检索结果-内蒙古大学图书馆

IEEE International Conference on systems, Man and Cybernetics

作者： Yulong Ding Bin Xin Hao Zhang Jie Chen School of Automation Beijing Institute of Technology Beijing China Peng Cheng Laboratory Shenzhen China Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing China

ISBN: (数字)9781728185262

ISBN: (纸本)9781728185279

This paper addresses a UAV path planning problem for a team of cooperating heterogeneous vehicles composed of one unmanned aerial vehicle (UAV) and multiple unmanned ground vehicles (UGVs). The UGVs are used as mobile actuators and scattered in a large area. To achieve multi-UGV communication and collaboration, the UAV serves as a messenger to fly all UGVs to transmit information. The path planning of messenger UAV is formulated as a Dynamic Dubins Traveling Salesman Problem with Neighborhood (DDTSPN). A novel memetic algorithm is proposed to find the shortest route enabling the UAV to fly over all requested UGVs. In the memetic algorithm, the combination of genetic algorithm and local search is employed to find a high-quality solution in a reasonable time, and a gradient-based repair strategy is used to repair the individuals violating dynamic constraints. The calculation results on both small and large instances show that the proposed method can generate high-quality solutions as compared with the state-of-the-art algorithms.

关键词： Memetics Heuristic algorithms Maintenance engineering Traveling salesman problems Unmanned aerial vehicles Path planning Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Evasion strategies of a three-player lifeline game

引用

Science China(Information Sciences) 2018年第11期61卷 144-154页

作者： Fan ZHANG 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

This study examines a multi-player pursuit-evasion game, more specifically, a three-player lifeline game in a planar environment, where a single evader is tasked with reaching a lifeline prior to capture. A decomposition method based on an explicit policy is proposed to address the game qualitatively from two main aspects:(1) the evader's position distribution to guarantee winning the game(i.e., the escape zone),which is based on the premise of knowing the pursuers' positions initially, and(2) evasion strategies in the escape zone. First, this study decomposes the three-player lifeline game into two two-player sub-games and obtains an analytic expression of the escape zone by constructing a barrier, which is an integration of the solutions of two sub-games. This study then explicitly partitions the escape zone into several regions and derives an evasion strategy for each region. In particular, this study provides a resultant force method for the evader to balance the active goal of reaching the lifeline and the passive goal of avoiding capture. Finally,some examples from a lifeline game involving more than one pursuer are used to verify the effectiveness and scalability of the evasion strategies.

关键词： lifeline game three-player pursuit-evasion game barrier evasion strategy game of kind

来源：评论

学校读者我要写书评

暂无评论

Adaptive RBF Neural Network control Method for Pneumatic Position Servo system ⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 8826-8831页

作者： Hai-Peng Ren Shan-Shan Jiao Xuan Wang Jie Li Shaanxi Key Laboratory Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an China School of Electrical Engineering Xi’an University of Technology Xi’an China

With the development of control theory and the pneumatic element, the application of pneumatic systems has attracted more attention because of the performance to price ratio improvement. Despite of these, there are still challenge to deal with the nonlinearity of the system, the uncertainty of the parameters, the input saturation and the unknown control direction in the tracking control of pneumatic system. In this paper, the nonlinearity and model uncertainty are treated with adaptive radial basis function neural network (RBFNN), meanwhile, the unknown control direction and input saturation are dealt with the Nussbaum function and Gauss error function, respectively. The stability of the designed controller is proved by Lyapunov theory. Finally, the experimental and comparison results show the effectiveness and superiority of the proposed method.

关键词： Pneumatic system RBFNN unknown model parameters unknown control direction input saturation

来源：评论

学校读者我要写书评

暂无评论

Image Fusion based on Variational Method for Maintenance of Gradient and Intensity

Image Fusion based on Variational Method for Maintenance of ...

引用

第三十九届中国控制会议

作者： Jinglan Bai Liping Yan Yuanqing Xia Bo Xiao Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of Technology School of Artificial Intelligence Beijing University of Posts and Telecommunications

Infrared and visible image fusion technology helps to improve the spatial resolution. It mainly preserves the features and details of the source images and generates a fusion image with visual enhancement. In this paper, based on the gradient features and intensity information of the source images, an optimization model for image fusion is built. Firstly, the pre-fused gradient of the source images is obtained by combining the structure tensor and the proposed local gradient similarity, where local gradient similarity is used to make the fused gradient direction more accurately. Secondly, the source images are reconstructed into salient and non-salient images according to the comparison of the pixel intensity. A weight map before the non-salient image in the optimization model makes the effective details preserved, so that the pre-fused images consist of the salient image and the non-salient image with a weight map. Finally, an optimization model is constructed to constrain the gradient and intensity of the final fused image close to the pre-fused gradient and the pre-fused images. The final fused image is obtained from solving the optimization model by use of the variational method. The experimental results are evaluated from subjective and objective assessments, which show the effectiveness of the proposed algorithm.

关键词： Image Fusion Structure Tensor Variational Method Gradient Domain

来源：评论

学校读者我要写书评

暂无评论

Online reinforcement learning control by direct heuristic dynamic programming: from time-driven to event-driven

arXiv

引用

arXiv 2020年

作者： Zhao, Qingtao Si, Jennie Sun, Jian Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing100081 China Department of Electrical Computer and Energy Engineering Arizona State University TempeAZ85287 United States

In this paper time-driven learning refers to the machine learning method that updates parameters in a prediction model continuously as new data arrives. Among existing approximate dynamic programming (ADP) and reinforcement learning (RL) algorithms, the direct heuristic dynamic programming (dHDP) has been shown an effective tool as demonstrated in solving several complex learning control problems. It continuously updates the control policy and the critic as system states continuously evolve. It is therefore desirable to prevent the time-driven dHDP from updating due to insignificant system event such as noise. Toward this goal, we propose a new event-driven dHDP. By constructing a Lyapunov function candidate, we prove the uniformly ultimately boundedness (UUB) of the system states and the weights in the critic and the control policy networks. Consequently we show the approximate control and cost-to-go function approaching Bellman optimality within a finite bound. We also illustrate how the event-driven dHDP algorithm works in comparison to the original time-driven dHDP. Copyright © 2020, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Multi-UAV 3D Path Planning in Simultaneous Attack

Multi-UAV 3D Path Planning in Simultaneous Attack

引用

International Conference on control and Automation (ICCA)

作者： Chuyi Xiong Bin Xin Miao Guo Yulong Ding Hao Zhang School of Automation Beijing Institute of Technology Beijing China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing China

ISBN: (数字)9781728190938

ISBN: (纸本)9781728190945

As the key technology of UAV mission planning, path planning has a very important impact on the combat effectiveness of UAV. In order to destroy enemy units, multiple UAVs are often needed to attack the target at the same time. In the complex combat environment, the path planning of multiple UAVs is a very complex problem. On the basis of genetic algorithm, this paper designs a path planning algorithm to ensure that multiple UAVs arrive at the same time from different angles on the premise of satisfying environment constraints and the motion constraints of UAV. The algorithm uses the method of regionalization to initialize the path, designs a reasonable fitness function, and adds an adaptive disturbance operator to plan the path of each UAV. Finally, the length difference between the paths planned for each UAV is taken as the path evaluation factor. Some of the paths are replanned to achieve the goal of the same path length and simultaneous attack by UAV. The effectiveness of the algorithm is verified by experiments in typical combat scenarios, and the superiority of the adaptive disturbance operator in the optimization of the algorithm is verified by the contrast experiment.

关键词： Path planning Radar Planning Optimization Radar detection Genetic algorithms Three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Model analysis and experimental research on hydraulic high-speed impact system 8

Model analysis and experimental research on hydraulic high-s...

引用

8th IEEE International Conference on Fluid Power and Mechatronics, FPM 2019

作者： Wang, Shoukun Shi, Mingxin Chen, Zhihua Beijing Institute of Technolog Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing China Key Laborator Yof Servo Motion System Drive and Control Ministry of Industry and Information Technology School of Automation Beijing Institute of Technology Beijing China

ISBN: (数字)9781728103112

ISBN: (纸本)9781728103112

High-speed impact simulation test is an important test method to study the fatigue properties or limit parameters of materials. With the advantages of great impact energy, good program control and convenient test operation, hydraulic impact is widely used in high-speed impact field. A hydraulic high speed impact simulation system is designed in this paper, which uses high pressure accumulator to supply oil and converts hydraulic energy into impact energy through servo valve controlled cylinder system. This system can simulate dynamic change process of impact velocity and acceleration of projectile, and has impact angle adjustment and end buffer function. First, the composition and working principle of this hydraulic impact simulation system is introduced, as well as the analysis of the hydraulic impact mechanism. Second, the system dynamics model of servo valve controlled cylinder based on accumulator oil is built, and the simplified model and its basic characteristics are analyzed. Then, the Influences of various parameters in impact dynamic model on impact process are also discussed. Finally, the simulation system and physical prototype system of hydraulic impact is presented, the simulation and actual impact test data and corresponding analysis conclusions are also given. © 2019 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Fault-tolerant sampled-data synchronization of Markovian jumping complex dynamical networks via looped-functional approach

Fault-tolerant sampled-data synchronization of Markovian jum...

引用

International Symposium on Autonomous systems (ISAS)

作者： Wang Xin Sun Jian Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing China

ISBN: (纸本)9781728112992

In this paper, the issue of sampled-data synchronization of Markovian jumping complex dynamical networks with sensor fault is investigated. Here, we utilize looped-functional approach to constructed Lyapunov functional with more information about r(t k ) and r(t k+1 ), which has contribution to decrease the conservatism of stability condition. Then, we design a sampled-data controller for Markovian jumping complex dynamical networks. Finally, the feasibility and superiority of our method are proved by several numerical and simulation examples.

关键词： complex networks control system synthesis fault tolerant control Lyapunov methods Markov processes network theory (graphs) sampled data systems stability synchronisation sampled data system fault-tolerant control control system synthesis Lyapunov methods Markov chain complex networks data synchronization Jumping Data sampling

来源：评论

学校读者我要写书评

暂无评论

Further results on mixed H∞ and passive sampled-data synchronization of complex dynamical networks via looped-functional approach

Further results on mixed H∞ and passive sampled-data synchr...

引用

International Symposium on Autonomous systems (ISAS)

作者： Wang Xin Sun Jian Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing China

ISBN: (纸本)9781728112992

This paper investigates the issue of H ∞ and passive sampled-data synchronization of delayed complex dynamical networks. By taking more information about r(t k ) and r(t k+1 ) into account, which has contribution to decrease the conservatism of stability condition, a novel Lyapunov-Krasovskii looped-functional is constructed. Then, we design a H ∞ and passive sampled-data controller for complex dynamical networks. Finally, the feasibility and superiority of our method are proved by several numerical and simulation examples.

关键词： complex networks control system synthesis delays H∞ control Lyapunov methods sampled data systems stability synchronisation sampled data system control system synthesis Lyapunov methods complex networks Data sampling data synchronization delay Conservatism

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：