In autonomous driving scene understanding task， accurate segmentation of drivable areas， dynamic and static objects is essential for subsequent local motion planning and motion control. However， the current general semantic segmentation method based on lidar point cloud cannot achieve real-time and robust prediction on vehicle-end edge computing devices， and cannot predict the motion state of objects at the current moment. In order to solve this problem， a multi-task segmentation network MultiSegNet for driving areas and dynamic and static objects is proposed in this paper. The network uses the depth map output by the lidar and the processed residual image as the representation of the encoded spatial features and motion features to input to the network for feature learning， so as to avoid directly processing disordered high-density point clouds. For the large difference in the number of target distributions in different directions of the depth map， a variable resolution grouping input strategy is proposed， which can reduce the amount of network computation and improve the segmentation accuracy of the network. In order to adapt to the size of the convolutional receptive field required for targets at different scales， a depth-value-guided hierarchical dilated convolution module is proposed. At the same time， in order to effectively correlate and fuse the spatial position and attitude information of objects in different time domains， a spatiotemporal motion feature enhancement network is proposed. The effectiveness of the proposed MultiSegNet is verified on the large-scale point cloud driving scene datasets SemanticKITTI and nuScenes. The results show that the segmentation IoU of driving area， static object and dynamic object reaches 98%， 97% and 70%， respectively， which is better than that of mainstream networks， with real-time inference realized on edge computing devices.

At present， the assembly ratio of air suspension in different vehicle models is increasing， however， the air suspension matching of vehicle performance is mainly carried out based on the constant ambient temperature， and the control performance of air suspension in wide temperature range is rarely considered. For the problem of air suspension height control of passenger cars in wide temperature range， this paper proposes a wide temperature range air spring characterization model from the static characteristics of air springs， and simulates the height control of the suspension system of passenger cars in the non-motion state to carry out simulation and experiments， so as to realize the improvement of the service performance of the vehicle in the wide temperature range. Firstly， a wide temperature domain air spring model is established by wide temperature domain test data， which fully considers the influence of temperature on rubber and on gas. Secondly， an air suspension control algorithm based on the online linear quadratic regulator method （LQR） is proposed， which takes into account of the influence of temperature on airbag parameters. Finally， the robustness of the controller is verified under wide temperature domain conditions. Simulation and experiments show that the controller can control the body height to reach the target height and avoid oscillations under wide temperature range， with good stability and robustness.

For the complex hydraulic nonlinearity and time-varying friction disturbance of the Integrated Electro-hydraulic Brake System （IEHB）， an adaptive pressure control strategy is proposed. The outer-loop pressure controller introduces in a dynamic linearization model of hydraulic characteristics and realizes the adaptation of nonlinear hydraulic characteristics based on real-time identification of model parameters by a sliding mode observer. The inner-loop servo controller adopts pressure-based continuous friction compensation and back-stepping dynamic surface control to address frictional disturbance in the transmission mechanism. Hardware-in-the-loop test results show that， compared with the existing advanced cascade pressure control， the designed pressure control strategy exhibits higher control accuracy and robustness in various operating conditions， significantly improving the pressure control performance of IEHB under different hydraulic circuit structures.

To thoroughly review the current state and identify future trends of the Interior Sound Quality of Electric Vehicles （EVs）， the research progress and distinctive features of interior sound quality of electric vehicles are introduced firstly in this paper. Then， the limitation of the A-weighted sound level in evaluating the interior sound quality of EVs is introduced in detail， alongside objective evaluation approaches that incorporate psychoacoustic parameters and several unconventional parameters. Following this， a summary of subjective evaluation methods for the interior sound quality of EVs is made， including the advantages and disadvantages. Then， the objective quantification models for the interior sound quality of EVs both at home and abroad are classified and summarized. Finally， a summary and outlook are made on the evaluation of the sound quality of electric vehicles. It is believed that in the future the evolution of this field will likely pivot towards adopting high-precision objective models over traditional subjective methods， aiming to diminish evaluation time and cost while improving accuracy.

In order to identify and obtain the automotive structure fatigue damage of user route， the concepts of ‘element spectrum’ and ‘survey vehicle’ are proposed， and a convenient method for obtaining fatigue damage of automotive structure of user route based on road condition identification， classification and element spectrum is proposed. Firstly， the mathematical model of IRI （International Roughness Index） is established to identify the road grade and the method of identifying the user's road surface grade through the simple sensor scheme is established. And the correlation and independence between vehicle speed and IRI are studied. Subsequently， the method for determining the road classification and mileage distribution of the survey vehicle for user route based on IRI and vehicle speed is proposed. Then， combined with the element spectrum and unit mileage damage collected locally by the full-channel vehicle， the fatigue damage of the vehicle structure on the user's route is finally calculated efficiently. Thereby， the solution of ‘element spectrum + survey vehicle’ to identify the total damage of user route is created. The verification results are good， indicating that the technology and method studied is operable， exact and effective.

For the characteristic of significant load variation in urban logistics autonomous light trucks and to meet the needs of low computational load and high stability， a path-tracking control method based on Linear Parameter-Varying Model Predictive Control （LPV-MPC） is proposed in this paper. Firstly， a linear parameter-varying model is constructed， and nonlinear mapping rules between the model and scheduling variables - speed and load - are established， to improve driving stability and mitigating system sensitivity to parameter fluctuations. Then， for the rolling optimization stage， a trajectory reconstruction method is designed to reconcile disparities between the discrete trajectory points provided by the planning layer and the demand of the control module's prediction layer. A smooth trajectory sequence tailored to the temporal scale of the prediction layer is constructed to effectively decrease the deviation between predicted and actual states. In addition， a multi-point state deviation prediction method is used instead of the traditional single-point prediction， fully leveraging reference trajectory information for improved tracking accuracy. Finally， the effectiveness of the proposed control strategy is verified through combined simulation and empirical vehicle tests.

In shared road space， there are path conflicts between different road users moving in various directions. Road users must negotiate right-of-way through driving interactions to avoid collision risks， thus resolving potential conflicts. The description and modeling of interactive behaviors is crucial for accurately understanding and predicting the dynamic environment. Therefore， a semantic-level representation and extraction method for multi-vehicle interactive behaviors is proposed in this paper， taking interactive trajectory primitives as analysis units. Firstly， a nonparametric Bayesian method is utilized to segment interactive behaviors， obtaining interaction segments with significant behavior patterns. Then， the sticky hierarchical Dirichlet-Hidden Markov Model is employed to extract interaction primitives from these interaction segments. Finally， unsupervised clustering is applied to the normalized interaction primitives to obtain semantic-level behavioral features of interaction scenarios. An empirical study based on 20 797 pairs of multi-vehicle interaction data from the NGSIM highway dataset shows that the method proposed in this paper can extract and analyze complex interactive scenarios involving multiple participants， breaking through the limitation of existing research that only constructs interaction primitives for two vehicle interaction scenarios， and supporting the analysis of interaction among multiple traffic participants. The experimental results show that the proposed method can segment continuous driving behaviors into discrete interaction primitives. The clustering results correspond to actual interaction scenarios and can be used to characterize the interaction behaviors among vehicles in different interactive trajectory primitives. Furthermore， the method can enhance performance of downstream driving tasks in complex scenarios. In multi-step vehicle trajectory prediction， by integrating with baseline prediction methods， the proposed method can reduce the average prediction error and final position error by 19.3% and 14.6%， respectively， compared to baseline methods.

The road adhesion coefficient has an important impact on the vehicle dynamics control performance. In order to accurately obtain the road adhesion coefficient in real time and improve the estimation accuracy and convergence speed of the algorithm under different road surfaces and driving conditions， an interactive multiple model adaptive unscented Kalman filter （IMM-AUKF） based on the seven-degree-of-freedom vehicle dynamics model and Dugoff tire model is proposed in this paper for the distributed four-wheel-drive vehicles. The algorithm first introduces the improved Sage-Husa noise estimator into the UKF algorithm to construct the AUKF observer， which updates the measurement noise in real time and ensures the positive characterization of its covariance matrix， improves the weight of the new observation data， and enhances the real-time tracking accuracy and stability of the algorithm. Afterwards， the algorithm selects different observation variables to construct the longitudinal driving condition AUKF observer and the lateral-longitudinal coupling driving condition AUKF observer. And the IMM algorithm is also used to switch the observer model， so as to realize the algorithm's accurate estimation of the road adhesion coefficient under different driving conditions. The results of simulation tests on high/low attachment， joint and u-split roads and real vehicle road tests show that the proposed IMM-AUKF algorithm has higher estimation accuracy and faster convergence speed than the traditional UKF algorithm， and it can adapt to the real-time and accurate estimation of the road adhesion coefficient under different driving conditions.

The load spectrum of commercial vehicle cab assembly is the key factor affecting the accuracy and computational efficiency of virtual fatigue prediction. In this article， key links such as road load spectrum collection and editing， high fidelity dynamic modeling， and virtual iteration are explored， in order to obtain accurate and efficient external point time-domain loads from the engineering application perspective. Firstly， the full path road load spectrum of the driver's cab assembly is collected from the actual vehicle in the test field， and the original data is normalized， split， and reassembled considering random errors to obtain a statistically strong total damage target in the test field. Then， using the principle of equal damage， 9 operating conditions and their number of cycles are optimized， which not only controls the error within 10%， but also increases the efficiency by 75%. Subsequently， based on the performance parameters of the measured damping components， a high fidelity rigid flexible coupling dynamic model of the cab is established， and the accuracy of the model is verified through a 7-channel road simulation bench in the cab. Finally， the load decomposition of the optimal operating conditions is completed through virtual iteration， with an iteration error of less than 10%. Based on the above optimization and decomposition of the external connection point load， the virtual fatigue calculation of the cab body is efficiently completed， and the failure of the cab welding points is accurately predicted， which has a high degree of consistency with the durability test results of the road simulation bench， providing strong technical support for the design and optimization of commercial vehicle cabins.

The pose control method of the vehicle with dual motor active lateral stabilizer bar is studied in this paper. Firstly， a dynamic model of a dual motor active lateral stabilizer bar and an eight-degree-of-freedom vehicle model including roll， lateral， yaw pitch， and suspension vertical displacement are established. Secondly， for the problem that the control algorithm parameters are difficult to adjust under complex working conditions， the actual pitch angle estimation method， the ideal pitch angle calibration method， and the pitch condition identification method based on vehicle state information such as suspension height signal and road slope signal are proposed. The pitch sub-controller and the roll sub-controller based on PID control algorithm are designed with the dual motor active lateral stabilizer bar as the actuator. Genetic algorithm is used to tune the parameters of each sub-controller. Finally， combined with the pose control matrix， the vehicle pose joint control algorithm is designed and verified through experiments. The Hardware in Loop results of MATLAB/Simulink CarsimRT and Rapid ECU show that the improvement of the roll angle， roll angle speed， and pitch angle of the vehicle equipped with dual motor active lateral stabilizer bar is more than 10% under different complex working conditions， which proves the feasibility and universality of the control algorithm.