In this paper, a gated recurrent unit–deep neural network (GRU-DNN) model integrated with multimodal feature embedding (MFE) is developed to evaluate the real-time risk of hazmat road transportation based on various types of data for contributing factors. MFE was incorporated into the framework of a deep learning model in which discrete variables, continuous variables, and images were uniformly embedded. GRU is a pre-trained sub-model, and the DNN is able to directly use the relative structure and weights of the GRU, improving the poor classification and recognition results due to insufficient samples. Additionally, the model is trained and validated based on hazmat road transportation database consisting of 2100 samples with 20 real-time contributing factors and four risk levels in China. The accuracy (ACC), precision (PR), recall (RE), F1-score (F1), and areas under receiver-operating-characteristic curves (AUC) of the proposed model and other commonly used models are compared as performance measurements in numerical examples. Finally, Carlini & Wagner attack and three defenses of adversarial training, dimensionality reduction and prediction similarity are proposed in the training to improve the robustness of the model, alleviating the impact of noise and error on small-sized samples. The results demonstrate that the average ACC of the model reaches 93.51% and 87.6% on the training and validation sets, respectively. The prediction of accidents resulting in injury is the most accurate, followed by fatal accidents. Combined with the RE of 89.0%, the model exhibits excellent performance. In addition, the proposed model outperforms other widely used models based on the overall comparisons of ACC, AUC, F1 and PR-RE curve. Finally, prediction similarity can be used as an effective approach for robustness improvement, with the launched adversarial attacks being detected at a high success rate.

To make driving assistance system more humanized, this study focused on the prediction and assistance of drivers’ perception-response time on mountain highway curves. Field tests were conducted to collect real-time driving data and driver vision information. A driver-vision lane model quantified curve elements in drivers’ vision. A multinomial log-linear model was established to predict perception-response time with traffic/road environment information, driver-vision lane model, and mechanical status (last second). A corresponding assistance model showed a positive impact on drivers’ perception-response times on mountain highway curves. Model results revealed that the driver-vision lane model and visual elements did have important influence on drivers’ perception-response time. Compared with roadside passive road safety infrastructure, proper visual geometry design, timely visual guidance, and visual information integrality of a curve are significant factors for drivers’ perception-response time.

The multitarget vehicle tracking and motion state estimation are crucial for controlling the host vehicle accurately and preventing collisions. However, current multitarget tracking methods are inconvenient to deal with multivehicle issues due to the dynamically complex driving environment. Driving environment perception systems, as an indispensable component of intelligent vehicles, have the potential to solve this problem from the perspective of image processing. Thus, this study proposes a novel driving environment perception system of intelligent vehicles by using deep learning methods to track multitarget vehicles and estimate their motion states. Firstly, a panoramic segmentation neural network that supports end-to-end training is designed and implemented, which is composed of semantic segmentation and instance segmentation. A depth calculation model of the driving environment is established by adding a depth estimation branch to the feature extraction and fusion module of the panoramic segmentation network. These deep neural networks are trained and tested in the Mapillary Vistas Dataset and the Cityscapes Dataset, and the results showed that these methods performed well with high recognition accuracy. Then, Kalman filtering and Hungarian algorithm are used for the multitarget vehicle tracking and motion state estimation. The effectiveness of this method is tested by a simulation experiment, and results showed that the relative relation (i.e., relative speed and distance) between multiple vehicles can be estimated accurately. The findings of this study can contribute to the development of intelligent vehicles to alert drivers to possible danger, assist drivers’ decision-making, and improve traffic safety.

Nowadays, conditional automated driving vehicles still need drivers to take-over in the scenarios such as emergency hazard events or driving environments beyond the system’s control. This study aimed to explore the changing trend of the drivers’ takeover behavior under the influence of traffic density and take-over budget time for the entire take-over process in emergency obstacle avoidance scenarios. In the driving simulator, a 2 × 2 factorial design was adopted, including two traffic densities (high density and low density) and two kinds of take-over budget time (3 s and 5 s). A total of 40 drivers were recruited, and each driver was required to complete four simulation experiments. The driver’s take-over process was divided into three phases, including the reaction phase, control phase, and recovery phase. Time parameters, dynamics parameters, and operation parameters were collected for each take-over phase in different obstacle avoidance scenarios. This study analyzed the variability of traffic density and take-over budget time with take-over time, lateral behavior, and longitudinal behavior. The results showed that in the reaction phase, the driver’s reaction time became shorter as the scenario urgency increased. In the control phase, the steering wheel reversal rate, lateral deviation rate, braking rate, average speed, and takeover time were significantly different at different urgency levels. In the recovery phase, the average speed, accelerating rate, and take-over time differed significantly at different urgency levels. For the entire take-over process, the entire take-over time increased with the increase in urgency. The lateral take-over behavior tended to be aggressive first and then became defensive, and the longitudinal take-over behavior was defensive with the increase in urgency. The findings will provide theoretical and methodological support for the improvement of take-over behavior assistance in emergency take-over scenarios. It will also be helpful to optimize the human-machine interaction system.

Because road infrastructures have significant impact on driving safety, their risk levels need to be evaluated dynamically according to drivers’ perception. To achieve this, this paper proposes two field strength models to quantify the impact of road infrastructures on drivers. First, road infrastructures are classified into two types (continuous and discrete). Then, two field strength models for these types are proposed. Continuous field strength model describes the impact of long-belt-shape infrastructure by differential and integral methods. Discrete field strength model describes the static and dynamic characteristics of infrastructures. This model includes four parameters: mass of vehicles, mass of infrastructures, warning level, and kinetic energy of road infrastructures. The field strength is a relative concept, which changes with vehicle state. At the end of this paper, risk assessment principles are listed to clarify the nature of road infrastructure risk evaluation. A workflow of risk assessment and a case study are presented to illustrate the application of this novel method. The result of this study shows that ① the field strength is positively related to its risk level; ② the distribution of road infrastructure risks explains driver behaviour correctly; ③ drivers tend to keep driving in low-risk area. These findings help to explain the impact mechanism of road infrastructures on drivers, which can be applied in AI-based driving assistance system in the future.