检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Jiang, Xia Zeng, Xianlin Sun, Jian Chen, Jie Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China Ministry of Education Beijing100081 China School of Electronic and Information Engineering Tongji University Shanghai200082 China

This paper proposes a distributed stochastic algorithm with variance reduction for general smooth non-convex finite-sum optimization, which has wide applications in signal processing and machine learning communities. In distributed setting, large number of samples are allocated to multiple agents in the network. Each agent computes local stochastic gradient and communicates with its neighbors to seek for the global optimum. In this paper, we develop a modified variance reduction technique to deal with the variance introduced by stochastic gradients. Combining gradient tracking and variance reduction techniques, this paper proposes a distributed stochastic algorithm, GT-VR, to solve large-scale non-convex finite-sum optimization over multi-agent networks. A complete and rigorous proof shows that the GT-VR algorithm converges to first-order stationary points with O(k1) convergence rate. In addition, we provide the complexity analysis of the proposed algorithm. Compared with some existing first-order methods, the proposed algorithm has a lower O(PMΕ−1) gradient complexity under some mild condition. By comparing state-of-the-art algorithms and GT-VR in experimental simulations, we verify the efficiency of the proposed algorithm. © 2021, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

The 110kV Live-Maintaining Robot control System Design for Substation Equipment in complex Working Conditions

The 110kV Live-Maintaining Robot Control System Design for S...

引用

Chinese control Conference (CCC)

作者： Chenyu Hu Xin Chen Chengyu Li Guangxian Huang Cheng Zhou Xu Jian School of Automation China University of Geosciences Wuhan China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China School of Future Technology China University of Geosciences Wuhan China Distribution Department State Grid Hubei Electric Power Co. Ltd. Xianning Power Supply Company Xianning China Operations and Maintenance Department State Grid Hubei Electric Power Co. Ltd Xianning Xian'an District Power Supply Company Xianning China Equipment Technology Center State Grid Hubei Electric Power Co. Ltd. Electric Power Science Research Institute Wuhan China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China

Live-maintaining work is essential for continuous power supply to the substation. To improve the safety and efficiency of live-maintaining work, this paper proposes an equipotential live-maintaining robot system suitable for 110kV voltage levels. Considering the narrow space, complex working conditions and strong electromagnetic interference in substations, binocular vision technology, manipulator trajectory planning algorithm based on time-energy optimization, high voltage electromagnetic shielding technology are utilized to develop the system, and the live-maintaining robot is successfully applied in actual substation. By accurately identifying and locating the joint bolts and insulator, the robot system can achieve equipotential live-disassemble, live-assemble the joint bolts within 18 minutes and live-clean insulator within 5 minutes, demonstrating its the effectiveness and practicability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed proximal gradient algorithm for non-smooth non-convex optimization over time-varying networks

arXiv

引用

arXiv 2021年

This note studies the distributed non-convex optimization problem with non-smooth regularization, which has wide applications in decentralized learning, estimation and control. The objective function is the sum of different local objective functions, which consist of differentiable (possibly non-convex) cost functions and non-smooth convex functions. This paper presents a distributed proximal gradient algorithm for the non-smooth non-convex optimization problem over time-varying multi-agent networks. Each agent updates local variable estimate by the multi-step consensus operator and the proximal operator. We prove that the generated local variables achieve consensus and converge to the set of critical points with convergence rate O(1/T). Finally, we verify the efficacy of proposed algorithm by numerical simulations. © 2021, CC BY.

关键词： Time varying networks

来源：评论

学校读者我要写书评

暂无评论

Model Predictive control for Human Following Rehabilitation Robot

Model Predictive Control for Human Following Rehabilitation ...

引用

IEEE Workshop on advanced Robotics and its Social Impacts, ARSO

作者： Shihao Yan Jing Tao Jian Huang Anshun Xue the Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Ministry of Civil Affairs of the People's Republic of China National Research Center for Rehabilitation Technical Aids Beijing China the Beijing Advanced Innovation Center of Intelligent Robots and Systems Beijing China

A new type of rehabilitation robot that can follow the user side-by-side is designed for aiding the elderly and disabled. The Human Following Rehabilitation Robot (HFRR) consists of a metal armrest, a set of sensors and a differential mobile base. By predicting the user's speed in the future through the user's current walking speed and the preset path, the problem of human following side-by-side is converted to a problem of keeping a certain lateral distance from the predicted trajectory. Linearizing the tracking error model, the nonholonomic mobile robot (NMR) can maintain a certain lateral distance from the trajectory by using Model Predictive control (MPC) and then follow the user side-by-side. The simulation and experimental results show the proposed controller can obtain good performance in this problem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

A Feedback-based Print Quality Improving Strategy for FDM 3D Printing: An Optimal Design Approach

Research Square

引用

Research Square 2021年

作者： Tami, Tariku Sinshaw Xiong, Gang Fang, Qihang Dong, Xisong Shen, Zhen Wang, Fei-Yue The State Key Laboratory for Management and Control of Complex Systems Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan523808 China

Fused deposition modelling (FDM) 3D printing, as a supporting technology in social manufacturing and cloud manufacturing, is a rapidly growing technology in the era of industry 4.0. It produces objects with the layer-by-layer material accumulation technique. However, qualitative uncertainties are the common challenges yet. In order to assure print quality, studying the error causing parameters and minimizing their effects is important. This paper presents a feedback-based error compensation strategy, which integrates fuzzy inference system and grey wolf optimization algorithm. The objectives are twofold. First, the possible errors in FDM 3D printing are discussed in detail and optimal error causing parameters are obtained in percentage. This is used to understand the effects of the printing errors in every phase of the 3D printing process. From the nine optimization configuration trials used, Config-6 that has 100 number of iterations and 60 wolves is selected due to its higher convergence speed and best fitness value. The integral absolute error (IAE) is used as an objective function and the global minimum is achieved in the iteration interval [86, 100]. The outputs of this optimization problem is used to achieve the next objective. Second, a closed-loop quality monitoring approach comprising of inner-loops and an outer-loop is utilized. The three inner-loops are used to monitor the errors during pre-printing, printing, and post-printing, respectively. The outer-loop, on the other hand, is responsible for monitoring the aggregated errors in all the three 3D printing phases. The error compensation system simulation in Matlab is run for 10 seconds, and the results show that the "normal" range deformation factors are reached within less than 2 seconds for the inner-loops, whereas the outer-loop deformation factor is achieved within 7 seconds. The responses are within the acceptable time range. © 2021, CC BY.

关键词： 3D printers

来源：评论

学校读者我要写书评

暂无评论

Design of Simultaneous State and Unknown Input Filtering Algorithm for a Class of Nonlinear Stochastic systems with Multiple Sensors

Design of Simultaneous State and Unknown Input Filtering Alg...

引用

IEEE International Conference on Cloud Computing and Intelligence systems (CCIS)

作者： Zhibin Hu Jun Hu Cai Chen Junhua Du Department of Applied Mathematics Harbin University of Science and Technology Harbin China School of Automation Harbin University of Science and Technology Harbin China Heilongjiang Provincial Key Laboratory of Optimization Control and Intelligent Analysis for Complex Systems Harbin University of Science and Technology Harbin China College of Science Qiqihar University Qiqihar China

ISBN: (纸本)9781665456579

In this paper, we investigate the simultaneous state and unknown input (SUI) filtering issue for a class of multi-sensor networked systems (MSNSs). The unknown input with no prior knowledge is introduced in the system state and output. The focus of this paper is to design the local filters with regard to the SUI, which can yield that the local upper bounds of the filtering error covariance for the SUI are derived at each instant. Moreover, the local filter gains of the SUI are designed such that the obtained upper bounds can be minimized. Finally, the proposed joint SUI algorithm is verified by using the simulation example.

关键词： Cloud computing Upper bound Filtering Stochastic systems Computational modeling Filtering algorithms Forward error correction

来源：评论

学校读者我要写书评

暂无评论

Ordinal Optimization for Optimal Orientation Problems in 3D Printing

引用

IFAC-PapersOnLine 2020年第5期53卷 97-102页

作者： Can Luo Gang Xiong Zhishuai Li Zhen Shen Li Wan MengChu Zhou Fei-Yue Wang State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Donggguan China Ten Dimensions (Guangdong) Technology Co. Ltd. Foshan China Macau University of Science and Technology Taipa Macau

Compared with a traditional manufacturing process, 3D printing has advantages of performance and cost in personalized customization and has been applied in many fields. The problem of 3D model orientation optimization is a crucial one in practice. In this paper, based on the mathematical relationship between model orientation and printing time, surface quality, and supporting area, the model orientation problem is transformed into a multi-objective optimization problem with goal of minimizing printing time, surface quality, and supporting area. Ordinal Optimization (OO) is not only applicable to problems with random factors, but also to solve complex deterministic problems. The model orientation is a complex deterministic problem. We solve it with OO in this paper and use linear weighting to convert the multi-objective optimization problem into single-objective one. Finally, we compare the experimental results of solving 3D model orientation problems solved by OO and Genetic Algorithm (GA). The results show that OO requires less calculation time than GA while achieving comparable performance.

关键词： Digital Manufacturing Genetic Algorithm intelligent Optimization Machine Learning Ordinal Optimization Orientation Optimization 3D Printing

来源：评论

学校读者我要写书评

暂无评论

A Smoothing-Type Algorithm for Solving Monotone Weighted Complementarity Problems

引用

Journal of Physics: Conference Series 2020年第1期1642卷

作者： Xiaoqin Jiang Yujin Huang Department of Public Basic Wuhan Technology And Business University Wuhan Hubei 430065 China School of Automation Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China University of Geosciences 388 Lumo Road Wuhan Hubei 430074 China

The weighted complementarity problem is an extension of the standard finite dimensional complementarity problem. It is well known that the smoothing-type algorithm is a powerful tool of solving the standard complementarity problem. In this paper, we propose a smoothing-type algorithm for solving the weighted complementarity problem with a monotone function, which needs only to solve one linear system of equations and performs one line search at each iteration. We show that the proposed method is globally convergent under the assumption that the problem is solvable. The preliminary numerical results indicate that the proposed method is effective and robust for solving the monotone weighted complementarity problem.

关键词：

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

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

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：