The rapid development of intelligent vehicles has paved the way for active chassis lateral stability, which is a novel issue and critical to vehicle stability and handling performance. To obtain active chassis lateral stability for intelligent vehicles, a nonlinear model predictive control (NMPC) method integrating active front steering and an additional yaw moment is proposed. It adopts the tire sideslip angle to express vehicle lateral stability, and addresses the actuator and security constraints and the nonlinear properties of the tire-road force effectively. Moreover, the hardware implementation, based on the field programmable gate array (FPGA), is presented to satisfy miniaturization and to discuss the computational efficiency of the proposed NMPC method. To verify the effectiveness of the presented NMPC method, offline simulations comparing the NMPC method with the direct yaw moment control (DYC) method under various running conditions and a real-time implementation experiment are carried out. The results indicate that the proposed NMPC method controls better than the DYC-based method. In addition, the presented NMPC method exhibits good robustness when the longitudinal velocity and tire-road friction coefficient vary within a suitable range. Moreover, the computational time of the proposed NMPC controller, implemented using the FPGA, is only 4.994 ms during one sampling period, which can satisfy the real-time requirement of active chassis lateral stability control.

This paper proposes an extensive overview of the tire-road interaction estimation issue as it relates to automated driving from the prospectives of sensor configuration, tire modeling, and estimation approaches. The tire-road interactions needed for estimation are first determined and classified. Then, the sensor configuration schemes of different types of tire-road interactions are presented and analyzed. The following introduces various types of tire models and provides the limitations and advantages of different estimation approaches based on categorizing and summarizing those techniques. Moreover, some interesting perspectives for future research are listed based on the extensive experience of the authors.

Predicting the trajectory of neighboring vehicles is closely related to the driving safety of intelligent vehicles and supports driving assistance. This article proposes a dual-attention mechanism trajectory prediction method based on long short-term memory encoding that is coupled with the motion trend of the ego vehicle. The temporal attention mechanism maximizes the use of historical trajectory information and analyses its validity under different working conditions. A spatial attention mechanism coupled with motion trend is proposed that analyses how neighboring vehicles influence the target vehicle’s trajectory, combining the motion trend of the ego vehicle with the free space of the target vehicle to reduce uncertainty in the potential trajectory. Tests conducted on the NGSIM dataset show that the method proposed here achieves greater prediction accuracy than state-of-the-art models and can divide the historical trajectory contribution and quantify the impact of neighboring vehicles. An error analysis for different traffic scenarios shows the generalizability of the model.

Connected automated vehicle (CAV) platoon control is becoming increasingly prevalent because of its unique advantages in reducing fuel consumption and improving traffic efficiency. A novel control framework for CAV platoon control is designed in this paper. First, a model predictive control (MPC)-based method is proposed to obtain the optimal velocity of the whole platoon, in which both reducing fuel consumption and improving transport efficiency are taken into account in the optimization process. Then, a distributed adaptive triple-step nonlinear control strategy is investigated from the perspective of multi-agent system control. The adaptive performance of the control strategy can guarantee string stability of the CAV platoon under the premise of the existence of dynamic uncertainties. Various simulation conditions with heterogeneous dynamic disturbances are designed to validate the proposed control strategy, and the results show that the proposed control strategy can be robust to dynamic disturbances while ensuring the string stability of the CAV platoon.

An online energy management controller is presented in this paper for a plug-in hybrid electric vehicle (PHEV), which is based on driving conditions recognition and genetic algorithm (GA). The proposed controller can be used in the real-time ap-plication. First, the studied multimode PHEV is modeled and four traction operation modes are introduced in detail. Second, the principal component analysis (PCA) algorithm is utilized to classify the real historical driving conditions data. Four types of driving conditions are constructed to describe the representative scenarios. Then, GA is applied to search the optimal values for seven control actions offline. These parameters for different driving conditions are preserved and can be activated online. Finally, the driving condition is identified online and the corre-sponding control actions are loaded and adopted. Simulation results indicate that the proposed approach is close to the glob-ally optimal method, dynamic programming (DP) and is superi-or to the charge depleting/charge sustaining (CD/CS) technique. Also, hardware in the loop (HIL) experiment is built to validate the real-time characteristic of the proposed strategy.

The roundabout is a typical changeable, interactive scenario in which automated vehicles should make adaptive and safe decisions. In this article, an optimization embedded reinforcement learning (OERL) is proposed to achieve adaptive decision-making under the roundabout. The promotion is the modified actor of the Actor-Critic framework, which embeds the model-based optimization method in reinforcement learning to explore continuous behaviors in action space directly. Therefore, the proposed method can determine the macroscale behavior (change lane or not) and medium-scale behaviors of desired acceleration and action time simultaneously with high sample efficiency. When scenarios change, medium-scale behaviors can be adjusted timely by the embedded direct search method, promoting the adaptability of decision-making. More notably, the modified actor matches human drivers' behaviors, macroscale behavior captures the human mind's jump, and medium-scale behaviors are preferentially adjusted through driving skills. To enable the agent adapts to different types of the roundabout, task representation is designed to restructure the policy network. In experiments, the algorithm efficiency and the learned driving strategy are compared with decision-making containing macroscale behavior and constant medium-scale behaviors of the desired acceleration and action time. To investigate the adaptability, the performance under an untrained type of roundabout and two more dangerous situations are simulated to verify that the proposed method changes the decisions with changeable scenarios accordingly. The results show that the proposed method has high algorithm efficiency and better system performance.