检索结果-内蒙古大学图书馆

第32届中国控制与决策会议

作者： Naijun Liu Tao Lu Yinghao Cai Rui Wang Shuo Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced TechnologyChinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology of the Chinese Academy of Sciences

Traditional programming method can achieve certain manipulation tasks with the assumption that robot environment is known and ***,with robots gradually applied in more domains,robots often encounter working scenes which are complicated,unpredictable,and *** overcome the limitation of traditional programming method,in this paper,we apply deep reinforcement learning(DRL) method to train robot agent to obtain skill *** policy trained with DRL on real-world robot is time-consuming and costly,we propose a novel and simple learning paradigm with the aim of training physical robot ***,our method train a virtual agent in an simulated environment to reach random target position from random initial ***,virtual agent trajectory sequence obtained with the trained policy,is transformed to real-world robot command with coordinate transformation to control robot performing reaching *** show that the proposed method can obtain self-adaptive reaching policy with low training cost,which is of great benefits for developing intelligent and robust robot manipulation skill system.

关键词： Robot reaching skill learning deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Robust Stabilizing control for Oscillatory Base Manipulators by Implicit Lyapunov Method

Research Square

引用

Research Square 2021年

作者： Guo, Yufei Hou, Baolin Xu, Shengyue Mei, Ruilin Wang, Zhigang Huynh, Van Thanh Key Laboratory of Metallurgical Equipment and Control Technology Ministry of Education School of Machinery and Automation Wuhan University of Science and Technology Wuhan430081 China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan430081 China Shool of Mechanical Engineering Nanjing University of Science and Technology Nanjing210094 China Shool of Engineering Deakin University GeelongVIC3217 Australia

Oscillatory base manipulators (OBMs) are a kind of mechanical systems suffering from unexpected base oscillations. The oscillations affect tremendously system stability. Various control methods have been explored, but most of them require measurement or prediction of the oscillations. This study is concerned with a novel OBM–the autoloader, which are used in modern, autonomous main battle tanks. The base oscillation of the autoloader is hard to be obtained in practice. Furthermore, control synthesis for autoloaders is complicated with intrinsic payload uncertainty and actuator saturation. To address these issues, a novel robust control scheme is proposed in this work relying on the implicit Lyapunov method. Moreover, a novel two-Degree-of-Freedom manipulator operating on a vibrating base is constructed to realize the proposed control. To the best of the authors’ knowledge, this is the first study considering both control and hardware implementation for the OBM-like autoloaders. Experimental results demonstrate that, although without prior information of the base oscillation, the proposed controller exhibits good robustness against the base oscillation and payload uncertainty. © 2021, CC BY.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Distributed Hierarchical Fault Diagnosis Based on Sparse Auto-Encoder and Random Forest 4th

Distributed Hierarchical Fault Diagnosis Based on Sparse Aut...

引用

4th International Conference on Machine Learning and Intelligent Communications, MLICOM 2019

作者： Li, Tong Song, Chunhe Liu, Yang Wang, Zhongfeng Yu, Shimao Su, Shanting Liaoning Electric Power Research Institute State Grid Liaoning Electric Power Co. Ltd. 110000 Shenyang China Key Laboratory of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9783030323875

For the diagnosis of large-scale local devices, the traditional centralized fault diagnosis systems are becoming incompetent to meet the requirement of real-time monitoring. This paper proposes the Distributed hierarchical Fault Diagnosis System (DFDS). Specifically, DFDS implements fault monitoring by an improved Sparse Auto-Encoder (SAE) on the monitor layer, classifies faults and identifies unknown faults by an improved random forest on the classification layer, learns new knowledge and updates the system on the decision layer. We apply DFDS in the laboratory data of Case Western Reserve University to verify the efficiency of the proposed system. The experimental results show that our method can accurately detect the fault and accurately identify the fault type. © 2019, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Attention-Guided Lightweight Network for Real-Time Segmentation of Robotic Surgical Instruments

Attention-Guided Lightweight Network for Real-Time Segmentat...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Zhen-Liang Ni Gui-Bin Bian Zeng-Guang Hou Xiao-Hu Zhou Xiao-Liang Xie Zhen Li State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China school of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

The real-time segmentation of surgical instruments plays a crucial role in robot-assisted surgery. However, it is still a challenging task to implement deep learning models to do real-time segmentation for surgical instruments due to their high computational costs and slow inference speed. In this paper, we propose an attention-guided lightweight network (LWANet), which can segment surgical instruments in real-time. LWANet adopts encoder-decoder architecture, where the encoder is the lightweight network MobileNetV2, and the decoder consists of depthwise separable convolution, attention fusion block, and transposed convolution. Depthwise separable convolution is used as the basic unit to construct the decoder, which can reduce the model size and computational costs. Attention fusion block captures global contexts and encodes semantic dependencies between channels to emphasize target regions, contributing to locating the surgical instrument. Transposed convolution is performed to upsample feature maps for acquiring refined edges. LWANet can segment surgical instruments in real-time while takes little computational costs. Based on 960x544 inputs, its inference speed can reach 39 fps with only 3.39 GFLOPs. Also, it has a small model size and the number of parameters is only 2.06 M. The proposed network is evaluated on two datasets. It achieves state-of-the- art performance 94.10% mean IOU on Cata7 and obtains a new record on EndoVis 2017 with a 4.10% increase on mean IOU.

关键词： Instruments Convolution Semantics Computational efficiency Decoding Surgery Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Short-Term Photovoltaic Power Prediction Modeling Based on AdaBoost Algorithm and Elman

Short-Term Photovoltaic Power Prediction Modeling Based on A...

引用

IEEE International Conference on Power and Energy systems (ICPES)

作者： Wenxuan Sun Tao Zhang Ran Tao Anna Wang College Of Information Science and Engineering Northeastern University Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China School of Electrical Engineering Dalian University of Technology Dalian China

ISBN: (数字)9781665404945

ISBN: (纸本)9781665404952

In recent years, with the rapid expansion of the installed capacity of renewable energy systems, the availability, stability and quality of smart grids have become increasingly important [1] . The application of renewable energy production forecasting has also been rapidly developed, especially in the field of solar photovoltaic (PV) [2][3] . In the example of solar PV output prediction, machine learning and hybrid technologies have been implemented for many applications. In this paper, a high-precision PV system output power prediction model based on improved AdaBoost and Elman is proposed. Multiple model using integrated AdaBoost algorithm fusion with the bat algorithm for the parameters of optimized combination of weak Elman neural network predictor to become a higher prediction precision, the method of strong predictor of the model can according to the weather information, such as temperature, solar radiation and the history of the output of the PV system data, the probability of photovoltaic power generation for 12 hours and deterministic prediction. The prediction accuracy of the model is determined by Root Mean Squared Error (RMSE). Experimental results show that the prediction accuracy of this algorithm is better than that of other benchmark models, and the algorithm can effectively predict the volatility and irregularity of complex time series.

关键词： Photovoltaic systems Renewable energy sources Machine learning algorithms Machine learning Predictive models Prediction algorithms Numerical models

来源：评论

学校读者我要写书评

暂无评论

A vision-based path planning and following system for a miniature robotic fish

A vision-based path planning and following system for a mini...

引用

2019 IEEE International Conference on Real-Time Computing and robotics, RCAR 2019

作者： Lu, Yue Chen, Xingyu Wu, Zhengxing Yan, Yan Yu, Junzhi 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 State Key Laboratory for Turbulence and Complex System Department of Mechanics and Engineering Science BIC-ESAT College of Engineering Peking University Beijing100871 China

ISBN: (纸本)9781728137261

Most existing path following algorithms for middle- or large-sized underwater vehicles minimize yaw difference of the control object. Breaking the canonical manner, this paper presents a vision-based path planning and following system for miniature robotic fish. As for path planning, the proposed system finds a gird path based on the AStar algorithm and selects a series of target points in the grid path. By connecting these points in order, a curve path can be planned. In terms of path following, the proposed system forgoes to give a specific yaw and only uses a global camera. It obtains coordinates of the robotic fish in real time by KCF tracking algorithm to calculate an approximate motion vector. A PID controller is employed to drive the difference angle between the motion vector and the target vector (the vector from the robotic fish to the target point) to zero. By swimming to target points one by one, the robotic fish can move to the terminus following the planned path. Finally, aquatic experiments are conducted to verify the effectiveness of the vision-based path planning and following system. The results reveal that the developed system can generate a safe and smooth path, and the robotic fish can follow the path with acceptable deviation. © 2018 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Hamiltonian Identification of Quantum Networks from Sequential Boolean Measurements

Hamiltonian Identification of Quantum Networks from Sequenti...

引用

IEEE Conference on Decision and control

作者： Biqiang Mu Hongsheng Qi Ian R. Petersen Guodong Shi Key Laboratory of Systems and Control Institute of Systems Science Chinese Academy of Sciences Beijing China Research School of Electrical Energy and Materials Engineering The Australian National University Canberra Australia Australian Center for Field Robotics School of Aerospace The University of Sydney NSW Australia

ISBN: (数字)9781728174471

ISBN: (纸本)9781728174488

Hamiltonian identification plays a key role in learning the dynamics of closed quantum systems. A novel strategy for Hamiltonian identification is developed in the paper by applying repeated projective measurements with a fixed period. The corresponding measurement outcome sequence forms a time-homogeneous Markov chain, the transition matrix of which is a quadratic function of the Hamiltonian. As a result, the identification method is achieved by two steps: 1) learning the transition matrix of the observed Markov chains; 2) identifying the Hamiltonian using the function relating it to the transition matrix, which is transformed to a manifold optimization problem. A simulation example is provided to show the efficacy of the proposed method.

关键词： Markov processes Qubit Maximum likelihood estimation Tomography Optimization Eigenvalues and eigenfunctions Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Synchronous Motion Generation of Multiple Continuum Robots Based on a Jacobian-Estimation Strategy

Synchronous Motion Generation of Multiple Continuum Robots B...

引用

IEEE International Conference on robotics and Biomimetics

作者： Ning Tan Ruikun Hu Yuyang Wu Xinyu Zhang Fenglei Ni Zhenglong Sun School of Computer Science and Engineering Sun Yat-sen University Guangzhou PR China State Key Laboratory of Robotics and Systems (HIT) Harbin PR China Engineering Research Center of Software/Hardware Co-Design Technology and Application Ministry of Education (East China Normal University) Shanghai PR China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9781665405362

In this paper, a novel model-free control scheme is proposed for synchronous motion control of multiple continuum robots. The control problem is formulated as two convex optimization routines in an adaptive and model-free closed-loop framework. The proposed approach is heading to address cooperative task execution for multiple continuum robots. The model-free feedback control guarantees the high portability for a wide range of continuum robots. Simulation studies are conducted on two kinds of tasks, which are cooperative task execution with two robots and simultaneously tracking control with three robots. Besides, the superiority of proposed approach is validated through comparisons with other methods. Simulation results prove the high accuracy and efficiency of this model-free feedback control scheme.

关键词： Jacobian matrices Adaptation models Tracking Simulation Conferences Convex functions Feedback control

来源：评论

学校读者我要写书评

暂无评论

Development of an assist upper limb exoskeleton for manual handling task

Development of an assist upper limb exoskeleton for manual h...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Yan, Zefeng Yi, Haoyuan Du, Zihao Huang, Tiantian Han, Bin Zhang, Lufeng Peng, Ansi Wu, Xinyu State Key Laboratory of Digital Manufacturing Equipment and Technology School of Mechanical Science and Engineering Huazhong University of Science and Technology China CAS Key Laboratory of Human-Manchine-Intelligence Synergic Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Science Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China

ISBN: (纸本)9781728163215

In this paper we describe the construction of a wearable upper arm exoskeleton to provide support for industrial workers who engaged in repetitive handling tasks and patients who full or partial loss of function in their upper limb due to accident injuries, spinal cord and strokes. We use flexible rope driven by a motor to realize the shoulder and elbow joints linkage, use ball screw to realize the self-locking in any position to providing assist for users. This novel design not only saves energy but also make the whole system portable. The total weight of the prototype is only 2 kg. The exoskeleton is connected upper limb with 3 bandages, and users take about 30 seconds to put it on and 20 seconds to put the exoskeleton off without any help. The PD adaptive control method is applied to the proposed exoskeleton to track expected trajectories. Five healthy people participated in data acquisition. Upper limb muscle integrated electromyography (IEMG) of the deltoid muscle(DM), the biceps femoris muscle (BFW), the femoral muscle (FM), the femoral wrist flexor (FWF) were compared in continuous handling for four different loads (0, 1.5, 3, 4.5kg). The average assistance efficiency were 39.1%, 41.5%, 36.5% and 40.6% for the DM, BFM, FM and FWF respectively. The experimental data show that the upper limb exoskeleton can provide assist for workers and protect their upper limbs injuries in long-term handling task. © 2019 IEEE.

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

Attention grasping network: A real-time approach to generating grasp synthesis

Attention grasping network: A real-time approach to generati...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Gu, Qipeng Su, Jianhua Bi, Xueting Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Institute of Automation Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences China Chinese Academy of Sciences Key Laboratory of Electromagnetic Radiation and Sensing Technology Institute of Electronics Beijing100190 China

ISBN: (纸本)9781728163215

This paper presents a real-time, pixelwise method to generate grasp synthesis based on fully convolutional netural networks (FCN). Our proposed Attention Grasping Network (AGN) applies a novel attention mechanism to robotic grasp detection, which automatically learns to focus on salient features of the input image. The model with attention mechnisms can compensate for the loss of detail information in standard FCN, which increases the sensitivity of the model and accuracy of prediction. In addition, in order to ensure a real-time grasp and save computing resources, the light-weight AGN model predicts the position and angle of grasping point. Our method only takes 22ms to execute the grasp detection pipeline on a GPU-equipped computer, and achieves 97.8% accuracy on Cornell Grasping Dataset. © 2019 IEEE.

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

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：