To solve the problem that the path tracking controller has a large tracking error under different road adhesion coefficients and vehicle speeds based on traditional Model Predictive Control (MPC), this paper proposed a path tracking control strategy for autonomous vehicles based on Particle Swarm Optimization (PSO)-BP neural network optimization MPC. Firstly, a path tracking controller based on MPC was designed; Secondly, PSO-BP was used to optimize MPC, and the controller accuracy and vehicle stability were taken as evaluation functions to obtain the offline optimal time domain parameters of PSO. Finally four conditions were selected for comparison and simulation verification of double shift lane tracking. The results show that the lateral control accuracy of double shift lane tracking under the 4 conditions, including low adhesion at low speed, high adhesion at low speed, high adhesion at high speed and medium adhesion at medium speed, is improved by 50%, 55%, 9% and 20% respectively.

In order to improve the accuracy and robustness of intelligent vehicle path tracking, a robust feedback path tracking controller was designed based on Lyapunov Stability Theory. By using Schur complement lemma and solving Linear Matrix Inequality (LMI), the feedback matrix of the control system was obtained. By building a CarSim/Simulink joint simulation platform, the robust feedback controller was compared with the Linear Quadratic Regulator (LQR). The performance of the designed controller was verified by simulation tests on the roads with different adhesion coefficients at different speeds. The simulation results show that, compared with LQR controller, the robust feedback controller based on Lyapunov stability theory not only has higher control accuracy, but also has stronger robustness when the vehicle is running on different roads at different speeds.

For the active obstacle avoidance of vehicle under different road conditions, this paper proposed an obstacle avoidance path planning method in driving risk field considering road adhesion coefficient. Firstly, the driving risk fields including road boundary risk field, target gravitational field and obstacle risk field were established. The road adhesion coefficient was estimated in real time based on the volumetric Kalman filter algorithm, and the driving risk field function considering the road adhesion coefficient was derived with negative gradient derivative, and the obstacle avoidance path with the lowest risk was obtained. Then, the obstacle avoidance reference path satisfying the vehicle constraints was obtained by 5-degree polynomial fitting optimization. Finally, the model predictive control algorithm was utilized to track the obstacle avoidance path. The simulation results show that at the same speed, the smaller the road adhesion coefficient, the smaller the lateral acceleration is, the smaller the standard deviation of the lateral acceleration is, and the more stable the obstacle avoidance effect will be.

This paper elaborated the overall framework of commercial vehicle fatigue early warning system, and analyzed in details the research status of monitoring system, human machine interface and fatigue detection method. The paper pointed out that the future monitoring system should have the ability of high stability, short delay and massive data processing, and divided the warning into two levels, and defined the effective human-computer interaction respectively. The paper then analyzed 4 categories of fatigue detection methods, and indicated that the fatigue detection method based on multi-feature information fusion will be the main research direction in the future. The paper finally revealed the difficulties of the current research, and prospected research of the commercial vehicle fatigue warning system from 3 aspects, i.e. obtaining more driver information, extracting more fatigue features, and reducing the dependence on specific fatigue features.

In order to improve the low lane departure warning rate due to the poor robustness of the traditional edge operator in lane feature extraction and the weak fitting ability of the traditional Hough transform curve, this paper proposed a lane departure warning method based on the threshold segmentation of the optimized maximum inter-class variance method (OTSU algorithm) and the sliding window method. Firstly, the genetic annealing algorithm was used to optimize and solve the optimal threshold of OTSU algorithm, and the Holistically-nested Edge Detection (HED) model was invoked to obtain the edge features of lane lines, and the area of interest was converted into an aerial view. Then, the sliding window method was utilized to slice the lane lines and the second-order polynomial fitting was carried out for the lane pixels in the window one by one. Finally, the lane departure warning and curve warning were given according to the relative position of the vehicle and the lane line. The test results show that the accuracy of the proposed method is 95.92%, and the detection rate can reach 34 ms/frame.

In order to improve the intelligent level of evidence collection and responsibility determination of traffic accidents, this article proposed a vehicle information management and accident forensics system based on blockchain and consensus mechanism. Vehicle information was managed in a permissioned blockchain framework, and the communication between the Electronic Control Unit (ECU) of the vehicle and the Road Side Unit (RSU) was used to ensure the legitimacy and integrity of vehicle data. In the proposed traffic accident digital forensics scheme, the data from involved vehicles was automatically managed by the RSU, and a consensus on data reliability was achieved through the practical Byzantine Fault Tolerance (pBFT) protocol. The experimental results show that the proposed blockchain scheme is able to meet the real-time requirements of transportation applications, and the block generation delay and Q-A verification delay in the experimental scenario do not exceed 18.13 ms and 1.55 ms, respectively. The qualitative results show that the proposed framework is able to resist known security attacks, ensure data reliability, and can help law enforcement achieve fair traffic accident liability determination.

For the situation that the current automatic parking system requires a high number of sensors and computing power, this paper proposed an automatic parking system based on panoramic images and human-machine interaction. Quantitative perception training was performed on the improved Vacant Parking Slot Network (VPS-Net) to realize real-time parking slot detection and parking slot occupancy classification. At the same time, with the help of the driver’s judgment on the surrounding environment, only 4 surround-view fisheye cameras around the car body were used to complete unoccupied parking slot detection and real-time monitoring of the parking environment, and multi-stage path planning and path-following controller were utilized to realize smooth and accurate parking of the vehicle into the parking slot. The verification results show that the system can realize automatic parking under various typical parking slots and lighting conditions.

This paper proposed a path planning method with low computing power requirement and small parking space for path planning of vertical parking space. First, the one-step and multi-step base path planning for vertical parking were designed based on the linear-arc combination considering the requirements of collision constraints and vehicle kinematic constraints in the parking process. Then, the curvature optimization was combined with the clothoid curve to realize the curvature smoothing of the parking path. Finally, the feasibility of the method was verified by simulation. The results show that the method can plan a safe and smooth parking path for different lateral parking spaces and different initial attitude angles.

For the situation that the hybrid A* algorithm is difficult to accelerate the search using collision-free Reeds-Shepp (RS) curves due to the complex environment near the destination in short distance parking scenarios, this paper proposed an improved hybrid A* algorithm that reversely searched the path from the target posture, combined with the cost map look up calculated by A* algorithm to obtain heuristic values. Collision detection was performed by judging whether the car body contour line intersecting with the simplified obstacle to save search time, and by setting suitable vehicle steering angle resolution to increase number of the node expansion direction to ensure the smoothness of the path. Finally, MATLAB was used to simulate and compare the improved algorithm with the original algorithm. The results showed the improved hybrid A * algorithm effectively shortened the path search time both in parallel and vertical parking scenario, resulting in shorter and smoother paths.

To provide the typical hazardous distracted driving scenarios for the development and testing of vehicle active safety systems, this research relied upon an in-depth investigation of 375 distracted driving accidents, determined parameters of the scenarios across three dimensions including road environment, participant’s speed, and motion state, compared and analyzed national statistics with samples from each accident type and extracted key feature parameters. Using the two-step cluster analysis method, this research obtained typical distracted driving scenarios of 11 different accident types associated with distracted driving, these scenarios were further refined to derive 4 core test scenarios by integrating key feature parameters.