This paper proposes a vehicle-parking trajectory planning method that addresses the issues of a long trajectory planning time and difficult training convergence during automatic parking. The process involves two stages: finding a parking space and parking planning. The first stage uses model predictive control (MPC) for trajectory tracking from the initial position of the vehicle to the starting point of the parking operation. The second stage employs the proximal policy optimization (PPO) algorithm to transform the parking behavior into a reinforcement learning process. A four-dimensional reward function is set to evaluate the strategy based on a formal reward, guiding the adjustment of neural network parameters and reducing the exploration of invalid actions. Finally, a simulation environment is built for the parking scene, and a network framework is designed. The proposed method is compared with the deep deterministic policy gradient and double-delay deep deterministic policy gradient algorithms in the same scene. Results confirm that the MPC controller accurately performs trajectory-tracking control with minimal steering wheel angle changes and smooth, continuous movement. The PPO-based reinforcement learning method achieves shorter learning times, totaling only 30% and 37.5% of the deep deterministic policy gradient (DDPG) and twin-delayed deep deterministic policy gradient (TD3), and the number of iterations to reach convergence for the PPO algorithm with the introduction of the four-dimensional evaluation metrics is 75% and 68% shorter compared to the DDPG and TD3 algorithms, respectively. This study demonstrates the effectiveness of the proposed method in addressing a slow convergence and long training times in parking trajectory planning, improving parking timeliness.
Considering the perception of a driver, driving safety, and riding comfort, an adaptive cruise control (ACC) method based on a multi-objective (MO) real-time optimization control algorithm is proposed. The ACC system can be divided into various working modes according to the driver’s perception, as well as the relative state of the host vehicle and the preceding vehicle. To distinguish the driver’s intention in the rapid acceleration, strong deceleration, steady, and larger clearance modes, a fuzzy tool is proposed to solve the problem. To maintain the inter-clearance, velocity, and jerking action in a reasonable region, an MO control algorithm based on model predictive control was used to obtain the optimal control vectors. Moreover, the control vector increment is restricted to suppressing the fluctuation caused by switching among various modes. Simulations were conducted for various scenarios to verify the effectiveness of the ACC method. The simulation results indicated that the driver’s comfort and fuel economy improved by 35.3% and 16.6%, respectively, compared with the linear quadratic algorithm in a complicated driving environment. Various simulation results demonstrated that the MO-ACC controller can reduce fuel consumption while barely sacrificing riding comfort or tracking performance, as compared to the linear quadratic controller.
Multitarget tracking based on multisensor fusion perception is one of the key technologies to realize the intelligent driving of automobiles and has become a research hotspot in the field of intelligent driving. However, most current autonomous-vehicle target-tracking methods based on the fusion of millimeter-wave radar and lidar information struggle to guarantee accuracy and reliability in the measured data, and cannot effectively solve the multitarget-tracking problem in complex scenes. In view of this, based on the distributed multisensor multitarget tracking (DMMT) system, this paper proposes a multitarget-tracking method for autonomous vehicles that comprehensively considers key technologies such as target tracking, sensor registration, track association, and data fusion based on millimeter-wave radar and lidar. First, a single-sensor multitarget-tracking method suitable for millimeter-wave radar and lidar is proposed to form the respective target tracks; second, the Kalman filter temporal registration method and the residual bias estimation spatial registration method are used to realize the temporal and spatial registration of millimeter-wave radar and lidar data; third, use the sequential m-best method based on the new target density to find the track the correlation of different sensors; and finally, the IF heterogeneous sensor fusion algorithm is used to optimally combine the track information provided by millimeter-wave radar and lidar, and finally form a stable and high-precision global track. In order to verify the proposed method, a multitarget-tracking simulation verification in a high-speed scene is carried out. The results show that the multitarget-tracking method proposed in this paper can realize the track tracking of multiple target vehicles in high-speed driving scenarios. Compared with a single-radar tracker, the position, velocity, size, and direction estimation errors of the track fusion tracker are reduced by 85.5%, 64.6%, 75.3%, and 9.5% respectively, and the average value of GOSPA indicators is reduced by 19.8%; more accurate target state information can be obtained than a single-radar tracker.
In order to meet the personalized needs of Chinese intelligent vehicles and improve the satisfaction and acceptance of human–computer interaction and collaboration in domestic intelligent vehicles. In this paper, we design an adaptive longitudinal following model that integrates the perceptual perturbation process and driver characteristics for simulating driver following behavior and studying the variability of driver following behavior. Firstly, for the independence and randomness of driver perception process, a set of random variables conforming to Wiener process is introduced to simulate the perception process of speed and following distance of the vehicle in front; secondly, for the characteristic differences of different drivers' following behavior, a driver characteristic parameter identification algorithm is designed to identify the expected collision time distance and following distance parameters of different drivers, and the identified parameters will be used for Again, a sliding mode control system based on fuzzy switching gain adjustment is designed to simulate the driver following control system. The results show that the designed following model recognizes the driver's characteristics well and can better simulate the driver's following behavior, and the following index is relatively improved by 80%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.