检索结果-内蒙古大学图书馆

Management-Oriented Operating systems: Harnessing the Power of DAOs and Foundation Models

学校读者我要写书评

暂无评论

Management-Oriented Operating Systems: Harnessing the Power ...

2023 IEEE International Conference on systems, Man, and cybernetics, SMC 2023

作者： Qin, Rui Li, Juanjuan Liang, Xiaolong Wang, Fei-Yue Institute of Automation State Key Laboratory of Multimodal Artificial Intelligence Systems Chinese Academy of Sciences Beijing100190 China Macau University of Science and Technology Faculty of Innovation Engineering Macau999078 China Institute of Automation The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9798350337020

This paper presents Management-Oriented Operating systems (M2OS) that leverages the power of parallel intelligence theory, Decentralized Autonomous Organizations (DAOs) and foundation models to revolutionize the manner of management in cyber-Physical-Social systems (CPSS). The parallel architecture on M2OS is proposed, including the parallel interactive actual M2OS and artificial M2OS. Among them, the artificial M2OSs provide digital infrastructures for organizations to operate, collaborate, and make decisions in the virtual space, and conduct computational experiments to evaluate management decisions and predict future states of the actual M2OS. Through parallel execution and closed-loop feedback between the artificial and actual M2OSs, the management and control, experimentation and evaluation, as well as learning and training of the actual M2OS can be realized. Moreover, the functional layers of M2OS, including the infrastructure layer, data layer, scenario layer, modeling layer, decision layer, and application layer, are discussed. These layers work together to support the intelligent, autonomous, collaborative, and adaptive nature of the M2OS, and facilitate data-driven decision-making, optimize business operations, and empower managers with real-time actionable insights. The proposed M2OS paradigm has great potential to transform the management paradigm and opens up new possibilities for intelligent and collaborative decision-making. © 2023 IEEE.

关键词： cyber-physical-social systems Decentralized Autonomous Organizations foundation models management-oriented operating systems parallel intelligence

A Monocular Biological Simultaneous Localization and Mapping Method Based on a Bionic Vision Model

学校读者我要写书评

暂无评论

A Monocular Biological Simultaneous Localization and Mapping...

Frontiers of Robotics and Software Engineering (FRSE), International Conference on

作者： Sitong Guo Yu Zhang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Key Laboratory of Collaborative sensing and autonomous unmanned systems of Zhejiang Province Hangzhou China

Animals can navigate robustly through large unknown environments, utilizing inaccurate sensor and egomotion cues. Inspired by the mechanism of the human visual system, this paper presents a biological simultaneous localization and mapping (SLAM) system based on a monocular vision sensor to perform navigation tasks in complex environments. Specifically, our contributions are two folds: an improved monocular visual odometry with a scale recovery algorithm to calibrate the estimated robot pose, and a bionic vision model based on image enhancement algorithm and feature extraction approach to detect closed-loop. Experiments on public datasets demonstrate that our proposed method performs competitively in illumination-varying scenarios indoors and outdoors, which achieve a trade-off to maintain performances in terms of accuracy, execution time, and robustness.

关键词：

From RAG/RAT to SAGE: Parallel Driving for Smart Mobility

学校读者我要写书评

暂无评论

IEEE Transactions on Intelligent Vehicles 2024年第5期9卷 4821-4825页

作者： Fei-Yue Wang Wuhan Institute of Industrial Innovation and Development Wuhan China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

The current issue includes 2 perspectives, 2 letters, and 12 regular papers. These perspectives explore critical issues within the field of IVs and pontential research directions based on the evolution of foundation m... 详细信息

关键词： Intelligent vehicles

Building Supporting SLAM Community for IEEE TIV: From DHWs to Smart Academic Organizations

学校读者我要写书评

暂无评论

IEEE Transactions on Intelligent Vehicles 2024年第7期9卷 5119-5123页

作者： Fei-Yue Wang Wuhan Institute of Industrial Innovation and Development Hubei China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

I would like to share with you the following information

关键词： Simultaneous localization and mapping Intelligent vehicles Buildings Organizations

From RAG/RAT to SAGE for Social Transportation: A CoT and New Perspective on Smart Logistics and Mobility

学校读者我要写书评

暂无评论

IEEE Transactions on Intelligent Vehicles 2024年第6期9卷 5005-5008页

作者： Fei-Yue Wang Wuhan Institute of Industrial Innovation and Development Hubei China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Dear All

关键词： Intelligent vehicles Transportation Logistics

The Autonomous Right of Way: Smart Governance for Smart Mobility With Intelligent Vehicles

学校读者我要写书评

暂无评论

IEEE Transactions on Intelligent Vehicles 2024年第8期9卷 5243-5246页

Steps Toward Industry 5.0:Building“6S”Parallel Industries With cyber-Physical-Social Intelligence

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2023年第8期10卷 1692-1703页

作者： Xingxia Wang Jing Yang Yutong Wang Qinghai Miao Fei-Yue Wang Aijun Zhao Jian-Ling Deng Lingxi Li Xiaoxiang Na Ljubo Vlacic School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China IEEE Macao University of Science and Technology Macao 999078China Beijing Engineering Research Center of Intelligent Systems and Technology Chinese Academy of SciencesBeijing 100098 State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China North Automatic Control Technology Institute Taiyuan 030006China China Huaneng Group Co. Ltd.Beijing 100031China Department of Electrical and Computer Engineering Indiana University-Purdue University Indianapolis(IUPUI)IndianapolisIN 46202 USA Department of Engineering University of CambridgeCambridgeCB21PZUK School of Engineering and Built Environment Griffith UniversityGold CoastQLD 4222Australia

Very recently,intensive discussions and studies on Industry 5.0 have sprung up and caused the attention of researchers,entrepreneurs,and policymakers from various sectors around the ***,there is no consensus on why and what is Industry 5.0 *** this paper,we define Industry 5.0from its philosophical and historical origin and evolution,emphasize its new thinking on virtual-real duality and human-machine interaction,and introduce its new theory and technology based on parallel intelligence(PI),artificial societies,computational experiments,and parallel execution(the ACP method),and cyber-physical-social systems(CPSS).Case studies and applications of Industry 5.0 over the last decade have been briefly summarized and analyzed with suggestions for its future *** believe that Industry 5.0 of virtual-real interactive parallel industries has great potentials and is critical for building smart *** are outlined to ensure a roadmap that would lead to a smooth transition from CPS-based Industry 4.0 to CPSS-based Industry 5.0 for a better world which is Safe in physical spaces,S ecure in cyberspaces,Sustainable in ecology,Sensitive in individual privacy and rights,Service for all,and Smartness of all.

关键词： ACP artificial intelligence CPS CPSS Industry 4.0 Industry 5.0 parallel industries parallel intelligence

Adaptive Parametric Impedance Model Order Reduction Method for Grid-tied Renewable Energy Dominated Microgrid

学校读者我要写书评

暂无评论

Adaptive Parametric Impedance Model Order Reduction Method f...

2024 International Exhibition and Conference for Power Electronics, Intelligent Motion, Renewable Energy and Energy Management, PCIM Asia 2024

作者： Jiang, Xun Mao, Meiqin Xie, Bao Chang, Liuchen Wang, Haijiao Research Center for Photovoltaic System Engineering of Ministry of Education Hefei University of Technology China University of New Brunswick Canada State Key Laboratory of Operation and Control of Renewable Energy & Storage Systems China Electric Power Research Institute China

ISBN: (纸本)9783800764150

The high-precision reduced order impedance model can significantly reduce the computation burden in the small-signal oscillatory instability detection process of grid-tied renewable energy dominated microgrids (REMGs). However, due to improper interpolation strategies, the existing model order reduction method cannot build the high-precision parametric reduced order impedance model (PROIM) for REMG. To fill these gaps, this paper proposes the adaptive parametric model order reduction method to build a high-precision PROIM for REMGs. In this method, the adaptive optimization of system parameters and frequency interpolation points is achieved by introducing the evaluation indexes including convergence error, cumulative error, and projection matrix rank. The error performance of the obtained PROIM by the proposed method and its efficiency in actual oscillatory stability analysis are validated by a small-scale REMG with 4 different converter-based renewable generators (CREGs) and a real-time simulation model using a large-scale REMG of 4.2 MW with 18 different CREGs. © VDE VERLAG GMBH.

关键词： Microgrids

Robust Robot control Policy Learning Based on Gaussian Mixture Variational Autoencoders

学校读者我要写书评

暂无评论

Robust Robot Control Policy Learning Based on Gaussian Mixtu...

2024 China Automation Congress, CAC 2024

作者： Dong, Qingwei Zeng, Peng Zang, Chuanzhi Wan, Guangxi Dong, Xiaoting Cui, Shijie State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Shenyang University of Technology Shenyang110870 China

ISBN: (纸本)9798350368604

Reinforcement learning methods have demonstrated advanced capabilities in training neural network controllers for specific tasks. In the industrial domain, where model discrepancies and state disturbances occur, robot control strategies must exhibit adaptability. Existing studies, such as Generative Motor Reflexes (GMR), employ Variational Autoencoders (VAE) to approximate the latent variable space distribution to a standard normal distribution. However, this method, while straightforward, offers limited capability in representing data. The Gaussian Mixture Variational Autoencoder (GMVAE) algorithm leverages a Gaussian Mixture Model (GMM) as the prior distribution for data generation, enhancing the representation of the original state distribution. To increase the robustness of the trained neural network controllers against unknown states, we utilize GMVAE to represent the original state space, subsequently learning the mapping from latent variables to actions. We further accelerate the policy search process by integrating state representation learning with Guided Policy Search (GPS) methods. Our method was evaluated on robotic reaching tasks. Experimental results validate the robustness of our method against state perturbations. © 2024 IEEE.

关键词： Normal distribution