Based on service-oriented architecture(SOA),a Bellman-dynamic-programming-based approach of service recovery decision-making is proposed to make valid recovery decisions.Both the attribute and the process of service...Based on service-oriented architecture(SOA),a Bellman-dynamic-programming-based approach of service recovery decision-making is proposed to make valid recovery decisions.Both the attribute and the process of services in the controllable distributed information system are analyzed as the preparatory work.Using the idea of service composition as a reference,the approach translates the recovery decision-making into a planning problem regarding artificial intelligence (AI) through two steps.The first is the self-organization based on a logical view of the network,and the second is the definition of evaluation standards.Applying Bellman dynamic programming to solve the planning problem,the approach offers timely emergency response and optimal recovery source selection,meeting multiple QoS (quality of service)requirements.Experimental results demonstrate the rationality and optimality of the approach,and the theoretical analysis of its computational complexity and the comparison with conventional methods exhibit its high efficiency.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
Traditional five-axis tool path planning methods mostly focus on differential geometric characteristics between the cutter and the workpiece surface to increase the material removal rate(i.e.,by minimizing path length...Traditional five-axis tool path planning methods mostly focus on differential geometric characteristics between the cutter and the workpiece surface to increase the material removal rate(i.e.,by minimizing path length,improving curvature matching,maximizing local cutting width,etc.) . However,material removal rate is not only related to geometric conditions such as the local cutting width,but also constrained by feeding speed as well as the motion capacity of the five-axis machine. This research integrates machine tool kinematics and cutter-workpiece contact kinematics to present a general kinematical model for five-axis machining process. Major steps of the proposed method include:(1) to establish the forward kinematical relationship between the motion of the machine tool axes and the cutter contact point;(2) to establish a tool path optimization model for high material removal rate based on both differential geometrical property and the contact kinematics between the cutter and workpiece;(3) to convert cutter orientation and cutting direction optimization problem into a concave quadratic planning(QP) model. Tool path will finally be generated from the underlying optimal cutting direction field. Through solving the time-optimal trajectory generation problem and machining experiment,we demonstrate the validity and effectiveness of the proposed method.展开更多
文摘Based on service-oriented architecture(SOA),a Bellman-dynamic-programming-based approach of service recovery decision-making is proposed to make valid recovery decisions.Both the attribute and the process of services in the controllable distributed information system are analyzed as the preparatory work.Using the idea of service composition as a reference,the approach translates the recovery decision-making into a planning problem regarding artificial intelligence (AI) through two steps.The first is the self-organization based on a logical view of the network,and the second is the definition of evaluation standards.Applying Bellman dynamic programming to solve the planning problem,the approach offers timely emergency response and optimal recovery source selection,meeting multiple QoS (quality of service)requirements.Experimental results demonstrate the rationality and optimality of the approach,and the theoretical analysis of its computational complexity and the comparison with conventional methods exhibit its high efficiency.
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.
基金supported by the National Basic Research Program of China ("973" Program) (Grant No. 2011CB706800)the National Natural Science Foundation of China (Grant No. 50835004)the National Funds for Distinguished Young Scientists of China (Grant No. 51025518)
文摘Traditional five-axis tool path planning methods mostly focus on differential geometric characteristics between the cutter and the workpiece surface to increase the material removal rate(i.e.,by minimizing path length,improving curvature matching,maximizing local cutting width,etc.) . However,material removal rate is not only related to geometric conditions such as the local cutting width,but also constrained by feeding speed as well as the motion capacity of the five-axis machine. This research integrates machine tool kinematics and cutter-workpiece contact kinematics to present a general kinematical model for five-axis machining process. Major steps of the proposed method include:(1) to establish the forward kinematical relationship between the motion of the machine tool axes and the cutter contact point;(2) to establish a tool path optimization model for high material removal rate based on both differential geometrical property and the contact kinematics between the cutter and workpiece;(3) to convert cutter orientation and cutting direction optimization problem into a concave quadratic planning(QP) model. Tool path will finally be generated from the underlying optimal cutting direction field. Through solving the time-optimal trajectory generation problem and machining experiment,we demonstrate the validity and effectiveness of the proposed method.