As one of the typical applications of cyber-physical system (CPS), autonomous vehicles (AVs) are vulnerable to malicious disturbance from cyber-attacks while tracking the desired path. This paper focuses on CPS-based path tracking control problem of AVs under cyber-attacks. Firstly, the nonlinear state and measurement equations of AVs under cyber-attacks are established based on vehicle dynamics model. Secondly, to improve the robustness of AVs against cyber-attacks, sensor redundancy is introduced. A cyber-attack detection method is designed by using extended Kalman filter (EKF), and the computational complexity of the cyber-attack detection method is analyzed. In addition, sensor switching rules are developed to isolate the disturbance of cyber-attacks. Then, the control problem of the AVs is formulated based on model predictive control (MPC). Input-to-state stability (ISS) of the control system under cyber-attacks is established, and a link between the tolerable attack intensity and the detection thresholds is clearly revealed. Finally, the simulation results demonstrate the effectiveness of the proposed control strategy.

Intelligent electric vehicles (IEVs) have attracted more and more attention benefitting from the characteristics of high degree of safety and energy efficiency. This paper proposes an adaptive cruise control framework considering regenerative braking to improve safety and energy efficiency of IEVs during the car-following process. At first, a coupled and nonlinear dynamic model of IEVs system is constructed, which is mainly composed of a powerful battery, an electric motor, a single-speed transmission, and a hydraulic braking system. Then, an adaptive fuzzy sliding mode high-level controller is designed to accurately obtain the desired longitudinal acceleration of IEVs, in which the fuzzy logic is utilized to approximate the switching control item of the sliding mode control for chattering free. And the stability of high-level controller is proven by the Lyapunov theory. In the lower-level controller, traction control and brake control are designed to track the desired acceleration produced by the high-level controller, in addition, a novel regenerative braking strategy is presented to maximize the braking energy recovery. Finally, the simulation results indicate that the proposed control scheme has the excellent performance of longitudinal tracking and braking energy recovery with no loss of safety.

The linear quadratic (LQ) synchronization problem for multiagent systems is solved by developing a distributed algorithm. It is the first time in the literature to formulate the LQ synchronization problem consisting of auxiliary synchronization state variables in discrete time with a finite horizon. The solution to this LQ synchronization problem is first considered in a centralized setting by leveraging connections to an alternating direction method of multiplier and then extended to a distributed setting, in which the individual agent's control inputs can be computed independently, thereby making the solution scalable. Numerical examples for both homogeneous and heterogeneous multiagent systems are given to demonstrate the effectiveness of the proposed method.

As autonomous vehicles and traditional vehicles will coexist for several decades, how to efficiently manage the mixed traffic, while enhancing road throughput, fuel consumption and traffic stability becomes a challenge. This is due to the randomness and heterogeneity of traditional vehicles interspersed among autonomous vehicles. Moreover, communication delays arising from the shared wireless communication network substantially degrade the performance of platooning control for connected autonomous vehicles. To address these challenging problems, this paper proposes a knowledge-guided self-learning mixed platoon control strategy. Firstly, the proposed strategy extracts key features of the continuous and aggregated behavior of traditional vehicles, such as desired time-varying time gap and standstill spacing, by integrating knowledge from the kinematic wave model and Newell’s car-following model. This helps autonomous vehicles predict traditional vehicles’ trajectories. Secondly, to tackle delayed current state information, the study incorporates previous control instructions into the state representation of the soft actor-critic algorithm. Simulations show the proposed strategy outperforms existing methods in traffic stability, passenger comfort, energy consumption cost and traffic oscillation dampening, with a zero collision rate in vehicle merging and diverging scenarios. The framework provides a generalizable and scalable solution for the development and adoption of connected autonomous vehicle systems.