检索结果-内蒙古大学图书馆

Deep Behavioral Cloning for Traffic control with Virtual Expert Demonstration Under a Parallel Learning Framework ⁎

IFAC-PapersOnLine 2020年第5期53卷 176-181页

作者： Xiaoshuang Li Fenghua Zhu Fei-Yue Wang State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100080 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing 100049 China

Intelligent traffic signal control is necessary for improving traffic efficiency. These fast changing and challenging traffic scenarios and demands are generally handled by professional traffic engineers. However, it may take years of time and thousands of practices to train such an engineer. This paper proposes a deep behavioral cloning method to learn how to control the traffic signal effectively and efficiently from virtual expert demonstration. The method imitates promising working behavior of optimized offline solutions, and applies it to solve online traffic signal control problems of the similar scenario. Different traffic demand patterns are generated through a combination of different kinds of components. Then the virtual demonstration is constructed by getting an exclusive and optimized solution for each generated virtual traffic demand pattern through a heuristic random search method. After that, a deep neural network-based behavioral cloning method is employed to learn from the virtual demonstration and finish on-line traffic signal control task. The experimental results show that compared with other methods, the proposed method significantly reduces the waiting time and time loss in different situations. And the average traffic speed of the road network at different saturation levels can be improved by 1.58% to 11.54%.

关键词： intelligent transportation system behavioral cloning virtual demonstration parallel learning

来源：评论

学校读者我要写书评

暂无评论

A Self-identifying Checkerboard-like Pattern for Camera Calibration

A Self-identifying Checkerboard-like Pattern for Camera Cali...

引用

Chinese control Conference (CCC)

作者： Zhang Gao Mingzhu Zhu Junzhi Yu School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory for Turbulence and Complex Systems Peking University Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

This paper proposes a new type of planar pattern for camera calibration featuring its checkerboard-like structure and self-identity. White and black blocks are arranged by a novel method to ensure the uniqueness of each local pattern, and meanwhile maintain all checkerboard corners. The pattern is generated by combining identification units based on a random search strategy. Positions of local patterns can be acquired by searching the global pattern, achieving the benefit of self-identity. Because of the checkerboard-like structure, no burden is introduced in sampling compared to traditional calibrations. Experimental results show the effectiveness of the proposed calibration method. The conceived pattern is especially suitable for the calibration of multi-camera system with limited overlapping scope.

关键词： Calibration Feature extraction Cameras Search problems Visualization complex systems Electronic mail

来源：评论

学校读者我要写书评

暂无评论

The Multi-Blockchain Based Data Trading Markets with Novel Pricing Mechanisms

SSRN

引用

SSRN 2022年

作者： Li, Juanjuan Li, Junqing Wang, Xiao Qin, Rui Yuan, Yong Wang, Fei-Yue The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China Qingdao Academy of Intelligent Industries Qingdao266109 China School of Mathematics Renmin University of China Beijing100872 China Macao Institute of Systems Engineering Macau University of Science and Technology 999078 China

Aiming to deal with the challenge of data security and data pricing in data trading markets, we propose the novel multi-blockchain-based framework and design the related pricing mechanisms. Specifically, data recording and trading are conducted separately in the Data Blockchain (DChain) and the Value Blockchain (VChain). Based on these blockchains, two-layer data trading markets are established to manage the initial data trading in the primary market and the data resale in the secondary market. Pricing mechanisms are proposed to protect the formulated data trading markets against strategic trading behaviors and balance the payoffs of both suppliers and users. In the regular data trading on VChain-S2D, two auction models are used to deal with users' strategic bidding in terms of the demand scale, where the incentive-compatible Vickrey-Clarke-Groves (VCG) model is dedicated to the low-demand trading scenario, while the nearly incentive-compatible Monopolistic Price (MP) model is for the high-demand trading scenario. In the temporary data trading on VChain-D2S, a reverse auction mechanism named Two-Stage Obscure Selection (TSOS) is designed to regulate both suppliers' quoting and users' valuation strategies. Moreover, experiments are carried out to validate our theoretical analysis. Our work is expected to enhance the data security and improve the trading efficiency. © 2022, The Authors. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Real-Time Marker Localization Learning for GelStereo Tactile Sensing

arXiv

引用

arXiv 2022年

作者： Liu, Shujuan Cui, Shaowei Zhang, Chaofan Cai, Yinghao Wang, Shuo The University of Science and Technology Beijing China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Institute of Automation Chinese Academy of Sciences Beijing100190 China The Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China

Visuotactile sensing technology is becoming more popular in tactile sensing, but the effectiveness of the existing marker detection/localization methods remains to be further explored. Instead of contour-based blob detection, this paper presents a learning-based marker localization network for GelStereo visuotactile sensing called Marknet. Specifically, the Marknet presents a grid regression architecture to incorporate the distribution of the GelStereo markers. Furthermore, a marker rationality evaluator (MRE) is modelled to screen suitable prediction results. The experimental results show that the Marknet combined with MRE achieves 93.90% precision for irregular markers in contact areas, which outperforms the traditional contour-based blob detection method by a large margin of 42.32%. Meanwhile, the proposed learning-based marker localization method can achieve better real-time performance beyond the blob detection interface provided by the OpenCV library through GPU acceleration, which we believe will lead to considerable perceptual sensitivity gains in various robotic manipulation tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Parallel Distance: A New Paradigm of Measurement for Parallel Driving

引用

IEEE/CAA Journal of Automatica Sinica 2020年第4期7卷 1169-1178页

作者： Teng Liu Hong Wang Bin Tian Yunfeng Ai Long Chen the Vehicle Intelligence Pioneers Inc. Qingdao 266109 the Department of Automotive Engineering Chongqing UniversityChongqing 400044China the Mechanical and Mechatronics Engineering Department Waterloo UniversityN2L 3G1Canada the State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China the School of Data and Computer Science Sun Yat-sen UniversityGuangzhou 510006China

In this paper, a new paradigm named parallel distance is presented to measure the data information in parallel driving system. As an example, the core variables in the parallel driving system are measured and evaluated in the parallel distance framework. First, the parallel driving 3.0 system included control and management platform, intelligent vehicle platform and remote-control platform is introduced. Then,Markov chain(MC) is utilized to model the transition probability matrix of control commands in these systems. Furthermore, to distinguish the control variables in artificial and physical driving conditions, different distance calculation methods are enumerated to specify the differences between the virtual and real signals. By doing this, the real system can be guided and the virtual system can be im-proved. Finally, simulation results exhibit the merits and multiple applications of the proposed parallel distance framework.

关键词： Artificial and physical system parallel distance parallel driving 3.0 parallel system rotational and accelerator signal

来源：评论

学校读者我要写书评

暂无评论

Evolution and Neural Representation of Mammalian Cooperative Behavior

SSRN

引用

SSRN 2021年

作者： Jiang, Mengping Wang, Miaoyaoxin Shi, Qianqian Wei, Lei Lin, Yongqin Wu, Dingcheng Liu, Boyi Nie, Xiupeng Qiao, Hong Xu, Lin Yang, Tianming Wang, Zuoren Institute of Neuroscience State Key Laboratory of Neuroscience CAS Center for Excellence in Brain Science &Intelligence Technology Chinese Academy of Sciences Shanghai200031 China Key Laboratory of Animal Models and Human Disease Mechanisms and Laboratory of Learning and Memory Kunming Institute of Zoology Chinese Academy of Sciences KunmingYunnan650223 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Cooperation is common in nature and has been pivotal to the development of human society. However, the details of how and why cooperation evolved remain poorly understood. Cross-species investigation of cooperation may help to elucidate the evolution of cooperative strategies. Thus, we designed a novel cooperative behavioral paradigm and quantitatively examined the cooperative abilities and strategies of mice, rats, and tree shrews. We found that social communication played a key role in the establishment of new cooperation, and that increased cooperative ability and a more efficient cooperative strategy emerged as a function of the evolutionary hierarchy of the tested species. We also found neural representations of distinct aspects of cooperation in the brains of rats through in vivo electrophysiological recording. Cooperation-preferential signals were identified in addition to material reward-preferential signals, each of which may represent internal drives for cooperation. © 2021, The Authors. All rights reserved.

关键词： Rats

来源：评论

学校读者我要写书评

暂无评论

Acupoint Detection Based on Deep Convolutional Neural Network

Acupoint Detection Based on Deep Convolutional Neural Networ...

引用

Chinese control Conference (CCC)

作者： Lingyao Sun Shiying Sun Yuanbo Fu Xiaoguang Zhao State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China The Department of Acupuncture and Moxibustion Capital Medical University Beijing Key Laboratory of Acupuncture Neuromodulation Beijing China

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

As an important component of Traditional Chinese Medicine (TCM), science of acupoint therapy has achieved significant results in clinical practice, but recognizing and positioning acupoints is heavily depends on the skills of practitioners. In recent years, researchers have proposed a few methods of automatic acupoints detection and positioning, but most of the methods are still based on manual designed features. In this paper, we propose an acupoints detection method based on deep convolutional neural network, and an evaluation method is proposed for acupoint detection. What's more, we build an acupoint detection dataset. Experiments are performed and a promising result is achieved.

关键词： 5G mobile communication

来源：评论

学校读者我要写书评

暂无评论

Internet of Mind with General Intelligent Dispatch in Electrical Industrial: The Concept, Framework, Technology, and Future

Internet of Mind with General Intelligent Dispatch in Electr...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Tianlu Gao Xiaoyan Gong Shiqian Ma Weichen Wang Xiaojing Yang Jian Wang The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Science Beijing China Power Dispatching and Control center State Grid Tianjin Electric Power Company Tianjin China

ISBN: (数字)9781728176840

ISBN: (纸本)9781728176857

This paper proposes the concept of general intelligent dispatch, which is a novel framework of electrical power dispatch based on modern artificial intelligence (AI). The general intelligent dispatch system is based on knowledge automation, parallel system, ACP method, and fully integrated with cutting-edge technologies such as parallel deep learning, parallel dynamics programming. The general intelligent dispatch system is devised to be a comprehensive framework that can support the applications of various modern AI technologies in electrical power dispatch. General intelligent dispatch can accommodate the rapid development of the future smart grid, especially the extensive implementation of distributed energy resources and renewable energy. General intelligent dispatch also provides the practical technical path and framework for the future smart power dispatch services to achieve a higher level of automation and intelligence. Based on the general intelligent dispatch concept, this paper addresses power grid situational awareness, which provides an example for the applications of general intelligent dispatch.

关键词： Automation Optimal scheduling Real-time systems Dispatching Smart grids Artificial intelligence Business

来源：评论

学校读者我要写书评

暂无评论

The Application of Artificial Intelligence in Energy Internet

The Application of Artificial Intelligence in Energy Interne...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Zhigang Huang Tianlu Gao Xiaoyan Gong Qian Li Wenzhong Gao Power Dispatching and Control Center State Grid Tianjin Electric Power Company Tianjin China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Science Beijing China

ISBN: (数字)9781728176840

ISBN: (纸本)9781728176857

The energy internet is a cyber-physical system (CPS) to connect directly and indirectly the devices of information, communication, control, and protection to effectively generate, transmit, use, and store various energy by merging new technologies such as artificial intelligence (AI), cloud computing, and blockchain, etc. Recently, AI technology has become increasingly popular in many research and industrial fields because it can perform tasks well. However, applying AI technologies to energy internet is relatively less. Therefore, in this paper, the potential applications of AI technologies in the energy internet will be reviewed and discussed. In section II and section III, the operating and monitoring of power systems are the main parts to discuss. Firstly, applying AI technologies to the operation of control, optimization, and decision-making in power systems will be detailed in section II from three aspects such as existing problems, potential demands, and valuable improvement. Secondly, in section III, detecting faults and analyzing stability by energy internet monitoring is mainly discussed. Finally, in section IV, it shows an example using the neural network to analyze the power flow of a standard IEEE 39 nodes power system compared with traditional Newton-Raphson method.

关键词： Decision making Power system stability Stability analysis Power grids Artificial intelligence Monitoring Optimization

来源：评论

学校读者我要写书评

暂无评论

Design of a robotic fish based on a passive flexible mechanism

Design of a robotic fish based on a passive flexible mechani...

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Lu, Ben Fu, Yuzhuo Zou, Qianqian Deng, Sai Zhou, Chao Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728163215

In recent years, along with the rapid development of manufacturing, control, sensing and other technologies, biomimetic robotic fish has played an increasingly important role in marine exploration, underwater rescue, water quality monitoring and other fields. This paper designed a robotic fish based on a passive flexible mechanism to realize the fish-like propulsion function. The motion simulation of the designed transmission mechanism was carried out to get the actual curve of the structure. Through the analysis of the force of the fishtail, the preliminary selection scheme of the elastic joints based on the passive flexible mechanism was obtained. Finally, this paper built a robotic fish based on a passive flexible mechanism, which could achieve the motion frequency adjustable from 0.5 to 9 Hz, and the maximum swimming speed reaching 1.05 BL/s (BL, body length). This design scheme provided a new reference for the design of the biomimetic robotic fish and had certain practical significance. © 2019 IEEE.

关键词： Fish

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：