Guoye Wang

The narrow tilting vehicle receives extensive public attention because of traffic congestion and environmental pollution, and the active rolling motion control is a traffic safety precaution that reduces the rollover risk caused by the structure size of the narrow vehicle. The drifting motion control reflects the relatively updated attentive research of the regular-size vehicle, which can take full advantage of the vehicle’s dynamic performance and improve driving safety, especially when tires reach their limits. The narrow tilting vehicle drifting control is worthy of research to improve the driving safety of the narrow tilting vehicle, especially when tires reach the limit. The nonlinear narrow tilting vehicle dynamic model is established with the UniTire model to describe the vehicle motion characteristics and is simplified to reduce the computation of the drifting controller design. The narrow tilting vehicle drifting controller is designed based on the robust theory with uncertain external disturbances. The controller has a wide application, validity, and robustness and whose performance is verified by realizing different drifting motions with different initial driving motions. The narrow tilting vehicle drifting robust control has some practical and theoretical significance for more research.

Professor drivers, including racing drivers, can drive cars to achieve drift motions by taking control of the steering angle in high tire slip ratios, which provides a way to improve the driving safety of autonomous vehicles. The existing studies can be divided into two kinds based on analysis methods, and the theory-based is chosen in this study. Because the recent theory based is most applied for planar models with neglect of the rollover accident risk, the nonlinear vehicle model is established by considering longitudinal, lateral, roll, and yaw motions and rolling safety with the nonlinear tire model UniTire. The drift motion mechanism is analyzed in steady and transient states to obtain drift motion conditions, including the velocity limitation and the relationship between sideslip angle and yaw rate, and vehicle main status parameters including the velocity, side-slip angle and yaw rate in drift conditions. The state-feedback controller is designed based on robust theory and LMI (linear matrix inequation) with uncertain disturbances to realize circle motions in drift conditions. The designed controller in simulations realizes drift circle motions aiming at analyzed status target values by matching the front-wheel steering angle with saturated tire forces, which satisfies the Lyapunov stability with robustness. Robust control in drift conditions solves the problem of how to control vehicles to perform drift motions with uncertain disturbances and improves the driving safety of autonomous vehicles.

Object recognition based on LIDAR data is crucial in automotive driving and is the subject of extensive research. However, the lack of accuracy and stability in complex environments obstructs the practical application of real-time recognition algorithms. In this study, we proposed a new real-time network for multicategory object recognition. The manually extracted bird’s eye view (BEV) features were adopted to replace the resource-consuming 3D convolutional operation. Besides the subject network, we designed two auxiliary networks to help the network learn the pointwise features and boxwise features, aiming to improve the category and bounding boxes’ accuracy. The KITTI dataset was adopted to train and validate the proposed network. Experimental results showed that, for hard mode, the total average precision (AP) of the category reached 97.4%. For an intersection over a union threshold of 0.5 and 0.7, the total AP of regression reached 93.2% and 85.5%; especially, the AP of car’s regression reached 95.7% and 92.2%. The proposed network also showed consistent performance in the Apollo dataset with a processing duration of 37 ms. The proposed network exhibits stable and robust object recognition performance in complex environments (multiobject, unordered objects, and multicategory). And it shows sensitivity to occlusion of the LIDAR system and insensitivity to close large objects. The proposed multifunction method simultaneously achieves real-time operation, high accuracy, and stable performance, indicating its great potential value in practical application.

Current regenerative braking systems in electric vehicles have several problems, such as complex structures, too many control parameters, and inconsistent braking responses. To solve these problems, a control algorithm with multidisciplinary design optimization (MDO) is proposed based on the novel regenerative–mechanical coupled brake-by-wire system. A dynamic model of the novel regenerative braking system was established to analyze the mechanism of coupled braking and propose a braking torque distribution strategy. To realize a better balance between the optimum braking stability and the maximum regenerative energy recovery based on the braking torque distribution strategy and sample points, the MDO mathematical model was developed to optimize the control parameters with the collaborative optimization algorithm. The finite sample points comprising the vehicle speed, battery state-of-charge, and braking severity were obtained through an optimal Latin hypercube design and represent the overall design space. A network was established based on the sample points and the optimization results. Using this network, the in-depth characteristics of the sample points and the optimization results were obtained through supervised learning to develop the control algorithm for vehicle braking. A simulation was performed using the normal braking condition, and the simulation results demonstrated that the control algorithm has higher control precision than conventional methods and better real-time performance than online optimization.