检索结果-南通市图书馆

Fixed-Time Cooperative Tracking for Delayed Disturbed Multi-Agent Systems Under Dynamic Event-Triggered Control

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2022年第5期9卷 930-933页

作者： Jian Liu Yongbao Wu Mengwei sun Changyin Sun School of Automation Southeast UniversityNanjing 210096 Key Laboratory of Measurement and Control of Complex System of Engineering Ministry of EducationSoutheast UniversityNanjing 210096China Institutes of Physical Science and Information Technology Anhui UniversityHefei 230601China IEEE

Dear editor,Recently,researchers have obtained many new results about the multi-agent systems(MASs)[1]-[3].In[1],the fixed-time cooperative control(FTCC)algorithm of linear MASs with matched disturbances was proposed.The nonholonomic chained-form dynamics case was considered in[2].In[3],the output tracking problem with data packet dropout was solved for high-order MASs.Moreover,delay frequently occurs because of the non-ideal data transmission[4],and the corresponding FTCC algorithm of MASs with delay was given in[5].

关键词： editor Dynamic Trigger Event

A Fast Clustering Based Evolutionary Algorithm for Super-Large-Scale Sparse Multi-Objective Optimization

在线全文

学校读者我要写书评

暂无评论

自动化学报：英文版 2023年第4期10卷 1048-1063页

作者： Ye Tian Yuandong Feng Xingyi Zhang Changyin Sun Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China School of Computer Science and Technology Anhui UniversityHefei 230601China School of Artificial Intelligence Anhui UniversityHefei 230601China School of Automation Southeast UniversityNanjing 210096China

During the last three decades,evolutionary algorithms(EAs)have shown superiority in solving complex optimization problems,especially those with multiple objectives and non-differentiable landscapes.However,due to the stochastic search strategies,the performance of most EAs deteriorates drastically when handling a large number of decision variables.To tackle the curse of dimensionality,this work proposes an efficient EA for solving super-large-scale multi-objective optimization problems with sparse optimal solutions.The proposed algorithm estimates the sparse distribution of optimal solutions by optimizing a binary vector for each solution,and provides a fast clustering method to highly reduce the dimensionality of the search space.More importantly,all the operations related to the decision variables only contain several matrix calculations,which can be directly accelerated by GPUs.While existing EAs are capable of handling fewer than 10000 real variables,the proposed algorithm is verified to be effective in handling 1000000 real variables.Furthermore,since the proposed algorithm handles the large number of variables via accelerated matrix calculations,its runtime can be reduced to less than 10%of the runtime of existing EAs.

关键词： Evolutionary computation fast clustering sparse multi-objective optimization super-large-scale optimization

Efficient Exploration for Multi-Agent Reinforcement Learning via Transferable Successor Features

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2022年第9期9卷 1673-1686页

作者： Wenzhang Liu Lu Dong Dan Niu Changyin Sun the School of Artificial Intelligence Anhui UniversityHefei 230039and also with the Peng Cheng LaboratoryShenzhen 518055China the School of Cyber Science and Engineering Southeast UniversityNanjing 211189China the School of Automation Southeast UniversityNanjing 210096China the School of Automation Southeast UniversityNanjing 210096and also with the Peng Cheng LaboratoryShenzhen 518055China

In multi-agent reinforcement learning(MARL),the behaviors of each agent can influence the learning of others,and the agents have to search in an exponentially enlarged joint-action space.Hence,it is challenging for the multi-agent teams to explore in the environment.Agents may achieve suboptimal policies and fail to solve some complex tasks.To improve the exploring efficiency as well as the performance of MARL tasks,in this paper,we propose a new approach by transferring the knowledge across tasks.Differently from the traditional MARL algorithms,we first assume that the reward functions can be computed by linear combinations of a shared feature function and a set of taskspecific weights.Then,we define a set of basic MARL tasks in the source domain and pre-train them as the basic knowledge for further use.Finally,once the weights for target tasks are available,it will be easier to get a well-performed policy to explore in the target domain.Hence,the learning process of agents for target tasks is speeded up by taking full use of the basic knowledge that was learned previously.We evaluate the proposed algorithm on two challenging MARL tasks:cooperative boxpushing and non-monotonic predator-prey.The experiment results have demonstrated the improved performance compared with state-of-the-art MARL algorithms.

关键词： Knowledge transfer multi-agent systems reinforcement learning successor features

Data-Based Optimal Tracking of Autonomous Nonlinear Switching Systems

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2021年第1期8卷 227-238页

作者： Xiaofeng Li Lu Dong Changyin Sun the School of Automation Southeast UniversityNanjing 210096 the Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSoutheast UniversityNanjing 210096China the College of Electronics and Information Engineering Tongji UniversityShanghai 201804China

In this paper,a data-based scheme is proposed to solve the optimal tracking problem of autonomous nonlinear switching systems.The system state is forced to track the reference signal by minimizing the performance function.First,the problem is transformed to solve the corresponding Bellman optimality equation in terms of the Q-function(also named as action value function).Then,an iterative algorithm based on adaptive dynamic programming(ADP)is developed to find the optimal solution which is totally based on sampled data.The linear-in-parameter(LIP)neural network is taken as the value function approximator.Considering the presence of approximation error at each iteration step,the generated approximated value function sequence is proved to be boundedness around the exact optimal solution under some verifiable assumptions.Moreover,the effect that the learning process will be terminated after a finite number of iterations is investigated in this paper.A sufficient condition for asymptotically stability of the tracking error is derived.Finally,the effectiveness of the algorithm is demonstrated with three simulation examples.

关键词： Adaptive dynamic programming approximation error data-based control Q-learning switching system

Self-triggered Consensus Control for Linear Multi-agent Systems With Input Saturation

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2020年第1期7卷 150-157页

作者： Yanxu Su Qingling Wang Changyin Sun School of Automation Southeast UniversityNanjing 210096and also with the Key Laboratory of Measurement and Control of Complex System of EngineeringMinistry of EducationSoutheast UniversityNanjing 210096China

In this paper, we study the consensus problem for a class of linear multi-agent systems(MASs) with consideration of input saturation under the self-triggered mechanism. In the context of discrete-time systems, a self-triggered strategy is developed to determine the time interval between the adjacent triggers. The triggering condition is designed by using the current sampled consensus error. Furthermore, the consensus control protocol is designed by means of a state feedback approach. It is shown that the considered multi-agent systems can reach consensus with the presented algorithm. Some sufficient conditions are proposed in the form of linear matrix inequalities(LMIs) to show the positively invariant property of the domain of attraction(DOA). Moreover, some sufficient conditions of controller synthesis are provided to enlarge the volume of the DOA and obtain the control gain matrix. A numerical example is simulated to demonstrate the effectiveness of the theoretical analysis results.

关键词： Index Terms—Input saturation linear matrix inequalities(LMIs),multi-agent systems(MASs) self-triggered control

Event-triggered receding horizon control via actor-critic design

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2020年第5期63卷 131-145页

作者： Lu DONG Xin YUAN Changyin Sun School of Automation Southeast University College of Electronics and Information Engineering Tongji University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSoutheast University

In this paper, we propose a novel event-triggered near-optimal control for nonlinear continuoustime systems. The receding horizon principle is utilized to improve the system robustness and obtain better dynamic control performance. In the proposed structure, we first decompose the infinite horizon optimal control into a series of finite horizon optimal problems. Then a learning strategy is adopted, in which an actor network is employed to approximate the cost function and an critic network is used to learn the optimal control law in each finite horizon. Furthermore, in order to reduce the computational cost and transmission cost, an event-triggered strategy is applied. We design an adaptive trigger condition, so that the signal transmissions and controller updates are conducted in an aperiodic way. Detailed stability analysis shows that the nonlinear system with the developed event-triggered optimal control policy is asymptotically stable.Simulation results on a single-link robot arm with different noise types have demonstrated the effectiveness of the proposed method.

关键词： event-triggered control receding horizon control actor-critic design optimal control nonlinear systems neural networks

A Bio-Inspired Flapping-Wing Robot With Cambered Wings and Its Application in Autonomous Airdrop

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2022年第12期9卷 2138-2150页

作者： Haifeng Huang Wei He Qiang Fu Xiuyu He Changyin Sun School of Intelligence Science and Technology University of Science and Technology BeijingBeijing 100083China Institute of Artificial Intelligence University of Science and Technology BeijingBeijing 100083China IEEE School of Automation Southeast UniversityNanjing 210096 School of Artificial Intelligence Anhui UniversityHefei 230601China

Flapping-wing flight, as the distinctive flight method retained by natural flying creatures, contains profound aerodynamic principles and brings great inspirations and encouragements to drone developers. Though some ingenious flapping-wing robots have been designed during the past two decades, development and application of autonomous flapping-wing robots are less successful and still require further research. Here, we report the development of a servo-driven bird-like flapping-wing robot named USTBird-I and its application in autonomous airdrop.Inspired by birds, a camber structure and a dihedral angle adjustment mechanism are introduced into the airfoil design and motion control of the wings, respectively. Computational fluid dynamics simulations and actual flight tests show that this bionic design can significantly improve the gliding performance of the robot, which is beneficial to the execution of the airdrop mission.Finally, a vision-based airdrop experiment has been successfully implemented on USTBird-I, which is the first demonstration of a bird-like flapping-wing robot conducting an outdoor airdrop mission.

关键词： Autonomous airdrop bionic design bio-inspired robot cambered wing flapping wing

A Data-Based Feedback Relearning Algorithm for Uncertain Nonlinear Systems

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2023年第5期10卷 1288-1303页

作者： Chaoxu Mu Yong Zhang Guangbin Cai Ruijun Liu Changyin Sun the School of Electrical and Information Engineering Tianjin UniversityTianjin 300072China the College of Missile Engineering Rocket Force University of EngineeringXi’an 710025China the School of Computer and Information Engineering Beijing Technology and Business UniversityBeijing 100048China the School of Automation Southeast UniversityNanjing 210096China

In this paper,a data-based feedback relearning algorithm is proposed for the robust control problem of uncertain nonlinear systems.Motivated by the classical on-policy and off-policy algorithms of reinforcement learning,the online feedback relearning(FR)algorithm is developed where the collected data includes the influence of disturbance signals.The FR algorithm has better adaptability to environmental changes(such as the control channel disturbances)compared with the off-policy algorithm,and has higher computational efficiency and better convergence performance compared with the on-policy algorithm.Data processing based on experience replay technology is used for great data efficiency and convergence stability.Simulation experiments are presented to illustrate convergence stability,optimality and algorithmic performance of FR algorithm by comparison.

关键词： Data episodes experience replay neural networks reinforcement learning(RL) uncertain systems

Hybrid Q-learning for data-based optimal control of non-linear switching system

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2022年第5期33卷 1186-1194页

作者： LI Xiaofeng DONG Lu sun changyin School of Automation Southeast UniversityNanjing 210096China School of Artificial Intelligence Anhui UniversityHefei 230601China School of Cyber Science and Engineering Southeast UniversityNanjing 211189China

In this paper,the optimal control of non-linear switching system is investigated without knowing the system dynamics.First,the Hamilton-Jacobi-Bellman(HJB)equation is derived with the consideration of hybrid action space.Then,a novel data-based hybrid Q-learning(HQL)algorithm is proposed to find the optimal solution in an iterative manner.In addition,the theoretical analysis is provided to illustrate the convergence and optimality of the proposed algorithm.Finally,the algorithm is implemented with the actor-critic(AC)structure,and two linear-in-parameter neural networks are utilized to approximate the functions.Simulation results validate the effectiveness of the data-driven method.

关键词： switching system hybrid action space optimal control reinforcement learning hybrid Q-learning(HQL)