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 re...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.展开更多
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 c...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.展开更多
基金support of the National Engineering Laboratory of High Mobility antiriot vehicle technology under Grant B20210017the National Natural Science Foundation of China under Grant 11672127+2 种基金the Fundamental Research Funds for the Central Universities under Grant NP2022408the Postgraduate Research&Practice Innovation Program of Jiangsu Province under Grant KYCX21_0188the Chinese Scholar Council under Grant 202106830118.
文摘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.
基金supported in part by the Key Research Project of North Minzu University under Grant 2021JCYJ09in part by the French Ministry of Higher Education and Research,in part by the National Center for Scientific Research(CNRS)+5 种基金in part by the ANR CoCoVeIA project(ANR-19-CE22-0009)in part by the ANR HM-Science project(ANR-21-CE48-0021)in part by the Hauts-de-France Region under the project RITMEA CPER 2021-2027in part by the National Natural Science Foundation of China under Grant 62163002in part by the Natural Science Foundation of Ningxia Hui Autonomous Region under Grant 2021AAC05011in part by the Advanced Intelligent Perception and Control Technology Innovative Team of Ningxia.
文摘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.
