检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Chen, Xingyu Yu, Junzhi Kong, Shihan Wu, Zhengxing Fang, Xi Wen, Li University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Mechanical Engineering and Automation Beihang University Beijing100191 China

Underwater machine vision has attracted significant attention, but its low quality has prevented it from a wide range of applications. Although many different algorithms have been developed to solve this problem, real-time adaptive methods are frequently deficient. In this paper, based on filtering and the use of generative adversarial networks (GANs), two approaches are proposed for the aforementioned issue, i.e., a filteringbased restoration scheme (FRS) and a GAN-based restoration scheme (GAN-RS). Distinct from previous methods, FRS restores underwater images in the Fourier domain, which is composed of a parameter search, filtering, and enhancement. Aiming to further improve the image quality, GAN-RS can adaptively restore underwater machine vision in real time without the need for pretreatment. In particular, information in the Lab color space and the dark channel is developed as loss functions, namely, underwater index loss and dark channel prior loss, respectively. More specifically, learning from the underwater index, the discriminator is equipped with a carefully crafted underwater branch to predict the underwater probability of an image. A multi-stage loss strategy is then developed to guarantee the effective training of GANs. Through extensive comparisons on the image quality and applications, the superiority of the proposed approaches is confirmed. Consequently, the GAN-RS is considerably faster and achieves a state-of-the-art performance in terms of the color correction, contrast stretch, dehazing, and feature restoration of various underwater scenes. The source code will be made available. Copyright © 2017, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Design and dynamic analysis for Amoeba-like roboţs turning-mechanism applied with spring and damp system

Design and dynamic analysis for Amoeba-like roboţs turning-...

引用

2016 International Conference on Advanced Robotics and Mechatronics, ICARM 2016

作者： Dong, Xiang Sun, Henghui Wang, Zengfu Cheng, Long Institute of Intelligent Machines Chinese Academy of Sciences Hefei230031 China State Key Lab. of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9781509033645

A new turning-mechanism for Amoeba-like Robot was proposed in this paper, which based on the amoeba-like robot kinematics characteristics of tail contracting and skin flipping. First, one kind of variable-speed node composed of the spring and damp was designed. Because of the existing of the variable-speed nodes, the velocities of the two strip-skins depended not only on the velocities of threads that gone through the variable-speed nodes, but also on the spring and damp it contained. So, although the velocities of threads that induced the velocities of the strip-skins were the same, the velocities of the strip-skins still can be different since the variable-speed nodes existed. That difference in velocities made the turning movement possible. Second, the dynamic model for the turning movement of the Amoeba-like Robot was established and analyzed. The analysis results included the angular velocity and angle curve related to time, which were computed with the dynamic model when shortening speed of threads length was constant. The results achieved in this paper provided an important basic for the research on the behaviors and control strategy of amoeba-like robot. The new turning-mechanism can be popularized to the tracked mobile robot, for it provided a new and available turning method. © 2016 IEEE.

关键词： Velocity

来源：评论

学校读者我要写书评

暂无评论

Data-Based Robust control for Unknown Nonlinear systems 35

Data-Based Robust Control for Unknown Nonlinear Systems

引用

第35届中国控制会议

作者： YANG Xiong LIU Derong WEI Qinglai School of Electrical Engineering and Automation Tianjin University School of Automation and Electrical Engineering University of Science and Technology Beijing The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

ISBN: (纸本)9781509009107

In this paper, we develop a data-based robust control method for a class of unknown nonlinear systems with input constraints. First, we transform the robust control problem into a constrained optimal control problem by introducing a value function for the nominal system. Then, under the framework of integral reinforcement learning, we construct an actor-critic architecture to approximately solve the constrained optimal control problem. Based on the present architecture, we only require system data rather than the availability of full/partial prior knowledge of system dynamics. In addition, by using Lyapunov's direct method, we prove that the obtained approximate optimal control can guarantee the unknown nonlinear system to be uniformly ultimately bounded. Finally, we provide an example to illustrate the effectiveness of the developed method.

关键词： Constrained input Integral reinforcement learning Nonlinear systems Optimal control Robust control

来源：评论

学校读者我要写书评

暂无评论

7.3: Compare Variation of User's EEG Owing to Parallax Cue

引用

SID Symposium Digest of Technical Papers 2018年第S1期49卷

作者： Haichen Hu Danli Wang Kang Yue Xinpan Yang Steve C. Chiu Beijing Key Lab of Human-Computer Interaction Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China The State Key Laboratory of Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China College of Science and Engineering Idaho State University Pocatello America

3D display has become increasingly popular in many fields. It can provide incredible immersion compared with 2D display. There are many researches referring to the change of user about no matter subjective experience or objective physiology signal while watching 3D content. Similarly, in this paper, we study the variation of user’s EEG when the user watched 3D content. However, we only focus on parallax cue and avoid other cues of 3D content by using Random Dot Stereogram(RDS) as visual stimulus. We designed an experiment which asked the subject to watch RDS with nine kinds of parallaxes(0,±0.5,±1.1,±1.3,±1.7). The users watched one RDS for 1 minute and then closed eyes and rest for 1 minute every time. During watching, EEG signal with 30-channel was recorded. The result suggests that significant variation of the user’s EEG data occurred in the Alpha (8–13Hz) and Beta(14–30Hz) frequency band by different parallax’s comparison. And we found not only parallax but also electrode position can impact the user’s EEG data significantly. Accurately, the EEG data has a significant change in six electrodes position in both frequency bands including CZ, PZ, OZ, O2 in international 10–20 system. It means those electrode positions we detect can be regarded as typical positions where we record EEG signal. It will simplify the process of EEG signal acquisition when we need to study the relationship between parallax cue of 3D display and the user further.

关键词： EEG Parallax RDS 3D

来源：评论

学校读者我要写书评

暂无评论

Distributed Consensus Tracking control for Multiple Simple-Pendulum Network systems 35

Distributed Consensus Tracking Control for Multiple Simple-P...

引用

第35届中国控制会议

作者： JIANG Yulian WANG Shenquan LI Yuanchun LIU Derong College of Electrical and Electronic Engineering Changchun University of Technology The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences School of Automation and Electrical Engineering University of Science and Technology Beijing

ISBN: (纸本)9781509009107

This paper investigates the consensus tracking problem for networked control systems consisting of multiple simplependulums driven by corresponding DC motors.A distributed adaptive consensus control algorithm is developed to guarantee the state tracking for each simple-pendulum with nonlinear *** dynamic model of networked simple-pendulums driven by DC motors is obtained first,and the mathematical description of consensus tracking control problem for multi-agent system is ***,fully distributed consensus tracking protocol without any global information is designed by using adaptive control technology to adjust the coupling weights between neighboring ***,simulation results demonstrate the effectiveness of the proposed consensus tracking control algorithm.

关键词： consensus tracking simple-pendulum network system adaptive control nonlinear dynamics multi-agent system

来源：评论

学校读者我要写书评

暂无评论

面向CPG驱动的仿生机器鱼容错控制方法

引用

Engineering 2018年第6期 253-269页

作者：杨越麒王健吴正兴喻俊志 State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences University of the Chinese Academy of Sciences

容错性能对于自推进仿生机器鱼在实际水下应用中的可操作性和生存能力至关重要。本文探讨了具有多个可活动关节和一个被卡住尾部关节的自由游动机器鱼的容错控制问题。提出的控制系统主要由两个部分组成:反馈控制器和前馈补偿器。具体而... 详细信息

容错性能对于自推进仿生机器鱼在实际水下应用中的可操作性和生存能力至关重要。本文探讨了具有多个可活动关节和一个被卡住尾部关节的自由游动机器鱼的容错控制问题。提出的控制系统主要由两个部分组成:反馈控制器和前馈补偿器。具体而言,一方面,设计了基于生物启发中心模式发生器的反馈控制器用于使机器鱼对外部干扰具有鲁棒性;另一方面,引入了基于动力学模型的前馈补偿器来加速整个控制系统的收敛。在此基础上,开展了仿真实验来完成控制系统分析和故障机器鱼游动性能验证。最后,水下实验表明,所提出的容错控制方法能够有效调整故障机器鱼,使其能够在故障情况下完成所需运动,进而提高实际机器鱼系统的稳定性和寿命。

关键词：容错控制机器鱼运动控制反馈控制器前馈补偿器

来源：评论

学校读者我要写书评

暂无评论

A Navigation Map Building Algorithm using Refined RBPF-SLAM

A Navigation Map Building Algorithm using Refined RBPF-SLAM

引用

2016 IEEE Chinese Guidance, Navigation and control Conference (IEEE CGNCC2016)

作者： Mengyin Fu Hao Zhu Yi Yang Meiling Wang Zhihong Deng State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institution of Technology

ISBN: (纸本)9781467383196

This paper proposes a map building algorithm for navigation task of autonomous vehicle.A local 2D grid map is designed to convey three types of information(free space,obstacle and unknown).A refined RBPF-SLAM algorithm is established to build a large scale,accurate navigation *** obstacle information is excluded in the final map,which provides better performance in vehicle's online *** sets of experiments are carried out in two driving conditions,with one in urban traffic environment and the other in unstructured *** mapping and localization result testify the effectiveness of our algorithm.

关键词： frame A Navigation Map Building Algorithm using Refined RBPF-SLAM

来源：评论

学校读者我要写书评

暂无评论

Policy iteration optimal tracking control for chaotic systems by using an adaptive dynamic programming approach

引用

Chinese Physics B 2015年第3期24卷 87-94页

作者：魏庆来刘德荣徐延才 The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

A policy iteration algorithm of adaptive dynamic programming（ADP） is developed to solve the optimal tracking control for a class of discrete-time chaotic systems. By system transformations, the optimal tracking problem is transformed into an optimal regulation one. The policy iteration algorithm for discrete-time chaotic systems is first described. Then,the convergence and admissibility properties of the developed policy iteration algorithm are presented, which show that the transformed chaotic system can be stabilized under an arbitrary iterative control law and the iterative performance index function simultaneously converges to the optimum. By implementing the policy iteration algorithm via neural networks,the developed optimal tracking control scheme for chaotic systems is verified by a simulation.

关键词： adaptive critic designs adaptive dynamic programming approximate dynamic programming neuro-dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Adaptive critic designs for solving event-based H∞ control problems

Adaptive critic designs for solving event-based H∞ control ...

引用

American control Conference

作者： Ding Wang Chaoxu Mu Derong Liu The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China the School of Electrical and Information Engineering Tianjin University Tianjin 300072 China the School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing 100083 China

ISBN: (纸本)9781509045839

In this paper, the adaptive critic method is applied to solve a class of continuous-time event-based H_∞ control problems. The present control problem is transformed into a two-player zero-sum differential game and the adaptive critic structure is employed for coping with the event-based minimax optimization. Next, the event-based optimal feedback control and the time-based worst-case disturbance law are learned by training a critic neural network. In addition, the closed-loop system is constructed with stability analysis of the critic error dynamics and the sampled-data plant. The exclusion of the infamous Zeno behavior of the present event-based control design is also discussed. Finally, the control performance of the present approach is evaluated through simulation study.

关键词： exclusion infamous Zeno exclusion critic Event-based Data sampling control performance design control

来源：评论

学校读者我要写书评

暂无评论

A TDC-based nano-scale displacement measure method inside scanning electron microscopes

A TDC-based nano-scale displacement measure method inside sc...

引用

2016 IEEE International Conference on Robotics and Biomimetics, ROBIO 2016

作者： Zhou, Chao Wang, Yu Deng, Lu Wu, Zhengxing Cao, Zhiqiang Wang, Shuo Tan, Min State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Statistics and Mathematics Central University of Finance and Economics Beijing100080 China

ISBN: (纸本)9781509043644

The one of the most important foundations of micro-manipulation is the micro- and nano- displacement's accurate measurement. This paper focused on the end effectors measurement for a nano-manipulation robot, which is working in the scanning electron microscope's vacuum chamber. A standard capacitor are charged and discharged through the strain gauge, and the time are measured by time-digital convertor, which can be used to calculate the displacement. The power consumption are analyzed and compared with traditional Wheatstone bridge. The power consumption is greatly reduced while the error is optimized, so it takes advantages in the environment of vacuum, which is hard to dissipate heat. The drift, resolution and linearity are tested, and demos of closed-loop control and repeated micro unit probing are given to verify the validity of this method. © 2016 IEEE.

关键词： Electric power utilization

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：