Fuzzy Unknown Input Observer for Estimating Sensor and Actuator Cyber‑Attacks in Intelligent Connected Vehicles

The detection and mitigation of cyber-attacks in connected vehicle systems(CVSs)are critical for ensuring the security of intelligent connected vehicles.This paper presents a solution to estimate sensor and actuator cyber-attacks in CVSs.A novel method is proposed that utilizes an augmented system representation technique and a nonlinear unknown input observer(UIO)to achieve asymptotic estimation of both CVS dynamics and cyber-attacks.The nonlinear CVS dynamics is represented in a Takagi–Sugeno(TS)fuzzy form with nonlinear consequents,which allows for the effective use of the differential mean value theorem to handle unmeasured premise variables.Furthermore,via Lyapunov stability theory sufficient conditions are proposed,expressed in terms of linear matrix inequalities,to design TS fuzzy UIO.Several test scenarios are performed with high-fidelity Simulink-CarSim co-simulations to show the effectiveness of the proposed cyber-attack estimation method.

Deep Reinforcement Learning Based Decision‑Making Strategy of Autonomous Vehicle in Highway Uncertain Driving Environments

Uncertain environment on multi-lane highway,e.g.,the stochastic lane-change maneuver of surrounding vehicles,is a big challenge for achieving safe automated highway driving.To improve the driving safety,a heuristic reinforcement learning decision-making framework with integrated risk assessment is proposed.First,the framework includes a long short-term memory model to predict the trajectory of surrounding vehicles and a future integrated risk assessment model to estimate the possible driving risk.Second,a heuristic decaying state entropy deep reinforcement learning algorithm is introduced to address the exploration and exploitation dilemma of reinforcement learning.Finally,the framework also includes a rule-based vehicle decision model for interaction decision problems with surrounding vehicles.The proposed framework is validated in both low-density and high-density traffic scenarios.The results show that the traffic efficiency and vehicle safety are both improved compared to the common dueling double deep Q-Network method and rule-based method.

Preface for Cyber‑Attack Detection and Resilient Control of Intelligent and Connected Vehicles

Intelligent and connected vehicles(ICVs),as a critical future product of the automotive industry,have developed rapidly in recent years.The insertion of a cyber chain between vehicles can bring considerable benefits,including shared perception information,improved traffic efficiency,enhanced vehicle safety,optimized energy utilization,and reduced carbon emissions.