检索结果-内蒙古大学图书馆

Policy iteration based Q-learning for linear nonzero-sum quadratic differential games

science China(Information sciences) 2019年第5期62卷 195-213页

作者： Xinxing LI Zhihong PENG Li LIANG Wenzhong ZHA School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex System Information Science Academy China Electronics Technology Group Corporation

In this paper, a policy iteration-based Q-learning algorithm is proposed to solve infinite horizon linear nonzero-sum quadratic differential games with completely unknown dynamics. The Q-learning algorithm, which employs off-policy reinforcement learning(RL), can learn the Nash equilibrium and the corresponding value functions online, using the data sets generated by behavior policies. First, we prove equivalence between the proposed off-policy Q-learning algorithm and an offline PI algorithm by selecting specific initially admissible polices that can be learned online. Then, the convergence of the off-policy Qlearning algorithm is proved under a mild rank condition that can be easily met by injecting appropriate probing noises into behavior policies. The generated data sets can be repeatedly used during the learning process, which is computationally effective. The simulation results demonstrate the effectiveness of the proposed Q-learning algorithm.

关键词： adaptive dynamic programming ADP Q-learning reinforcement learning RL linear nonzerosum quadratic differential games policy iteration PI off-policy

来源：评论

学校读者我要写书评

暂无评论

Integrated design and performance optimization of three-electrode sliding discharge plasma power supply

引用

Plasma science and technology 2024年第11期26卷 152-161页

作者： Borui ZHENG Linwu WANG Jianbo ZHANG Shaojie QI Yuhong CHEN Haodong LIU Dongliang BIAN School of Automation and Information Engineering Xi’an University of TechnologyXi’an 710048People’s Republic of China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an 710048People’s Republic of China School of Mechanical and Precision Instrument Engineering Xi’an University of TechnologyXi’an 710048People’s Republic of China Science and Technology on Plasma Dynamics Laboratory Air Force Engineering UniversityXi’an 710038People’s Republic of China

The three-electrode sliding dielectric barrier discharge(TES-DBD) plasma actuator significantly enhances the ionization rate and momentum exchange between charged particles and neutral particles by incorporating a parallel DC electrode into the standard DBD design. This design improves the body force and induced jet velocity while allowing flexible control of the induced jet angle, overcoming the limitations of discharge extension and uncontrollable direction in traditional DBD plasma actuators. An integrated plasma power supply has been designed specifically for TES-DBD plasma actuators, streamlining the power supply management. The methodology involves designing the circuit topology for the TES-DBD power supply, followed by simulating and validating its operating principles using Multisim software. The operational performance of the power supply is evaluated through a comprehensive analysis of its electrical,thermal, and aerodynamic properties specific to TES-DBD plasma actuation.

关键词： plasma flow control dielectric barrier discharge three-electrode sliding discharge plasma power supply

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal evolution laws of sector-shaped dielectric-barrier-discharge plasma actuator

引用

Plasma science and technology 2024年第10期26卷 108-115页

作者： Borui ZHENG Jianbo ZHANG Shaojie QI Jianghua XU Yiche LI Yuanzhong JIN Dongliang BIAN School of Automation and Information Engineering Xi’an University of TechnologyXi’an 710048People’s Republic of China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an 710048People’s Republic of China School of Mechanical and Precision Instrument Engineering Xi’an University of TechnologyXi’an 710048People’s Republic of China Science and Technology on Plasma Dynamics Laboratory Air Force Engineering UniversityXi’an 710038People’s Republic of China

Dielectric barrier discharge(DBD)plasma actuators are widely used in active flow control due to their simple design and rapid ***,they need more effectiveness and discharge *** overcome these limitations,a sector-shaped dielectric barrier discharge(SS-DBD)plasma actuator with an adjustable jet angle was developed to enhance flow control *** flow field dynamics induced by the SS-DBD plasma actuator were quantitatively analyzed using particle image velocimetry(PIV).Experimental investigations showed that precise adjustments to the actuation voltage can modulate the maximum velocity of the induced ***,a quasi-linear relationship between the sector-shaped angles of the SS-DBD and the deflected jet angles was established,indicating that changes in the sector-shaped angles directly influence the direction of the deflected *** correlation enables precise control over jet angles,significantly enhancing flow control by adjusting the SS-DBD-PA's sector-shaped angle.

关键词： plasma flow control plasma actuator particle image velocimetry

来源：评论

学校读者我要写书评

暂无评论

Monocular Visual-Inertial Odometry Based on Point and Line Features

Monocular Visual-Inertial Odometry Based on Point and Line F...

引用

International Conference on Computer and Communications (ICCC)

作者： Gongyan Chen Hai Zhang Wenxing Fu Yiqun Qiao School of Automation Science and Electrical Engineering Beihang University Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9781728186351

ISBN: (纸本)9781728186368

In order to solve the problem that the point feature tracking is not robust enough to reduce the accuracy of the system in a low-texture environment, this paper proposes a visual inertial odometry system based on point-line features (PL-VINS). Firstly, the system improves the extraction and matching algorithm of line features to increase the speed and accuracy of the algorithm; then the line features are added to the front-end tracking and back-end optimization. Finally, the EuRoc public data set is used as the experimental object to prove the effectiveness of the algorithm.

关键词： Visualization Conferences Feature extraction Cameras Real-time systems Optimization Optical flow

来源：评论

学校读者我要写书评

暂无评论

An Improved Robust Adaptive Kalman Filtering Algorithm

An Improved Robust Adaptive Kalman Filtering Algorithm

引用

第三十八届中国控制会议

作者： Liuyang Jiang Wenxing Fu Hai Zhang Zheng Li Longyun Chi School of Automation Science and Electrical Engineering Beihang University Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory National Airspace Management Center

Robust adaptive Kalman filter(RAKF) is a method that can not only compensate for the model errors but also resist the measurement outliers. The method reduces the influence of the measurement outliers on the filtering system by reducing the weight of the abnormal observation. After the processing of robust estimation, all the errors are attributed to the inaccuracy of the model. Since the robust estimation is not theoretically quantitative that it can only reduce the observation error to a certain extent, the remaining observation errors are compensated as the model errors, resulting in new estimation errors. To address this problem, a method for detecting the model error is proposed as a trigger condition for RAKF to compensate for the model error,and this constitutes an improved robust adaptive Kalman filter(IRAKF) algorithm. The new algorithm performs the model errors compensation stricter than the original method. The efficacy of the improved algorithm is demonstrated via a traffic running testing with GPS/INS tight integration navigation system. Simulation results indicate that the improved algorithm can effectively reduce the inaccurate adaptive procedure and obtain relatively accurate and stable filtering results.

关键词： Adaptive Kalman Filter Robust Estimation Improved Model Errors Tight Integrated Navigation

来源：评论

学校读者我要写书评

暂无评论

A Multi-Robot Task Allocation Method Based on Graph Attention Network and Unsupervised Learning

A Multi-Robot Task Allocation Method Based on Graph Attentio...

引用

2024 IEEE International Conference on Unmanned systems, ICUS 2024

作者： Wu, Zirui Li, Zhen Zhu, Dong Liao, Qiuhan Yao, Weiran School of Astronautics Harbin Institute of Technology Harbin China Beijing Electro-Mechanical Engineering Institute Beijing China Chengdu CHG Robots & Intelligent Equipment Institute Co. Ltd. Chengdu China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing China

ISBN: (纸本)9798350384185

The task allocation for multiple robots is a critical component in the coordination of unmanned *** existing heuristic algorithms are hard to achieve satisfactory results in large-scale problems, and reinforcement learning-based methods face challenges in ensuring the rationality of reward *** paper introduces a model based on multi-head attention and graph neural networks to address the schedule-dependent multi-robot task allocation problem, trained using unsupervised learning *** model can be trained with varying numbers of robots and tasks without necessitating changes to its structure or *** the experiment of this paper, the model is trained under two different conditions, and the performance is evaluated across six different problem *** the proposed model against greedy algorithms and genetic algorithms, the results demonstrate that the proposed model has significant advantages in overall performance. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Prescribed-Time Clusters Flocking for Multi-agent systems of UAVs and USVs 6

Prescribed-Time Clusters Flocking for Multi-Agent Systems of...

引用

6th International Conference on Electronic Engineering and Informatics, EEI 2024

作者： Shang, Hanjun Wang, Zhenhuan Tian, Yingxin Hou, Qimin Kuang, Jiyuan Gao, Yabin School of Astronautics Harbin Institute of Technology Harbin150001 China Elite Engineers School Harbin Institute of Technology Harbin150001 China The National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing100074 China School of Software Harbin Institute of Technology Harbin150001 China

ISBN: (纸本)9798350353594

This paper deals with the problem of clusters flocking for a heterogeneous multi-agent system of Unmanned Aerial Vehicles (UAVs) and Unmanned Surface Vessels (USVs). The dynamics models of the UAVs and USVs are established separately. Due to the different state dimensions and dynamics models of the UAVs and USVs, the two types of agents are formulated with two clusters. Then, the functions of formation errors of the two clusters are constructed. For the two clusters, a new type of prescribed-time formation control laws is designed respectively. Moreover, compared with the conventional formation control that can only ensure that the multi-agent system completes ideal formations without strict time constraints theoretically, the present prescribed-time control laws can enable the multi-agent system to complete ideal formation strictly at a prescribed time independent of initial formation errors. Finally, the effectiveness of the prescribed-time formation control is verified by simulations. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Magnetic Microrobots Fabricated by Photopolymerization and Assembly

引用

Cyborg and Bionic systems 2023年第1期4卷 41-46页

作者： Xiyue Liang Yue Zhao Dan Liu Yan Deng Tatsuo Arai Masaru Kojima Xiaoming Liu Key Laboratory of Biomimetic Robots and Systems Ministry of EducationState Key Laboratory of Intelligent Control and Decision of Complex SystemBeijing Advanced Innovation Center for Intelligent Robots and Systemsand School of Mechatronical EngineeringBeijing Institute of TechnologyBeijing 100081China Center for Neuroscience and Biomedical Engineering The University of Electro-CommunicationsTokyo 182-8585Japan Department of Materials Engineering Science Osaka UniversityOsaka 560-8531Japan

Magnetic soft microrobots have great potential to access narrow spaces and conduct multiple tasks in the biomedical *** now,drug delivery,microsurgery,disease diagnosis,and dredging the blocked blood vessel have been realized by magnetic soft microrobots in vivo or in ***,as the tasks become more and more complex,more functional units have been embedded in the body of the developed magnetic *** magnetic soft microrobots with complex designed geometries,mechanisms,and magnetic orientation are now greatly challenging the fabrication of the magnetic *** this paper,we propose a new method combining photopolymerization and assembly for the fabrication of magnetic soft *** the micro-hand assembly system,magnetic modules with different shapes and materials are firstly arrayed with precise position and orientation ***,the developed photopolymerization system is employed to fix and link these modules with soft *** on the proposed fabrication method,3 kinds of soft magnetic microrobots were fabricated,and the fundamental locomotion was *** believe that the presented fabrication strategy could help accelerate the clinical application of magnetic microrobots.

关键词： Magnetic system precise

来源：评论

学校读者我要写书评

暂无评论

Leader-follower Formation control for a Multi-missile system via Deep Reinforcement Learning

Leader-follower Formation Control for a Multi-missile System...

引用

Chinese control and Decision Conference, CCDC

作者： Jianfeng Li Keyuan Yu Shenmin Song Center for Control Theory and Guidance Technology School of Astronautics Harbin Institute of Technology Harbin China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

The methods for the formation tracking control problem are mainly based on nonlinear control theories. Usually, the control effect of such methods heavily depends on an accurate control model and a lot of controller parameters need to be selected properly. To cope with these shortcomings, a novel reinforcement learning-based formation controller is proposed for a leader-follower multi-missile system. The deep deterministic policy gradient (DDPG) algorithm is implemented to generate the formation control signals. An interaction environment containing a leader and a follower is formulated, in which a model-free optimal control policy is obtained by a training process. The convergent actor-network is tested for a multi-missile system. Simulation results show that the formation control objective can be rapidly achieved in spite of the change of leader maneuvers. There is no need to change the hyperparameters of the policy for different kinds of formation scenarios, which shows great advantages over the conventional nonlinear control theory-based methods in terms of parameter selection.

关键词： Training Three-dimensional displays Target tracking Simulation Heuristic algorithms Process control Optimal control

来源：评论

学校读者我要写书评

暂无评论

A Generic Anti-Windup Design Under Linear Active Disturbance Rejection control Scheme

A Generic Anti-Windup Design Under Linear Active Disturbance...

引用

Electrical, Automation and Computer Engineering (ICEACE), International Conference on

作者： Li Hui Xu Cheng Ji Hua Yin Zhide Hu Wanhai Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China The 3rd Research Academy of CASIC Beijing China

A generic anti-windup compensation strategy under Linear Active Disturbance Rejection control scheme is proposed. The difference, between the controller output and the actuator output, after multiplied by a tunable parameter, together with controller output, is fed back to the extended state observer to compensate controller windup. While windup problem arises in control system, the controller output is expectedly produced, and the disadvantageous influence of nonlinearity on closed-loop dynamics is distinctly alleviated. The approach is employed to a near space vehicle with fin-deflection saturation. The numerical simulations show that the proposed approach has the better effectiveness in active disturbance rejection control designed situation than some previous anti-windup compensation strategy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：