International Journal of Vehicle Design (6 papers in press)

Regular Issues

• Open Access

  Intelligent obstacle avoidance control method for autonomous vehicles based on improved SAC algorithm ( Free Full-text Access )

  by Yulin Ma, Yide Qian, Teng Ma, Yicheng Li, Jian Wan 
  Abstract: To improve the success rate of collision avoidance for autonomous vehicles and shorten response time, an intelligent obstacle avoidance control method based on an improved SAC algorithm is proposed. This method is based on a self-organizing cluster model, integrating short-range repulsion, medium-range velocity calibration, and obstacle avoidance rules to achieve collision-free cluster collaboration. The conventional SAC algorithm adopts the AC framework to maximize the expected reward and entropy value while reducing the estimation bias of the value function through the value network component. On this basis, the PER-SAC method is proposed, which integrates priority experience replay and importance sampling weight strategy while optimizing network structure, reward and punishment functions, continuous state and action space design. Additionally, transfer learning is incorporated. The experimental results demonstrate the effectiveness of this method, achieving a collision avoidance success rate of 97%, with a maximum response time of just 0.54 s.
  Keywords: improved SAC algorithm; autonomous vehicles; intelligent obstacle avoidance control; PER; priority experience replay.
  DOI: 10.1504/IJVD.2025.10073969
   
  
• This is a test paper, pleaseignore it
  by ReviewerV ReviewerC 
  Abstract: This is a test submission. Please ignore it
  Keywords: test test test test test test test test test test test test test test test test.
  
  
• A stable adaptive control method for the four wheel independent steering vehicle  
  by Zhiyao Pan, Hongyu Zheng 
  Abstract: Vehicle stability control is crucial for securing vehicle driving safety, while precise stability classification can assist in enhancing the performance of vehicle control. A stable adaptive model predictive controller (MPC) of the four-wheel independent steering (4WIS) vehicle is introduced in this paper. Firstly, a new vehicle dynamic model derived from a long short-term memory (LSTM) network is established and an attribute dataset representing vehicle stability is procured further. Subsequently, we employ the Gaussian mixture model (GMM)-hidden Markov model (HMM) to classify the stability of the 4WIS vehicle. According to the different classification results, the stable adaptive MPC integrated with Bayesian optimization (BO) is designed to track an optimal trajectory with high accuracy while working under different conditions. Through the simulation tests in various typical driving scenarios, the advantages of the stability classification strategy and the stable adaptive control method proposed in this paper are confirmed.
  Keywords: stability classification; stable adaptive control; four-wheel independent steering; LSTM; HMM-GMM; dataset; trajectory.
  DOI: 10.1504/IJVD.2025.10072493
   
  
• Prediction of the pedestrian landing mechanism in pedestrian-vehicle collisions  
  by Tiefang Zou, Pengchen Luo, Zhuzi Liu 
  Abstract: The pedestrian-ground injuries in pedestrian-vehicle collision has always been a research focus. This study explores the prediction model of pedestrian landing mechanism in pedestrian-vehicle collision. First, seven important parameters before, during and after the collision were extracted from 1,300 cases. The obtained parameters are converted into input parameters through Principal Component Analysis (PCA). Finally, the pedestrian landing mechanism prediction model under default parameters are constructed based on Back-Propagation Neural Network (BPNN), Genetic Algorithm (GA) optimized BPNN (GA-BPNN), Support Vector Machine (SVM), Decision Tree (DT) and Random Forest (RF). The results showed that the GA-BPNN model is the optimal model under default parameters; the performance of GA-BPNN was improved after hyperparameter optimization, and the prediction accuracy of the improved GA-BPNN (IGA-BPNN) model was 76.78%, 94.86% and 95.09%, respectively. Considering the pedestrian landing mechanism can significantly reduce the risk of vehicle braking control method and improve their protection efficiency.
  Keywords: pedestrian-vehicle collision; ground-related injury; pedestrian injury protection; prediction model of pedestrian landing mechanism; neural network; vehicle braking control.
  DOI: 10.1504/IJVD.2025.10073935
   
  
• Dynamic modelling of the stator system of flat wire motors  
  by Chao Yang, Ju-Guang Lin, Su-Xin Chen, Yong-Bin Zhang 
  Abstract: The dynamic behaviour of a stator system is crucial for the development of electric motors, as it plays a vital role in predicting and optimising the motor noise, which has emerged as a primary source of noise emissions in pure electric vehicles. Although the finite element method (FEM) is widely employed for modelling stator systems, existing FEM models typically focus on circular wire windings and fail to accurately represent stator systems with flat wire windings. Consequently, this paper aims to develop more precise FEM models for flat wire motor stator systems. The FEM models for the stator core, flat wire windings, insulating material, and the entire stator system are constructed by incorporating the unique characteristics of flat wire stator systems, particularly their radial stacking features. These proposed FEM models are validated through modal experiments conducted on an 8-pole 48-slot permanent magnet synchronous motor with flat wire windings.
  Keywords: stator; flat wire windings; finite element method; dynamic modelling.
  DOI: 10.1504/IJVD.2025.10074108
   
  
• Research on vehicle stability control under crosswind disturbance  
  by Jun Yang, Rui Qi, Yan Zheng 
  Abstract: Aiming at the problem that the high-speed vehicle is prone to yaw instability and drive away from the predetermined path under crosswind disturbance, this paper established an eight-degree-of-freedom vehicle dynamics model considering crosswind action, and used the phase plane method to identify the vehicle's state in crosswind environment. The coordinated controller of active front-wheel steering (AFS) and direct yaw-moment control (DYC) is designed to control the stability of the vehicle in the crosswind environment. The control algorithm is simulated and verified under the crosswind disturbance condition, and the results show that the lateral displacement of the vehicle with the coordinated controller of AFS and DYC is smaller than that of the vehicle with no control and a single controller, and the vehicle yaw rate, sideslip angle, and lateral acceleration are all significantly improved. The controller improves the driving safety and stability of the vehicle in the crosswind environment.
  Keywords: crosswind disturbance; stability control; active front-wheel steering control; direct yaw-moment control; phase plane method; coordinated control.
  DOI: 10.1504/IJVD.2025.10074109