, then 1980 effective crossing samples of pedestrians are selected. Influencing parameter sets of pedestrian crossing intention are then obtained through statistical analysis. Finally, long short-term memory network with attention mechanism (AT-LSTM) model is proposed. Compared with the support vector machine (SVM) model, results show that when the pedestrian crossing intention is recognized 0 s prior to crossing, the recognition accuracy of the AT-LSTM model for pedestrian crossing intention is 96.15%, which is 6.07% higher than that of SVM model; when the pedestrian crossing intention is recognized 0.6 s prior, the recognition accuracy of AT-LSTM model is 90.68%, which is 4.85% higher than that of the SVM model. The determination of pedestrian crossing intention parameter set and the more accurate recognition of pedestrian intention provided in this work provide a foundation for future fully automated driving vehicles.