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

Spherical interpolated convolutional network with distance-feature density for 3D semantic segmentation of point clouds

arXiv

引用

arXiv 2020年

作者： Wang, Guangming Yang, Yehui Zhang, Huixin Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Computer Science and Technology University of Cambridge United Kingdom

The semantic segmentation of point clouds is an important part of the environment perception for robots. However, it is difficult to directly adopt the traditional 3D convolution kernel to extract features from raw 3D point clouds because of the unstructured property of point clouds. In this paper, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3D convolution operator. This newly proposed feature extraction operator improves the accuracy of the network and reduces the parameters of the network. In addition, this paper analyzes the defect of point cloud interpolation methods based on the distance as the interpolation weight and proposes the self-learned distance-feature density by combining the distance and the feature correlation. The proposed method makes the feature extraction of spherical interpolated convolution network more rational and effective. The effectiveness of the proposed network is demonstrated on the 3D semantic segmentation task of point clouds. Experiments show that the proposed method achieves good performance on the ScanNet dataset and Paris-Lille-3D dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Compliant net for AUV retrieval using a UAV

引用

IFAC-PapersOnLine 2018年第29期51卷 431-437页

作者： Ivanovic, Antun Polic, Marsela Salah, Omar Orsag, Matko Bogdan, Stjepan Laboratory for Robotics and Intelligent Control Systems Faculty of Electrical Engineering and Computing University of Zagreb Unska 3 Zagreb10 000 Croatia Mechanical Engineering Department Faculty of Engineering Assiut University Assiut Egypt

This paper addresses the problem of retrieving an autonomous underwater vehicle (AUV) with an unmanned aerial vehicle (UAV). The design of the compliant net that naturally adapts to the payload morphology is proposed as a retrieval tool. We constructed the proposed compliant net and conducted experiments with an underwater vehicle model as payload. Furthermore, mathematical model of a system comprised of the UAV and the payload is presented and a mid-ranging controller is utilized for such a system. We also present simulation results and analyze the stability of the UAV with the cable attached payload. © 2018

关键词： Autonomous underwater vehicles Antennas Unmanned aerial vehicles (UAV) Autonomous underwater vehicles (AUV) Marine systems Mechanical design Retrieval tool Soft robotics Underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

Position tracking for continuum robots with joint limit constraints

Position tracking for continuum robots with joint limit cons...

引用

2019 IEEE International Conference on Unmanned systems and Artificial Intelligence, ICUSAI 2019

作者： Lin, Dengliang Dong, Xin Yang, Chenguang Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and Engineering South China University of Technology Guangzhou China Nottingham University Department of Mechanical Materials and Manufacturing Engineering NottinghamNG7 2RD United Kingdom Bristol Robotics Laboratory University of the West of England BristolBS16 1QY United Kingdom

ISBN: (纸本)9781728158594

This paper presents a novel tip-following approach for real-time position tracking and avoiding obstacle of continuum robots with joint limit constraints. This type of hyper-redundant robot, which is more flexible and compliant to explore in complex and constrained environments, such as in pipeline or narrow entrance. However, tradictional method based on inverse kinematic model is difficult to control the end-effector of continuum robot to avoid abstcales in the constrained circumstance. Therefore a new tip-following method based on forward kinematic model is proposed to control the robot and make it inspect the environment. For the method, we use nonliner progamming approach to solve the optimization problem, which is used to find minimum of constrained nonlinear objective function to ensure that the end-effector of the robot follow the desired position with minimal error. In this paper, we employ a 24 DoF continuum robot with continuous backbone and compliant joint to the simulation, and it is testified that the proposed approch can ensure joint limit avoidance, track the end postion in real time and minimize the tracking errors. © 2019 IEEE.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

Efficient dense frontier detection for 2D graph SLAM based on occupancy grid submaps

arXiv

引用

arXiv 2019年

作者： Oršulić, Juraj Miklić, Damjan Kovačić, Zdenko Faculty of Electrical Engineering and Computing Laboratory for Robotics and Intelligent Control Systems University of Zagreb Croatia RoMb Technologies d.o.o. Zagreb Croatia

In autonomous robot exploration, the frontier is the border in the world map dividing the explored and unexplored space. The frontier plays an important role when deciding where in the environment the robots should go explore next. We consider a modular control system pipeline for autonomous exploration where a 2D graph SLAM algorithm based on occupancy grid submaps performs map building and localization, and frontier detection is one of key system components. We provide an overview of the state of the art in frontier detection and the relevant SLAM concepts and propose a fast specialized frontier detection method which is efficiently constrained to active submaps, yet robust to graph SLAM loop closures. Copyright © 2019, The Authors. All rights reserved.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Non-Periodic Lower-Limb Motion Recognition with Noncontact Capacitive Sensing

Non-Periodic Lower-Limb Motion Recognition with Noncontact C...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Enhao Zheng Jinchen Zeng Dongfang Xu Qining Wang Hong Qiao State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences No. 95 of Zhongguancun East Road Beijing China School of Automation and Electrical Engineering University of Science and Technology Beijing 30 Xueyuan Road Beijing Robotics Research Group College of Engineering Peking University Beijing China

ISBN: (数字)9781728167947

ISBN: (纸本)9781728167954

Noncontact captive sensing is a new sensing strategy that we proposed previously to compensate for the limitations of existing surface electromyography studies for exoskeleton control. It has been validated on locomotion mode recognition and gait phase estimation. However, our previous studies addressed the tasks of periodic ambulation based on machine learning algorithms. The performances of the capacitive sensing on non-periodical lower-limb motion recognition have never been evaluated. In this preliminary study, we designed a motion recognition method by fusing the capacitive sensing and the inertial sensors. The recognition algorithm was designed based on the combined logics, which freed the system from burdensome training procedures in the recognition tasks. The method was validated on three healthy subjects in performing 6 lower-limb motions and the transitions between them (10 in total). The capacitance-inertial fusion method produced an average precision/recall of >0.92 in static motions and >0.86 with transitions. The most prominent improvement of using the capacitance signals is that it increases the time-response ability during the motion transitions. Compared with purely using inertial sensors, the sensor fusion method reduced more than 100-ms latency on average. The pilot study extends the scope of the new sensing method in human motion recognition. Future efforts will be paid in this direction to get more promising results.

关键词： Robot sensing systems Capacitance Electrodes Task analysis Legged locomotion Exoskeletons

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time Series Forecast in Industrial Process Based on XGBoost and GRU

Multivariate Time Series Forecast in Industrial Process Base...

引用

IEEE Joint International Information Technology and Artificial Intelligence Conference (ITAIC)

作者： Naiju Zhai Peifu Yao Xiaofeng Zhou 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 University of Chinese Academy of Sciences Beijing China China Copper Co.LTD Kunming China

ISBN: (数字)9781728152448

ISBN: (纸本)9781728152455

In this paper, a time series prediction model that merges eXtreme Gradient Boosting (XGBoost) and Gate Recurrent Unit (GRU), XGB-GRU model, is proposed for multivariate time series prediction in industry. The XGB-GRU model uses XGBoost's strong feature extraction capabilities to extract the hidden information of multiple control variables in industrial data. Next, the model uses GRU's unique gating unit to extract the timing information in the industrial data. Finally, the importance of XGBoost output variables to guide actual production and solve the problem of inexplicability of neural networks. Predicting the temperature of the heating furnace verifies that the proposed XGB-GRU is better than a single XGBoost and GRU model. And the model has a good fit to the predicted value.

关键词： Heating systems Furnaces Time series analysis Predictive models Feature extraction Timing Data mining

来源：评论

学校读者我要写书评

暂无评论

Optimal Feature Selection for EMG-Based Finger Force Estimation Using LightGBM Model

Optimal Feature Selection for EMG-Based Finger Force Estimat...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Yuhang Ye Chao Liu Nabil Zemiti Chenguang Yang Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and Engineering South China University of Technology Guangzhou China Department of Robotics LIRMM CNRS-University of Montpellier Montpellier France Bristol Robotics Laboratory University of the West of England Bristol UK

Electromyogram (EMG) signal has been long used in human-robot interface in literature, especially in the area of rehabilitation. Recent rapid development in artificial intelligence (AI) has provided powerful machine learning tools to better explore the rich information embedded in EMG signals. For our specific application task in this work, i.e. estimate human finger force based on EMG signal, a LightGBM (Gradient Boosting Machine) model has been used. The main contribution of this study is the development of an objective and automatic optimal feature selection algorithm that can minimize the number of features used in the LightGBM model in order to simplify implementation complexity, reduce computation burden and maintain comparable estimation performance to the one with full features. The performance of the LightGBM model with selected optimal features is compared with 4 other popular machine learning models based on a dataset including 45 subjects in order to show the effectiveness of the developed feature selection method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Grasping CNN with Image Segmentation for Mobile Manipulating Robot

A Grasping CNN with Image Segmentation for Mobile Manipulati...

引用

IEEE International Conference on robotics and Biomimetics

作者： Yingying Yu Zhiqiang Cao Shuang Liang Zhicheng Liu Junzhi Yu Xuechao Chen State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Intelligent Robots and Systems Intelligent Robotics Institute BIT Beijing China

This paper presents a grasping convolutional neural network with image segmentation for mobile manipulating robot. The proposed method is cascaded by a feature pyramid network FPN and a grasping network DrGNet. The FPN network combined with point cloud clustering is used to obtain the mask of the target object. Then, the grayscale map and the depth map corresponding to the target object are combined and sent to the DrGNet network for providing multi-scale images. On this basis, depthwise separable convolution is used for encoding. The results of encoders are refined according to the light-weight RefineNet as well as sSE, which can achieve a better grasp detection. The proposed method is verified by the experiments on mobile manipulating robot.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Arctic Respiratory Monitoring System

Arctic Respiratory Monitoring System

引用

International Multi-Conference on Industrial Engineering and Modern Technologies (FarEastCon)

作者： G. Lukyanov A. Rassadina V. Kossareva A.A. Stepanov R.Z. Alexeev The Faculty of Control Systems and Robotics ITMO University Saint-Petersburg Russia Larionov Institute of Physical and Technical Problems of the North SB RAS Yakutsk Russian Federation Laboratory of Immunological researches Yakut Science Centre of Complex Medical Problems Medical Institute M. K. Ammosov North-Eastern Federal University Yakutsk Russia

ISBN: (数字)9781728169514

ISBN: (纸本)9781728169521

The results of heat transfer dynamic processes during the breathing are presented. The study is relevant for investigation of health in the extreme conditions of the Arctic. For estimation of this processes the measurement system of temperature, pressure and velocity pulsations in nostrils are developed. It has been shown that for respiratory system diagnostic it is necessary to analyze such dynamic characteristics as the power spectral density and entropy.

关键词： Temperature measurement Heat transfer Monitoring Temperature sensors Pressure measurement Fluctuations Semiconductor device measurement

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：