To resolve the response delay and overshoot problems of intelligent vehicles facing emergency lane-changing due to proportional-integral-differential(PID)parameter variation,an active steering control method based on ...To resolve the response delay and overshoot problems of intelligent vehicles facing emergency lane-changing due to proportional-integral-differential(PID)parameter variation,an active steering control method based on Convolutional Neural Network and PID(CNNPID)algorithm is constructed.First,a steering control model based on normal distribution probability function,steady constant radius steering,and instantaneous lane-change-based active for straight and curved roads is established.Second,based on the active steering control model,a three-dimensional constraint-based fifth-order polynomial equation lane-change path is designed to address the stability problem with supersaturation and sideslip due to emergency lane changing.In addition,a hierarchical CNNPID Controller is constructed which includes two layers to avoid collisions facing emergency lane changing,namely,the lane change path tracking PID control layer and the CNN control performance optimization layer.The scaled conjugate gradient backpropagation-based forward propagation control law is designed to optimize the PID control performance based on input parameters,and the elastic backpropagation-based module is adopted for weight correction.Finally,comparison studies and simulation/real vehicle test results are presented to demonstrate the effectiveness,significance,and advantages of the proposed controller.展开更多
The paper presents a preview controller design for ATS （active trailer steering） systems to improve high-speed stability of AHVs （articulated heavy vehicles）. An AHV consists of a towing unit, namely tractor or tr...The paper presents a preview controller design for ATS （active trailer steering） systems to improve high-speed stability of AHVs （articulated heavy vehicles）. An AHV consists of a towing unit, namely tractor or truck, and one or more towed units which called trailers. Individual units are connected to one another at articulated joints by mechanical couplings. Due to the multi-unit configurations, AHVs exhibit unique unstable motion modes, including jack-knifing, trailer swing and rollover. These unstable motion modes are the leading cause of highway accidents. To prevent these unstable motion modes, the preview controller, namely the LPDP （lateral position deviation preview） controller, is proposed. For a truck/full-trailer combination, the LPDP controller is designed to control the steering of the front and rear axle wheels of the trailing unit. The calculation of the corrective steering angle of the trailer front axle wheels is based on the preview information of the lateral position deviation of the trajectory of the axle center from that of the truck front axle center. Similarly, the steering angle of the trailer rear axle wheels is calculated by using the lateral position deviation of the trajectory of the axle center from that of the truck front axle. To perform closed-loop dynamic simulations and evaluate the vehicle performance measure, a driver model is introduced and it ＇derives＇ the AHV model based on well-defined testing specifications. The proposed preview control scheme in the continuous time domain is developed by using the LQR （linear quadratic regular） technique. The closed-loop simulation results indicate that the performance of the AHV with the LPDP controller is improved by decreasing rearward amplification ratio from the baseline value of 1.28 to 0.98 and reducing transient off-tracking by 95.03%. The proposed LPDP control algorithm provides an alternative method for the design optimization of AHVs with ATS systems.展开更多
Vehicle collision avoidance system is a kind of auxiliary driving system based on vehicle active safety,which can assist the driver to take the initiative to avoid obstacles under certain conditions,so as to effective...Vehicle collision avoidance system is a kind of auxiliary driving system based on vehicle active safety,which can assist the driver to take the initiative to avoid obstacles under certain conditions,so as to effectively improve the driving safety of vehicle.This paper presents a collision avoidance system for an autonomous vehicle based on an active front steering,which mainly consists of a path planner and a robust tracking controller.A path planner is designed based on polynomial parameterization optimized by simulated annealing algorithm,which plans an evasive trajectory to bypass the obstacle and avoid crashes.The dynamic models of the AFS system,vehicle as well as the driver model are established,and based on these,a robust tracking controller is proposed,which controls the system to resist external disturbances and work in accordance with the planning trajectory.The proposed collision avoidance system is testified through CarSim and Simulink combined simulation platform.The simulation results show that it can effectively track the planning trajectory,and improve the steering stability and anti-interference performance of the vehicle.展开更多
基金Supported by National Key R&D Program of China(Grant No.2018YFB1600500)Jiangsu Provincial Postgraduate Research&Practice Innovation Program of(Grant No.KYCX22_3673).
文摘To resolve the response delay and overshoot problems of intelligent vehicles facing emergency lane-changing due to proportional-integral-differential(PID)parameter variation,an active steering control method based on Convolutional Neural Network and PID(CNNPID)algorithm is constructed.First,a steering control model based on normal distribution probability function,steady constant radius steering,and instantaneous lane-change-based active for straight and curved roads is established.Second,based on the active steering control model,a three-dimensional constraint-based fifth-order polynomial equation lane-change path is designed to address the stability problem with supersaturation and sideslip due to emergency lane changing.In addition,a hierarchical CNNPID Controller is constructed which includes two layers to avoid collisions facing emergency lane changing,namely,the lane change path tracking PID control layer and the CNN control performance optimization layer.The scaled conjugate gradient backpropagation-based forward propagation control law is designed to optimize the PID control performance based on input parameters,and the elastic backpropagation-based module is adopted for weight correction.Finally,comparison studies and simulation/real vehicle test results are presented to demonstrate the effectiveness,significance,and advantages of the proposed controller.
文摘The paper presents a preview controller design for ATS （active trailer steering） systems to improve high-speed stability of AHVs （articulated heavy vehicles）. An AHV consists of a towing unit, namely tractor or truck, and one or more towed units which called trailers. Individual units are connected to one another at articulated joints by mechanical couplings. Due to the multi-unit configurations, AHVs exhibit unique unstable motion modes, including jack-knifing, trailer swing and rollover. These unstable motion modes are the leading cause of highway accidents. To prevent these unstable motion modes, the preview controller, namely the LPDP （lateral position deviation preview） controller, is proposed. For a truck/full-trailer combination, the LPDP controller is designed to control the steering of the front and rear axle wheels of the trailing unit. The calculation of the corrective steering angle of the trailer front axle wheels is based on the preview information of the lateral position deviation of the trajectory of the axle center from that of the truck front axle center. Similarly, the steering angle of the trailer rear axle wheels is calculated by using the lateral position deviation of the trajectory of the axle center from that of the truck front axle. To perform closed-loop dynamic simulations and evaluate the vehicle performance measure, a driver model is introduced and it ＇derives＇ the AHV model based on well-defined testing specifications. The proposed preview control scheme in the continuous time domain is developed by using the LQR （linear quadratic regular） technique. The closed-loop simulation results indicate that the performance of the AHV with the LPDP controller is improved by decreasing rearward amplification ratio from the baseline value of 1.28 to 0.98 and reducing transient off-tracking by 95.03%. The proposed LPDP control algorithm provides an alternative method for the design optimization of AHVs with ATS systems.
基金supported by the Research Project of Advanced Manufacture Technology for Automobile Parts(Chongqing University of Technology)Ministry of Education(Grant No.2015KLMT04)the National Natural Science Foundation of China(Grant No.51375007 and 51605219)
文摘Vehicle collision avoidance system is a kind of auxiliary driving system based on vehicle active safety,which can assist the driver to take the initiative to avoid obstacles under certain conditions,so as to effectively improve the driving safety of vehicle.This paper presents a collision avoidance system for an autonomous vehicle based on an active front steering,which mainly consists of a path planner and a robust tracking controller.A path planner is designed based on polynomial parameterization optimized by simulated annealing algorithm,which plans an evasive trajectory to bypass the obstacle and avoid crashes.The dynamic models of the AFS system,vehicle as well as the driver model are established,and based on these,a robust tracking controller is proposed,which controls the system to resist external disturbances and work in accordance with the planning trajectory.The proposed collision avoidance system is testified through CarSim and Simulink combined simulation platform.The simulation results show that it can effectively track the planning trajectory,and improve the steering stability and anti-interference performance of the vehicle.
