检索结果-内蒙古大学图书馆

Long and Short-Term Constraints Driven Safe Reinforcement Learning for Autonomous Driving

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hu, Xuemin Chen, Pan Wen, Yijun Tang, Bo Chen, Long School of Artificial Intelligence Hubei University Wuhan430062 China Key Laboratory of Intelligent Sensing System and Security Hubei University Ministry of Education Hubei Wuhan430062 China Department of Electrical and Computer Engineering Worcester Polytechnic Institute WorcesterMA01609 United States State Key Laboratory of Multimodal Artificial Intelligence Systems State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing100190 China WAYTOUS Inc. Beijing100083 China Shenzhen518107 China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi’an710049 China

Reinforcement learning (RL) has been widely used in decision-making and control tasks, but the risk is very high for the agent in the training process due to the requirements of interaction with the environment, which seriously limits its industrial applications such as autonomous driving systems. Safe RL methods are developed to handle this issue by constraining the expected safety violation costs as a training objective, but the occurring probability of an unsafe state is still high, which is unacceptable in autonomous driving tasks. Moreover, these methods are difficult to achieve a balance between the cost and return expectations, which leads to learning performance degradation for the algorithms. In this paper, we propose a novel algorithm based on the long and short-term constraints (LSTC) for safe RL. The short-term constraint aims to enhance the shortterm state safety that the vehicle explores, while the long-term constraint enhances the overall safety of the vehicle throughout the decision-making process, both of which are jointly used to enhance the vehicle safety in the training process. In addition, we develop a safe RL method with dual-constraint optimization based on the Lagrange multiplier to optimize the training process for end-to-end autonomous driving. Comprehensive experiments were conducted on the MetaDrive simulator. Experimental results demonstrate that the proposed method achieves higher safety in continuous state and action tasks, and exhibits higher exploration performance in long-distance decision-making tasks compared with state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Lagrange multipliers

On the convergence of step decay step-size for stochastic optimization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Xiaoyu Magnússon, Sindri Johansson, Mikael The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology StockholmSE-100 44 Sweden Department of Computer and System Science Stockholm University Stockholm Sweden

The convergence of stochastic gradient descent is highly dependent on the step-size, especially on non-convex problems such as neural network training. Step decay step-size schedules (constant and then cut) are widely used in practice because of their excellent convergence and generalization qualities, but their theoretical properties are not yet well understood. We provide the convergence results for step decay in the non-convex regime, ensuring that the gradient norm vanishes at an (Formula presented) rate. We also provide the convergence guarantees for general (possibly non-smooth) convex problems, ensuring an (Formula presented) convergence rate. Finally, in the strongly convex case, we establish an (Formula presented) rate for smooth problems, which we also prove to be tight, and an (Formula presented) rate without the smoothness assumption. We illustrate the practical efficiency of the step decay step-size in several large scale deep neural network training tasks. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

Society 5.0: Metaverse Facilitated Human-centric “5H” Services Across Cyber-Physical-Social Spaces

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2024年第3期58卷 159-164页

作者： Xiao Wang Jun Huang QingHua Ni Zhe Wan HuaDan Xue Larry Stapleton Fei-Yue Wang Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education Anhui University Hefei 230601 China Macau University of Science and Technology Macau 999078 China Beijing Normal University Beijing 100875 China Department of Radiology Peking Union Medical College Hospital Shuaifuyuan Beijing 100730 Dongcheng District China Brownsbarn Thomastown Co. Kilkenny Ireland R95D8P2 Qingdao Academy of Intelligent Industries Qingdao 266109 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China

Cyber-Physical-Social systems bridge the gap between social resource organization and distribution, and give birth to Society 5.0, which represents a transformative vision aimed at realizing the human-centric paradigm for more efficient and effective sustainable development. In this paper, we discuss the decentralized paradigm in fostering human needs-driven smart services, in line with Maslow’s hierarchy of needs theory. Societies 5.0 is committed to optimizing the use of natural, artificial, and social resources by enhancing democratic participation and ensuring that decision-making processes are more transparent, reliable, and aligned with the needs of the populace in sustainable ways. Moreover, our discussion extends to how Society 5.0’s principles correlate with the United Nations Sustainable Development Goals (SDGs), providing a framework that supports health, education, and poverty reduction, among other targets. This approach also aligns with the Human Development Index (HDI), reinforcing the notion that technological progress in Society 5.0 does not overshadow but rather complements and enhances human values, paving a synergistic path towards sustainable development that is both advanced and fundamentally human-centric.

关键词： Cyber-Physical-Social systems Society 5.0 Human-Centric Services Socio-technical synergistic sustainable development

Spatial-nonlocality-induced non-Markovian electromagnetically induced transparency in a single giant atom

学校读者我要写书评

暂无评论

Physical Review A 2022年第4期106卷 043710-043710页

作者： Y. T. Zhu S. Xue R. B. Wu W. L. Li Z. H. Peng M. Jiang Department of Automation Shanghai Jiao Tong University Shanghai 200240 People's Republic of China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 People's Republic of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai 200240 People's Republic of China Center for Intelligent and Networked Systems Department of Automation Tsinghua University Beijing 100084 People's Republic of China Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education Key Laboratory for Matter Microstructure and Function of Hunan Province Department of Physics and Synergetic Innovation Center for Quantum Effects and Applications Hunan Normal University Changsha 410081 People's Republic of China School of Electronics and Information Engineering Soochow University Suzhou 215006 People's Republic of China

The nonlocal waveguide coupling of giant atoms can bring up novel physics and applications. In this paper, we find unconventional electromagnetically induced transparency in giant atoms that has not been reported so far. We present a consistent theory for describing the unconventional EIT which includes a real-space scattering method and a time-delayed master equation. Our analysis shows this phenomenon is a full quantum effect led by a quantized interaction between the atom and the waveguide. Our theory shows that it can be observed when the time delay between two neighboring coupling points is comparable to the relaxation time of the atom. This phenomenon results from the inherent nonlocality of the giant atom, which physically forces propagating fields to be standing waves in space and the atom exhibiting retardations in time.

关键词： Quantum optics with artificial atoms Scattering theory Quantum master equation

Simultaneously Calibration of Multi Hand-Eye Robot system Based on Graph

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Zishun Ma, Liping Liu, Xilong Cao, Zhiqiang Yu, Junzhi The Institute of Automation Chinese Academy of Sciences Beijing100190 China The College of Electrical Engineering and Computer Science Australian National University Canberra2601 Australia 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 The State Key Laboratory for Turbulence and Complex System Department of Advanced Manufacturing and Robotics BIC-ESAT College of Engineering Peking University Beijing100871 China

Precise calibration is the basis for the vision-guided robot system to achieve high-precision operations. systems with multiple eyes (cameras) and multiple hands (robots) are particularly sensitive to calibration errors, such as micro-assembly systems. Most existing methods focus on the calibration of a single unit of the whole system, such as poses between hand and eye, or between two hands. These methods can be used to determine the relative pose between each unit, but the serialized incremental calibration strategy cannot avoid the problem of error accumulation in a large-scale system. Instead of focusing on a single unit, this paper models the multi-eye and multi-hand system calibration problem as a graph and proposes a method based on the minimum spanning tree and graph optimization. This method can automatically plan the serialized optimal calibration strategy in accordance with the system settings to get coarse calibration results initially. Then, with these initial values, the closed-loop constraints are introduced to carry out global optimization. Simulation experiments demonstrate the performance of the proposed algorithm under different noises and various hand-eye configurations. In addition, experiments on real robot systems are presented to further verify the proposed method. © 2023, CC BY-SA.

关键词： Multipurpose robots

State Estimation for Integrated Energy systems: Motivations, Advances, and Future Work

学校读者我要写书评

暂无评论

IEEE Transactions on Power systems 2024年

作者： Zhao, Junbo Srivastava, Ankur Guo, Ye Cetenovic, Dragan Lin, Yuzhang Levi, Victor Yin, Guanxiong Huang, Manyun Zhang, Tingting Li, Zhigang Chen, Yanbo Exposito, Antonio G. Zhang, Wen Zheng, Weiye Chakrabarti, Saikat Li, Yang Sharma, Ankush Kamwa, Innocent Guo, Qinglai Terzija, Vladimir Mili, Lamine University of Connecticut Department of Electrical and Computer Engineering StorrsCT06269 United States Tsinghua University Tsinghua-Berkeley Shenzhen Institute Shenzhen518055 China The University of Manchester Department of Eee ManchesterM13 9PL United Kingdom University of Kragujevac Faculty of Technical Sciences Čačak Čačak32000 Serbia New York University Department of Electrical and Computer Engineering NY11201 United States Tsinghua University Department of Electrical Engineering Beijing100084 China Hohai University College of Energy and Electrical Engineering Nanjing210098 China Shandong University Key Laboratory of Power System Intelligent Dispatch and Control Ministry of Education Jinan250061 China The Chinese University of Hong Kong-Shenzhen School of Science and Engineering Shenzhen518172 China North China Electric Power University School of Electrical and Electronic Engineering Beijing102206 China University of Sevilla Spain Sevilla41092 Spain South China University of Technology School of Electrical Power Engineering Guangzhou510641 China Indian Institute of Technology Kanpur Department of Electrical Engineering Kanpur208016 India Northeast Electric Power University School of Electrical Engineering Jilin132012 China Laval University Department of Electrical and Computer Engineering QuebecQCG1V 0A6 Canada Tsinghua University State Key Laboratory of Power Systems Department of Electrical Engineering Beijing100084 China Newcastle University School of Engineering Newcastle upon TyneNE1 7RU United Kingdom Virginia Polytechnic Institute and State University Bradley Department of Electrical and Computer Engineering Falls ChurchVA22043 United States

This paper summarizes the technical activities of a three-year-long IEEE Task Force (TF) on State Estimation (SE) for Integrated Energy systems (IES). It presents the formal definition and characteristics of IES, along with the comprehensive discussion on Electric Power systems (EPS) model, and static and dynamic models associated with heating and natural gas systems. The paper also identifies the barriers of SE for IES, such as estimation modeling, observability analysis, and measurement requirements, together with addressing multi-scale dynamics. An extensive comparative analysis between Integrated Energy systems-State Estimation (IES-SE) and more established Electric Power system-State Estimation (EPS-SE) is presented. The paper also provides future research needs and directions related to IES-SE. © 1969-2012 IEEE.

关键词： Power system analysis

Milestones in Autonomous Driving and Intelligent Vehicles Part I: control, Computing system Design, Communication, HD Map, Testing, and Human Behaviors

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Long Li, Yuchen Huang, Chao Xing, Yang Tian, Daxin Li, Li Hu, Zhongxu Teng, Siyu Lv, Chen Wang, Jinjun Cao, Dongpu Zheng, Nanning Wang, Fei-Yue The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Waytous Ltd. China BNU-HKBU United International College Zhuhai519087 China Hong Kong Baptist University Kowloon999077 Hong Kong The Department of Industrial and System Engineering Hong Kong Polytechnical University Hong Kong The School of Aerospace Transport and Manufacturing Cranfield University United Kingdom The School of Transportation Science and Engineering Beihang University China The Department of Automation Tsinghua University China The Department of Mechanical and Aerospace Engineering Nanyang Technological University Singapore The College of Artificial Intelligence Xi'an Jiaotong University China The School of Mechanical Engineering Tsinghua University China

Interest in autonomous driving (AD) and intelligent vehicles (IVs) is growing at a rapid pace due to the convenience, safety, and economic benefits. Although a number of surveys have reviewed research achievements in this field, they are still limited in specific tasks and lack systematic summaries and research directions in the future. Our work is divided into 3 independent articles and the first part is a Survey of Surveys (SoS) for total technologies of AD and IVs that involves the history, summarizes the milestones, and provides the perspectives, ethics, and future research directions. This is the second part (Part I for this technical survey) to review the development of control, computing system design, communication, High Definition map (HD map), testing, and human behaviors in IVs. In addition, the third part (Part II for this technical survey) is to review the perception and planning sections. The objective of this paper is to involve all the sections of AD, summarize the latest technical milestones, and guide abecedarians to quickly understand the development of AD and IVs. Combining the SoS and Part II, we anticipate that this work will bring novel and diverse insights to researchers and abecedarians, and serve as a bridge between past and future. Copyright © 2023, The Authors. All rights reserved.

关键词： Autonomous vehicles

Planning of active power distribution network based on source-network-load collaborative optimization 16

学校读者我要写书评

暂无评论

Planning of active power distribution network based on sourc...

16th IET International Conference on AC and DC Power Transmission, ACDC 2020

作者： Jiang, Zhicheng Yu, Qingguang Li, Ang Xiong, Yufeng Long, Gaoxiang Liu, Yuming Key Laboratory of Modern Power System Simulation and Control and Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China State Key Laboratory of Power Systems Department of Electrical Engineering Tsinghua University Beijing China

ISBN: (纸本)9781839533914

With the fast development of renewable energy generation, the randomness and volatility seriously threaten the stability of the power system. In order to improve the consumption rate of renewable energy and the economic benefit, the source-network-load collaborative optimization is put forward and widely used in the power system. And the active power distribution network which consists of the energy storage devices and flexible load is the best carrier to realize it. Based on the active power distribution network planning, this paper firstly designs an economic index covering construction cost and operation cost as the optimization objective. Then with the physical constraints consisting of the physical features of generation units, energy storage devices and flexible load, the source-network-load collaborative optimization model of active power distribution network is established. Finally, a case of city distribution network is presented to verify the effect of source-network-load collaborative optimization and the efficiency of the optimization model. © 2020 Institution of engineering and Technology. All rights reserved.

关键词： Optimization

MPC Performances for Nonlinear systems Using Several Linearization Models

学校读者我要写书评

暂无评论

MPC Performances for Nonlinear Systems Using Several Lineari...

American control Conference

作者： Yusuke Igarashi Masaki Yamakita Jerry Ng H. Harry Asada Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo Japan Department of System and Control Engineering Tokyo Institute of Technology Tokyo Japan Department of Mechanical Engineering Massachusetts Institute of Technology Massachusetts USA

ISBN: (数字)9781538682661

ISBN: (纸本)9781538682678

It is now well known that dynamics of nonlinear systems can be lifted to higher or infinite dimensional spaces and represented as linear systems. We call such linear system representations and approximations, 'lifting linear' representations. Once we have such a linear system representation, we can apply linear control theorems to the previous nonlinear systems. The behavior of the lifting linear system are closer to the original systems than those of Taylor series approximations. In this paper, we compare performances of MPC (Model Predictive control) for nonlinear systems using several different approximated linear models. When the systems are represented as linear systems, MPC can be solved by convex quadratic optimization methods if the constraints are linear. It will be shown that computational times become much shorter and the optimality of the solutions are improved using particular lifting linearizations.

关键词： Linear system lift lifts Taylor series Optimization methods optimality Linearization computational time closer