检索结果-内蒙古大学图书馆

Generative Adversarial Networks:Introduction and Outlook

IEEE/CAA Journal of Automatica Sinica 2017年第4期4卷 588-598页

作者： Kunfeng Wang Chao Gou Yanjie Duan Yilun Lin Xinhu Zheng Fei-Yue Wang IEEE State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Qingdao Academy of Intelligent Industries State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences University of Chinese Academy of Sciences Department of Computer Science and Engineering University of Minnesota Research Center for Computational Experiments and Parallel Systems Technology National University of Defense Technology

Recently, generative adversarial networks(GANs)have become a research focus of artificial intelligence. Inspired by two-player zero-sum game, GANs comprise a generator and a discriminator, both trained under the adversarial learning *** goal of GANs is to estimate the potential distribution of real data samples and generate new samples from that *** their initiation, GANs have been widely studied due to their enormous prospect for applications, including image and vision computing, speech and language processing, etc. In this review paper, we summarize the state of the art of GANs and look into the future. Firstly, we survey GANs' proposal background,theoretic and implementation models, and application ***, we discuss GANs' advantages and disadvantages, and their development trends. In particular, we investigate the relation between GANs and parallel intelligence,with the conclusion that GANs have a great potential in parallel systems research in terms of virtual-real interaction and integration. Clearly, GANs can provide substantial algorithmic support for parallel intelligence.

关键词： ACP approach adversarial learning generative adversarial networks(GANs) generative models parallel intelligence zero-sum game

来源：评论

学校读者我要写书评

暂无评论

controlling the depth of a gliding robotic dolphin using dual motion control modes

引用

Science China(Information Sciences) 2020年第9期63卷 217-230页

作者： Jian WANG Zhengxing WU Min TAN Junzhi YU State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences University of Chinese Academy of Sciences State Key Laboratory for Turbulence and Complex System Department of Mechanics and Engineering ScienceBIC-ESAT College of Engineering Peking University

This paper investigates the performance of the dual mode, namely flipper mode and central pattern generator(CPG) mode, for controlling the depth of a gliding robotic dolphin. Subsequent to considering the errors in dynamic models, we propose a depth control system that combines the line-of-sight(LOS)method with an adaptive control approach(ACA) to deal with uncertainties in the model parameters. First,we establish a full-state dynamic model to conduct simulations and optimize the parameters used in later aquatic experiments. Then, we use the LOS method to transform the control target from the depth to the pitch angle and employ the ACA to calculate the control signal. In particular, we optimize the ACA’s control parameters using simulations based on our dynamic model. Finally, our simulated and experimental results demonstrate not only that we can successfully control the robotic dolphin’s depth, but also that its performance was better than that of the CPG-based control, thus indicating that we can achieve three-dimensional motion by combining flipper-based and CPG-based control. The results of this study suggest valuable ideas for practical applications of gliding robotic dolphins.

关键词： gliding robotic dolphin depth control dual motion adaptive control approach

来源：评论

学校读者我要写书评

暂无评论

Speed and Accuracy Tradeoff for LiDAR Data Based Road Boundary Detection

引用

IEEE/CAA Journal of Automatica Sinica 2021年第6期8卷 1210-1220页

作者： Guojun Wang Jian Wu Rui He Bin Tian State Key Laboratory of Automotive Simulation and Control Jilin UniversityChangchun 130022China State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the Qingdao Academy of Intelligent Industries ShandongChina

Road boundary detection is essential for autonomous vehicle localization and decision-making,especially under GPS signal loss and lane *** road boundary detection in structural environments,obstacle occlusions and large road curvature are two significant ***,an effective and fast solution for these problems has remained *** solve these problems,a speed and accuracy tradeoff method for LiDAR-based road boundary detection in structured environments is *** proposed method consists of three main stages:1)a multi-feature based method is applied to extract feature points;2)a road-segmentation-line-based method is proposed for classifying left and right feature points;3)an iterative Gaussian Process Regression(GPR)is employed for filtering out false points and extracting boundary *** demonstrate the effectiveness of the proposed method,KITTI datasets is used for comprehensive experiments,and the performance of our approach is tested under different road *** experiments show the roadsegmentation-line-based method can classify left,and right feature points on structured curved roads,and the proposed iterative Gaussian Process Regression can extract road boundary points on varied road shapes and traffic ***,the proposed road boundary detection method can achieve real-time performance with an average of 70.5 ms per frame.

关键词： 3D-LiDAR autonomous vehicle object detection point cloud road boundary

来源：评论

学校读者我要写书评

暂无评论

Parallel Transportation management and control System and Its Applications in Building Smart Cities

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2016年第6期17卷 1576-1585页

作者： Zhu, Fenghua Li, Zhenjiang Chen, Songhang Xiong, Gang Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Advancements in complexity, complex systems, and the intelligence sciences, particularly smart city technologies, have shown great potential in aiding to ease traffic congestion. The overall approach and the main ideas in building smart transportation for smart cities, particularly ACP (artificial system, computational experiment, and parallel execution)-based parallel transportation management and control systems (PTMS), are presented. PTMS can be expanded to the new generation of intelligent transportation systems. The main components of the proposed architecture include social signal and social traffic, ITS clouds and services, agent-based traffic control, and transportation knowledge automation. Some technical details of these components are discussed. Finally, one case study is introduced, and the effectiveness is analyzed.

关键词： Intelligent transportation systems (ITS) artificial system computational experiment and parallel execution (ACP) approach parallel transportation management and control system (PTMS) computational experiment ITS cloud social transportation transportation knowledge automation

来源：评论

学校读者我要写书评

暂无评论

Feature correspondence based on directed structural model matching

引用

IMAGE AND VISION COMPUTING 2015年 33卷 57-67页

作者： Yang, Xu Qiao, Hong Liu, Zhi-Yong Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Feature correspondence lays the foundation for many tasks in computer vision and pattern recognition. In this paper the directed structural model is utilized to represent the feature set, and the correspondence problem is then formulated as the structural model matching. Compared with the undirected structural model, the proposed directed model provides more discriminating ability and invariance against rotation and scale transformations. Finally, the recently proposed convex-concave relaxation procedure (CCRP) is generalized to approximately solve the problem. Extensive experiments on synthetic and real data witness the effectiveness of the proposed method. (C) 2014 Elsevier B.V. All rights reserved.

关键词： Feature correspondence Directed structural model Graph matching

来源：评论

学校读者我要写书评

暂无评论

GNCCP-Graduated NonConvexity and Concavity Procedure

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2014年第6期36卷 1258-1267页

作者： Liu, Zhi-Yong Qiao, Hong Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

In this paper we propose the graduated nonconvexity and concavity procedure (GNCCP) as a general optimization framework to approximately solve the combinatorial optimization problems defined on the set of partial permutation matrices. GNCCP comprises two sub-procedures, graduated nonconvexity which realizes a convex relaxation and graduated concavity which realizes a concave relaxation. It is proved that GNCCP realizes exactly a type of convex-concave relaxation procedure (CCRP), but with a much simpler formulation without needing convex or concave relaxation in an explicit way. Actually, GNCCP involves only the gradient of the objective function and is therefore very easy to use in practical applications. Two typical related NP-hard problems, partial graph matching and quadratic assignment problem (QAP), are employed to demonstrate its simplicity and state-of-the-art performance.

关键词： Combinatorial optimization graduated optimization deterministic annealing partial graph matching quadratic assignment problem

来源：评论

学校读者我要写书评

暂无评论

Coupled Multivehicle Detection and Classification With Prior Objectness Measure

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2017年第3期66卷 1975-1984页

作者： Yao, Yanjie Tian, Bin Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Vehicle recognition plays an important role in traffic surveillance systems, advanced driver-assistance systems, and autonomous vehicles. This paper presents a novel approach for multivehicle recognition that considers vehicle space location and classification as a coupled optimization problem. It can speed up the detection process with more accurate vehicle region proposals and can recognize multiple vehicles using a single model. The proposed detector is implemented in three stages: 1) obtaining candidate vehicle locations with prior objectness measure;2) classifying vehicle region proposals to distinguish the three common types of vehicles (i.e., car, taxi, and bus) by a single convolutional neural network (CNN);and 3) coupling classification results with the detection process, which leads to fewer false positives. In experiments on high-resolution traffic images, our method achieves unique characteristics: 1) It matches the state-of-the-art detection accuracy;2) it is more efficient in generating a smaller set of high-quality vehicle windows;3) its searching time is decreased by about 30 times compared with the other two popular detection schemes;and 4) it recognizes different vehicles in each image using a single CNN model with eight layers.

关键词： Convolutional neural network (CNN) multivehicle detection object proposals vehicle classification

来源：评论

学校读者我要写书评

暂无评论

Development of a Fast-Swimming Dolphin Robot Capable of Leaping

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2016年第5期21卷 2307-2316页

作者： Yu, Junzhi Su, Zongshuai Wu, Zhengxing Tan, Min Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

It remains a great challenge for a biomimetic dolphin robot to leap out of the water by reason of requirements for very high speed and exquisite motion control. In this paper, we estimate the minimum exit speed that allows the dolphin to completely leap out of the water, and for the first time, we build a self-contained leaping dolphin robot with commercially available actuators and power supply. To quantify the possible impact of the body length on the minimum exit speed during the leap, we employ a rigid bodymodel rather than a particle model to numerically evaluate the leaping process. Furthermore, a robotic prototype intended for leap motions is created, with particular emphasis on streamlining and high-thrust tail propulsive mechanism designs in conjunction with a passive control strategy for the dorsoventral propulsion. Underwater tests on the untethered dolphin robot demonstrate the effectiveness of the proposed methods and mechatronic designs. We found that the dolphin robot successfully performed leaps with a length-specific speed of over 2.3 body lengths per second, and an emergence angle ranging between 35 and 60 degrees.

关键词： Bioinspired robot control engineering dolphin robot leaping minimum exit speed

来源：评论

学校读者我要写书评

暂无评论

An efficient realization of deep learning for traffic data imputation

引用

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES 2016年 72卷 168-181页

作者： Duan, Yanjie Lv, Yisheng Liu, Yu-Liang Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

Traffic data provide the basis for both research and applications in transportation control, management, and evaluation, but real-world traffic data collected from loop detectors or other sensors often contain corrupted or missing data points which need to be imputed for traffic analysis. For this end, here we propose a deep learning model named denoising stacked autoencoders for traffic data imputation. We tested and evaluated the model performance with consideration of both temporal and spatial factors. Through these experiments and evaluation results, we developed an algorithm for efficient realization of deep learning for traffic data imputation by training the model hierarchically using the full set of data from all vehicle detector stations. Using data provided by Caltrans PeMS, we have shown that the mean absolute error of the proposed realization is under 10 veh/5-min, a better performance compared with other popular models: the history model, ARIMA model and BP neural network model. We further investigated why the deep leaning model works well for traffic data imputation by visualizing the features extracted by the first hidden layer. Clearly, this work has demonstrated the effectiveness as well as efficiency of deep learning in the field of traffic data imputation and analysis. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Traffic data imputation Deep learning Missing data

来源：评论

学校读者我要写书评

暂无评论

Discrete-time online learning control for a class of unknown nonaffine nonlinear systems using reinforcement learning

引用

NEURAL NETWORKS 2014年 55卷 30-41页

作者： Yang, Xiong Liu, Derong Wang, Ding Wei, Qinglai Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

In this paper, a reinforcement-learning-based direct adaptive control is developed to deliver a desired tracking performance for a class of discrete-time (DT) nonlinear systems with unknown bounded disturbances. We investigate multi-input-multi-output unknown nonaffine nonlinear DT systems and employ two neural networks (NNs). By using Implicit Function Theorem, an action NN is used to generate the control signal and it is also designed to cancel the nonlinearity of unknown DT systems, for purpose of utilizing feedback linearization methods. On the other hand, a critic NN is applied to estimate the cost function, which satisfies the recursive equations derived from heuristic dynamic programming. The weights of both the action NN and the critic NN are directly updated online instead of offline training. By utilizing Lyapunov's direct method, the closed-loop tracking errors and the NN estimated weights are demonstrated to be uniformly ultimately bounded. Two numerical examples are provided to show the effectiveness of the present approach. (C) 2014 Elsevier Ltd. All rights reserved.

关键词： Adaptive critic design Neural network Nonaffine nonlinear system Online learning Reinforcement learning

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：