For safe and feasible pathplanning in real time of autonomous parking system, a parking path planning algorithm based on constrained reinforcement learning with a hybrid action space is proposed in this paper. Specifically, the proposed algorithm employs a hybrid action space reinforcement learning framework that integrates discrete actions with continuous parameters to achieve parameterized trajectory planning, thereby enhancing the executability of planned paths. On this basis, a constrained reinforcement learning algorithm within the hybrid action space is designed to optimize safe policy execution, ensuring the safety of parking paths. Moreover, a curriculum learning mechanism is introduced during model training to guide exploration progressively, improving training stability and convergence speed. Finally, extensive comparative and ablation experiments are conducted on both perpendicular and parallel parking scenarios. The experimental results show that the proposed parking path planning algorithm outperforms existing stateoftheart methods in terms of success rate, safety, and realtime performance, exhibiting superior overall effectiveness.

Developing a highprecision Statistical Energy Analysis (SEA) model to predict vehicle wind noise response requires a significant amount of time and cost. In this paper, a method is proposed for rapidly constructing an equivalent SEA model for vehicle wind noise based on parameter identification, which simplifies the modeling process while ensuring prediction accuracy. An initial SEA model of the compartment is established according to the vehicle's body structure and dimensions, with the pressure fluctuation excitation on the side window surface and the actual wind tunnel response serving as the model's input and output, respectively. The Grey Wolf Optimizer (GWO) algorithm is employed to identify the acoustic cavity parameters of the model, resulting in an equivalent model that approximates the true wind noise response characteristics. Taking a prototype vehicle as an example, the equivalent wind noise SEA model is used to predict the wind noise response in the compartment under different design schemes. The average prediction error for the total sound pressure level is 1.47%, and the root mean square error of the spectrum is 1.23 dB. The results show that the equivalent model can accurately predict the invehicle wind noise response under different design schemes, thereby reducing the number of wind tunnel tests and having high engineering application value.

In traffic accidents, the results of head injuries resulting from frontal and side impact of vehicles vary significantly, primarily due to the differing impact locations. To investigate the specific effect of impact locations on brain injuries with various impact strengths, experiments are conducted on male rats, focusing on cranial vertex and temporal lobe impact. An experimental protocol is established based on the L₄ (2³) orthogonal table, including impact strength and impact location factors. Rats are injured using the BIMIV rat head impact machine. The effect of impact factors and their levels on TBI is assessed systematically by behavioral performance and pathological findings of key brain regions in rats. The results show that impact strength is the primary factor influencing head injury, but the effect of impact location is not negligible. At the same impact strength, cranial vertex impact is more likely to cause coma, motor and memory deficits, and anxiety than temporal lobe impact. Furthermore, cranial vertex impact results in higher pathological injuries than the nonimpact side of temporal lobe impact, but lower than the impact side. The linear fitting between behavioral performance and pathological results reveals that postinjury behavioral performance in rats more closely aligns with the pathological outcomes on the less injured side of the brain. The findings of this study are crucial for understanding the mechanisms of head injury, proposing appropriate injury evaluation guidelines, and establishing effective protection strategies.

The dualmotor coupled drive is a common configuration for the Electromechanical Transmission (EMT) system in tracked vehicles, which is characterized by inputoutput coupling, high power transmission efficiency, and variable load conditions. However, most existing torsional vibration control strategies for EMT are designed for symmetric excitation conditions on both sides, which do not align well with realworld operating scenarios. To improve the torsional vibration under asymmetric excitation, an EMT torsional vibration model is first established to investigate the vibration energy coupling effect between the two sides of the EMT under asymmetric excitation and its influence mechanism on the system's dynamic behavior. Based on these findings, a disturbance compensation method based on dualloop feedback is proposed, and a torsional vibration suppression strategy tailored for EMT under asymmetric excitation is developed. Verification results show that this strategy can effectively suppress torsional vibration of the EMT system under such excitation conditions.

The total vehicle mass is an important parameter for both power and safety control of the vehicle, especially for heavyduty trucks. Based on the theory of vehicle longitudinal dynamics, a method for estimating the total vehicle mass according to the vehicle operating conditions is proposed in this paper. Firstly, under acceleration conditions, engine torque and longitudinal acceleration are obtained through CAN bus, using the Kalman filter algorithm (KF) to estimate the total vehicle mass. Then the estimated mass is used to identify the unknown parameters. At constant speed, the mass is estimated based on the identified unknown parameters and a simplified vehicle longitudinal dynamics model. The effectiveness of the method is verified through joint simulation suing the estimator constructed by TruckSim/Simulink. By the vehicle road test, the results show that the method is able to estimate the total vehicle mass more accurately under different operating conditions.

A speed loop optimization strategy based on cascaded extended state observer (ESO) is proposed to address the insufficient transient response of permanent magnet synchronous motor (PMSM) for steering power oil pump application in pure electric commercial vehicles. An extended Kalman filter (EKF) is designed as the basis of position sensorless control, with the adaptive design to avoid the problems of complicated parameter tuning and slow convergence. The antidisturbance and tracking ability of the speed loop is improved by the cascaded observation of internal and external disturbances, and the use of the linear state error feedback control rate (LSEFC) for replacement of the traditional PI controller. The bench tests show that the sensorless control scheme proposed in this paper significantly reduces the position estimation error under dynamic and steadystate conditions, with a steadystate error of only 1.4°. The optimized speed loop control effectively improves the system's performance of disturbance rejection and transient response. The reliability test shows that the steering power motor controller operates stably without performance failure.

In order to adapt to the high power density of automotive high-speed motors and the high thermal load under extreme working conditions, the current motor cooling mostly adopts the direct contact oil cooling heat dissipation method, and it is necessary to establish a motor oil temperature model suitable for the study of thermal control methods. Existing methods are mainly based on finite element simulation calibration, which cannot meet the realtime application requirements, while the multi-physical field coupling of the complex oilwater heat transfer circuit makes it difficult for the online reconstruction of oil temperature. In this paper, a secondorder lumpedparameter oil temperature model is proposed to strengthen the time-sequence cyclic process and consider the strong autocor-relation. The oil circuit unit is modeled according to the calibration, and the motor loss response is determined based on bench-top measurements. The time-sequence convolution method is adopted to describe the heat transfer process, and a cyclic dynamic recursive model with high and low oil temperature coupling is established. Oil temper-ature-sensitive parameters are introduced to improve the adaptability of the working conditions to solve the difficult problem of describing the oil temperature distribution in the flow path. Finally, the model accuracy is verified online by road spectrum working conditions, with the average absolute estimation error of the oil coolant temperature within 1°C, which can support the refined thermal management of the motor.

For the problem that the spatiotemporal separation trajectory planning method used in autonomous vehicles is prone to insufficient vehicle flexibility, and even cannot generate feasible trajectories under complex working conditions, while the existing spatiotemporal unified trajectory planning method is difficult to meet the requirements of structured road application, a spatiotemporal unified planning method based on dynamic programming and numerical optimization algorithm is proposed. Firstly, the spatiotemporal unified coarse trajectory is generated by dynamic programming algorithm in Frenet coordinate system. In the process, deterministic sampling method is used to expand the child nodes. Then, taking the coarse trajectory as reference, the feasible spatiotemporal corridor is constructed in Cartesian coordinate system, and the NMPC optimization model is established to generate the final trajectory. Finally, the algorithm is verified by simulation. The results show that the proposed algorism has good adaptability to structured road, and can better balance the requirements of traffic efficiency, trajectory comfort and time consumption than other spatiotemporal unified algorithms.

The power system and energy consumption characteristics of electric buses significantly differ from those of traditional buses with internal combustion engines, and conventional ecodriving strategies cannot fully adapt to electric buses. An energy consumption predictionbased deep reinforcement learning model is proposed for ecodriving of connected electric buses, taking into account of signal timing, information from preceding vehicles, energy consumption characteristics and comfort of passengers. Firstly, natural driving data from battery electric buses is collected, and a basic energy consumption model is established using vehicle dynamics, considering the regenerative braking characteristics of electric buses. A system identification model is then constructed to identify and estimate the unknown parameters in the basic energy consumption model. Next, the impact of different signal phases on speed patterns when entering and exiting signalized intersections is analyzed, and state variables that accurately describe traffic environment information are determined. Based on the constructed energy consumption model, a reward function is developed, considering safety, efficiency, energy conservation, and comfort. An optimization model for ecodriving strategies at signalized intersections for electric buses is established using the SAC (soft actor critic) algorithm. Finally, the proposed strategy is compared with the classic intersection passage strategy GLOSA. The results show that the proposed ecodriving strategy ensures vehicle safety across the four defined traffic scenarios. Despite an average increase in travel time of only 7.29%, the strategy enhances comfort by an average of 21.96% and reduces energy consumption by an average of 24.47%.

In a mixed traffic ecosystem, accurately predicting the trajectories of surrounding vehicles is crucial for the safety of autonomous vehicles. However, existing technologies still face issues of accuracy and computational complexity in longterm prediction. A spatiotemporal interactive sparse attention model combined with intention probability is proposed in this paper, which predicts trajectories through an efficient encoderdecoder structure. The position mask matrix is first constructed to extract positional information from historical trajectories, and key features are selected using the sparse attention mechanism. The intention behavior analysis module is utilized to improve the accuracy of intention recognition. Finally, spatiotemporal features, positional features, and intention features are fused and input into the decoder, and the model is trained using a multitask learning approach. The experimental results show that, compared to the optimal algorithm on the HighD and NGSIM datasets, the proposed model achieves a notable reduction in root mean square error (RMSE) in longterm prediction of 3 to 5 seconds, significantly enhancing prediction accuracy. In addition, the model's performance in realworld scenarios is validated through road tests, further demonstrating its application potential in complex traffic environment.