检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks

作者： Dong Li Dongbin Zhao Qichao Zhang Chaomin Luo The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences. Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781509061839

Policy gradient algorithm is often used to deal with the continuous control problems. But as a model-free algorithm, it suffers from the low data efficiency and long learning phase. In this paper, a policy gradient with Gaussian process modelling (PGGPM) algorithm is proposed to accelerate learning process. The system model is approximated by Gaussian process in an incremental way, which is used to explore state action space virtually by generating imaginary samples. Both the real and imaginary samples are used to train the actor and critic networks. Finally, we apply our algorithm to two experiments to verify that Gaussian process can accurately fit system model and the supplementary imaginary samples can speed up the learning phase.

关键词： Gaussian processes Learning (artificial intelligence) Approximation algorithms Kernel Computational modeling System dynamics

来源：评论

学校读者我要写书评

暂无评论

A Review of Quadruped Robots and Environment Perception 35

A Review of Quadruped Robots and Environment Perception

引用

第35届中国控制会议

作者： MENG Xiangrui WANG Shuo CAO Zhiqiang ZHANG Leijie State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences

ISBN: (纸本)9781509009107

As legged robots are suitable to be used in unstructured environments,it becomes a popular field of research *** this paper,the development of quadruped robots is *** several typical and recent robot systems are addressed in details,such as HyQ series,StarlETH,ANYmal,MIT Cheetah and BigDog,***,some key techniques of environment perception for quadruped robots,including sensors,feature extraction and identification,mapping and SLAM,are also ***,future researches of quadruped robots in environment perception are given.

关键词： Quadruped robot environment perception sensors feature extraction mapping and SLAM

来源：评论

学校读者我要写书评

暂无评论

Long short-term memory based on a reward/punishment strategy for recurrent neural networks

Long short-term memory based on a reward/punishment strategy...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Jiangjiang Liu Biao Luo Pengfei Yan Ding Wang Derong Liu School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing China The State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781538629024

Recurrent neural networks and their variants have received huge success in many difficult tasks, such as handwriting recognition and generation, natural language processing, acoustic modeling of speech, and so on. As a kind of recurrent neural network architectures, the long short-term memory (LSTM) has attracted great attention. Most research works focus on its structures, training algorithms and topology structures. As an improvement to the structure of LSTM, a reward/punishment strategy is developed for LSTM in this paper, which we call RP-LSTM. In RP-LSTM, a reward/punishment (RP) strategy is proposed to evaluate its memory cells' memorization such that it improves its efficiency by forgetting more reasonably. Analysis of properties of the developed RP-LSTM is conducted from the neuroscience aspect. To test the performance of the developed RP-LSTM, comparative simulation studies are conducted on three structures, i.e., LSTM, LSTM with forget gate (LSTM-FG) and RP-LSTM. Simulation results on sentiment analysis model and sequence to sequence model demonstrate that RP-LSTM achieves better performance.

关键词： Logic gates Mathematical model Training Memory management Recurrent neural networks Speech Neuroscience

来源：评论

学校读者我要写书评

暂无评论

ϵ-SVR-based estimation for the motion trajectory of human lower limb using acceleration signals

ϵ-SVR-based estimation for the motion trajectory of human l...

引用

2016 IEEE International Conference on Information and Automation, IEEE ICIA 2016

作者： Dongxu, Zhang Zengguang, Hou Long, Cheng Guibin, Bian Xiaoliang, Xie Liang, Peng State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781509041022

Active training mode has good clinical effect for patients who need lower limb rehabilitation, and estimation for the motion trajectory of human lower limb is one of the most important and fundamental work for active training. In this study, a novel estimation method is proposed based on ϵ-support vector regression (ϵ-SVR) using acceleration signals of lower limb. Firstly, some qualitative variation regularities between acceleration signals of lower limb superficial muscle group and angle values of hip, knee and ankle joints were obtained through the preliminary analysis of the data, which were acquired in the experiments designed and performed in different motion trajectories that were cycling, walk and pedaling. Then, according to the regularities, the input vectors and the output vectors of ϵ-SVR were determined for the estimation model. After that, experimental data were divided into training data and test data. The estimation model was built based on ϵ-SVR using training data. At last, the estimation model was verified through the test data. The results were that the absolute mean error between predicted values and measured values were respectively 6.26, 4.86 and 5.75 for three kinds of motion trajectories that were cycling, walk and pedaling. The effectiveness and applicability of the estimation model for active training of rehabilitation were confirmed. © 2016 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Report on crowd sourcing and social transportation workshop in itsc 2015: Transportation 5.0 discussed in las palmas report

Report on crowd sourcing and social transportation workshop ...

引用

作者： Cao, Jianping Wang, Xiao China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences China

Reports on the events, activities, and papers presented at the annual IEEE International Conference of intelligent Transportation systems (ITSC 2015) that was held on September, 15th, 2015, in Las Palmas, Spain. ©... 详细信息

关键词： intelligent systems

来源：评论

学校读者我要写书评

暂无评论

A hybrid heading control scheme for a biomimetic underwater vehicle 26

A hybrid heading control scheme for a biomimetic underwater ...

引用

26th Annual International Ocean and Polar Engineering Conference, ISOPE 2016

作者： Wang, Rui Wang, Shuo Wang, Yu State Key Laboratory of Management Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781880653883

This paper addresses the novel design of a biomimetic underwater vehicle (BUV) propelled by undulatory fins and its heading control problems. Inspired by the cuttlefish, which can perform flexible motions by undulatory propulsion in narrow spaces, our BUV with two undulatory fins is designed. The specific implementation of mechanical structure is elaborated. Moreover, a hybrid heading control which combines active disturbance rejection control (ADRC) with fuzzy strategy is proposed to achieve accurate heading control for this BUV. In the end, experimental results demonstrate the feasibility and effectiveness of the mechanism and control system. © Copyright 2016 by the International Society of Offshore and Polar Engineers (ISOPE).

关键词： Fins (heat exchange)

来源：评论

学校读者我要写书评

暂无评论

Multi-view hybrid embedding: A divide-and-conquer approach

arXiv

引用

arXiv 2018年

作者： Xu, Jiamiao Yu, Shujian You, Xinge Leng, Mengjun Jing, Xiao-Yuan Chen, C. L. Philip School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan430074 China Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States Department of Computer Science University of Houston HoustonTX77204 United States State Key Laboratory of Software Engineering School of Computer Wuhan University China Department of Computer and Information Science Faculty of Science and Technology University of Macau Macau99999 China Dalian Maritime University Dalian116026 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China

We present a novel cross-view classification algorithm where the gallery and probe data come from different views. A popular approach to tackle this problem is the multiview subspace learning (MvSL) that aims to learn a latent subspace shared by multi-view data. Despite promising results obtained on some applications, the performance of existing methods deteriorates dramatically when the multi-view data is sampled from nonlinear manifolds or suffers from heavy outliers. To circumvent this drawback, motivated by the Divideand-Conquer strategy, we propose Multi-view Hybrid Embedding (MvHE), a unique method of dividing the problem of cross-view classification into three subproblems and building one model for each subproblem. Specifically, the first model is designed to remove view discrepancy, whereas the second and third models attempt to discover the intrinsic nonlinear structure and to increase discriminability in intra-view and interview samples respectively. The kernel extension is conducted to further boost the representation power of MvHE. Extensive experiments are conducted on four benchmark datasets. Our methods demonstrate overwhelming advantages against the stateof-the-art MvSL based cross-view classification approaches in terms of classification accuracy and robustness. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

On the nonexistence of event-based triggers that preserve Gaussian state in presence of package-drop

On the nonexistence of event-based triggers that preserve Ga...

引用

American control Conference

作者： Enoch Kung Junfeng Wu Dawei Shi Ling Shi Electronic and Computer Engineering Hong Kong University of Science and Technology Department of Automatic Control The Royal Institute of Technology (KTH) State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology

ISBN: (纸本)9781509045839

state estimation is a core objective in cyber-physical systems. In the state estimation problem over linear systems, the Kalman filter is the standard solution. The filter is the format on which the solutions to subsequent estimation problems are based. Among these problems are the estimation problem in the presence of packet drops and estimation problem involving event-based triggers. We study in this paper both phenomena simultaneously. In an attempt to find the Kalman-like filter, which proves the Gaussianity of the state and offers a set of update equations, our paper shows that no such filter exists. More precisely, one cannot find an event-based trigger such that under possible packet drops, the state variable remains a Gaussian variable. This conclusion can be reasonably extended to a more general setting.

关键词： state estimation Packet drops Event-based triggers state estimation Event-based Filters state variable TRIGGERS Gauss

来源：评论

学校读者我要写书评

暂无评论

Design and simulation of a cable-pulley-based transmission for artificial ankle joints

引用

Frontiers of Mechanical Engineering 2016年第2期11卷 170-183页

作者： Huaxin LIU Marco CECCARELLI Qiang HUANG Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing 100081 China Key Laboratory of Biomimetic Robots and Systems (Beijing Institute of Technology) Ministry of Education Beijing 100081 China Laboratory of Robotics and Mechatronics (LARM) DICeM University of Cassino and South Latium Cassino 03043 Italy Beijing Innovation Center for Intelligent Robots and Systems Beijing 100081 China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing 100081 China

In this paper, a mechanical transmission based on cable pulley is proposed for human-like actuation in the artificial ankle joints of human-scale. The anatomy articular characteristics of the human ankle is discussed for proper biomimetic inspiration in designing an accurate, efficient, and robust motion control of artificial ankle joint devices. The design procedure is presented through the inclusion of conceptual considerations and design details for an interactive solution of the transmission system. A mechanical design is elaborated for the ankle joint angular with pitch motion. A multi-body dynamic simulation model is elaborated accordingly and evaluated numerically in the ADAMS environment. Results of the numerical simulations are discussed to evaluate the dynamic performance of the proposed design solution and to investigate the feasibility of the proposed design in future applications for humanoid robots.

关键词： biomimetic designs ankle joints cable-pulleytransmissions multi-body dynamic simulation numericalcharacterization

来源：评论

学校读者我要写书评

暂无评论

Towards Robot-Assisted Post-Stroke Hand Rehabilitation: Fugl-Meyer Gesture Recognition Using sEMG

Towards Robot-Assisted Post-Stroke Hand Rehabilitation: Fugl...

引用

IEEE International Conference on Cyber Technology in Automation, control, and intelligent systems

作者： Miao Chen Long Cheng Fubiao Huang Yan Yan Zeng-Guang Hou University of Chinese Academy of Sciences Faculty of Rehabilitation Capital Medical University Beijing China State Key laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China

Robot-assisted rehabilitation training requires to identify the patient's motion intention effectively. These motions are usually originated from rehabilitation actions included in the Fugl-Meyer assessment scale. Surface electromyography (sEMG) is the most commonly used physiological signal for identifying the motion intention of patients. The use of sEMG to classify different gesture patterns is one key technology for the human-machine interaction. Therefore, this paper investigates a Fugl-Meyer hand gesture recognition method towards robot-assisted hand rehabilitation. The experiment data set including eight hand gesture information is collected from six volunteers. Six single features (Difference Absolute Mean Value (DAMV), Integral of Absolute Value (IAV), Variance (VAR), Autoregressive Coefficients (AR), maximum value of Discrete Wave Transformation (DWTmax) and standard deviation of Discrete Wavelet Transform (DWTstd)) are used to recognize the gesture. The experimental results demonstrate that: (1) a segment length of 250 ms contains enough information to estimate the hand gestures and leaves sufficient time to do feature extraction and gesture recognition;(2) by comparing the performance of different single features, DWTstd wins the highest accuracy (i.e., 96%);(3) the combination of single features into a multi-feature can effectively improve the recognition accuracy, where the best performance is achieved by multi-feature combining DAMV, IAV and AR under BP neural network classifier (the average accuracy is 97.71%);(4) as to different classifiers, BP neural network has a better performance than Support Vector Machine (SVM) and Extreme Learning Machine (ELM).

关键词： Feature extraction Gesture recognition Discrete wavelet transforms Muscles Robots Thumb Training

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：