检索结果-内蒙古大学图书馆

An Incremental Learning Framework for Skeletal-based Hand Gesture Recognition with Leap Motion 9

An Incremental Learning Framework for Skeletal-based Hand Ge...

9th IEEE Annual International Conference on Cyber Technology in Automation, control, and Intelligent systems (IEEE-CYBER)

作者： Li, Jie Zhong, Junpei Chen, Fei Yang, Chenguang South China Univ Technol Sch Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Guangzhou 510640 Peoples R China Nottingham Trent Univ Sch Sci & Technol Nottingham NG11 8NS England Ist Italiano Tecnol Dept Adv Robot Via Morego 30 I-16163 Genoa Italy Univ West England Bristol Robot Lab Bristol BS16 1QY Avon England

ISBN: (纸本)9781728107707

Hand gesture recognition has become the focus of researchers lately because of its manifold applications in various fields. Leap Motion (LM) is a device to obtain useful and accurate information of the hand action, which is suitable for collecting the three-dimensional (3D) human hand gesture. In this paper, a novel framework which consists of an incremental learning (IL) algorithm without deep structure is proposed and applied to hand gestures classification that explicitly aimed to the LM data. The same datasets are used to train the proposed framework and the conventional Long Short Term Memory Recurrent Neural Network (LSTM-RNN). Due to the structural advantage of the proposed model, the recognition performance is improved distinctly in robustness and training time than the LSTM network. Moreover, convincing experiment results are given to illustrate that the solution is more efficient in static gesture classification.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Dual Arm Cooperation Based on Visual Servo control

Dual Arm Cooperation Based on Visual Servo Control

引用

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

作者： Junbao Gan Chenguang Yang Long Cheng Ying Feng Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and Engineering South China University of Technology Guangzhou China Bristol Robotics Laboratory University of the West of England Bristol UK Key Laboratory of Complex Systems and Intelligence Science Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728107707

ISBN: (纸本)9781728107714

In this paper, a position-based visual servo method is proposed to perform the high-accuracy precision grasping and collaborative tasks for dual arm robot. Firstly, an adaptive color identification procedure is presented to cope with the problem that the color of the object will change when the object is in different positions for object identification. Secondly, we employ the position-based visual servo method to build a control loop including the sensor data streams obtained from the visual system, the force / torque sensors and the joint encoders. Based on these data, the joint velocity value and the on-line motion trajectory of manipulator could be obtained, which led to a good performance on grasping a fixed object and tracking online. Finally, we implement three experiments to verify the effectiveness of the position-based visual servo method in this paper. The experimental results demonstrate the proposed method can effectively identify target objects with a good positioning accuracy and high capture success rate for collaborative tasks.

关键词： Conferences Automation control systems Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Disturbance observer based sliding mode control for unmanned helicopter hovering operations

Disturbance observer based sliding mode control for unmanned...

引用

第三届国际航空科学青年学者学术会议

作者： Ihsan ULLAH Hai-Long PEI Key Lab of Autonomous Systems and Networked Control Ministry of Education School of Automation South China University of Technology

Numerous control techniques are developed for miniature unmanned helicopters to do hover operation with each methods having its own advantages and limitations. During the hover operation helicopters suffer from unknown external disturbances such as wind and ground effect. For a stable operation, these disturbances must be compensated accurately. This paper presents a disturbance observer based sliding mode control technique for small-scale unmanned helicopters to do hover operation in presence of external disturbances. To counteract both matched and mismatched uncertainties a new sliding surface is designed based on the disturbances estimations. The controller design is based on the linearized state-space model of the helicopter which effectively describes helicopter dynamics during the hover operations. The model mismatch and external disturbances are estimated as lumped disturbances and are compensated in the controller design. The proposed controller reduces chattering and is capable of handling matched and mismatched uncertainties. The control performance is successfully tested in Simulink.

关键词： Unmanned helicopter External Disturbances Sliding mode control Disturbance Observer Chatter reduction Mismatched uncertainty

来源：评论

学校读者我要写书评

暂无评论

Simultaneous identification of velocity and water depth of linear water waves

Simultaneous identification of velocity and water depth of l...

引用

第三十八届中国控制会议

作者： Yang Yu Hai-Long Pei Cheng-Zhong Xu Key Laboratory of Autonomous Systems and Networked Control Ministry of Education Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong College of Automation Science and Engineering South China University of Technology LAGEP Batiment CPE University Claude Bernard-Lyon 1

In this paper, we propose an algorithm of identification in order to simultaneously estimate the velocity of water waves and the water depth in coastal region. We assume that the motion of water waves is described by linearized water wave equation(LWWE) and the surface wave elevation is measurable. Based on the gradient descent method, we design an algorithm of identification to recover simultaneously both the velocity of water waves and the water depth. Numerical simulations are carried out to show the effectiveness of the algorithm.

关键词： LWWE infinite dimensional system water depth velocity gradient descent method

来源：评论

学校读者我要写书评

暂无评论

Teleoperation System for Omnidirectional Mobile Robot Based on Shared control Scheme 8

Teleoperation System for Omnidirectional Mobile Robot Based ...

引用

8th IEEE Annual International Conference on Cyber Technology in Automation, control, and Intelligent systems (IEEE-CYBER)

作者： Li, Weihao Yang, Chenguang Zhang, Xuebo Li, Zhijun South China Univ Technol Coll Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Guangzhou 510640 Peoples R China Nankai Univ IRAIS Tianjin 300071 Peoples R China

ISBN: (纸本)9781538670576

In this paper, a teleoperation system for omnidirectional mobile robot(TSOMR) is proposed in which the operator can use his hand gesture to tele-control the omnidirectional mobile robot(OMR). For hand gesture recognition, MYO is used to collect operator's sEMG sinal. Thanks to the structure os the omni wheels(OW), the OMR can achieve any direction without constraints and its kinematic model is built in this paper. The OMR equips with a depth camera which obtains OMR's surroundings information and transmit it to the operator. This paper also puts forward a shared control scheme for the OMR's obstacle avoidance which can make the motion smooth and effective. This paper uses a modified potential field method for auxiliary assistive obstacle avoidance. The experiment results verify the effectiveness and advantage of the proposed control scheme.

关键词： Teleoperation control Omnidirectional Mobile Robot Motion Planning Potential Field Method

来源：评论

学校读者我要写书评

暂无评论

A Teleoperated Shared control Scheme for Mobile Robot Based sEMG 3

A Teleoperated Shared Control Scheme for Mobile Robot Based ...

引用

3rd IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Xu, Yanbin Yang, Chenguang Liu, Xiaofeng Li, Zhijun South China Univ Technol Sch Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Guangzhou 510641 Guangdong Peoples R China Hohai Univ Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781538670668

This paper developed a novel shared control scheme for mobile robot based on human surface Electromyography (sEMG) signals. we combined the human gesture and the stiffness of the arm with the potential field method (PFM) for the mobile robot path planning. On one hand, the sEMG signals are used to recognized the operator's gesture which is applied to control move direction of mobile robots, on the other hand, the stiffness of human arm is estimated that is able to change the velocity of mobile robot. And the PFM is combined with human teleoperation, which can overcame the local minima and goals non-reachable with the obstacle and goal point as the same line with motion direction of mobile robot. The training samples are collected by MYO armband built-in eight bioelectrical sensors used to estimate sEMG signals, and human gesture recognition by Support Vector Machine(SVM). A omnidirectional mobile robot with a depth camera has been teleoperated by the operator, and the results of the experiment presented the effectiveness of the share control scheme.

关键词： sEMG Teleoperation Shared control Potential field method

来源：评论

学校读者我要写书评

暂无评论

Grasping Novel Objects with Real-Time Obstacle Avoidance 1

引用

10th International Conference on Social Robotics (ICSR)

作者： Zhang, Jiahao Yang, Chenguang Li, Miao Feng, Ying South China Univ Technol Coll Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Guangzhou Peoples R China Wuhan Univ Inst Technol Sci Wuhan Peoples R China

ISBN: (数字)9783030052041

ISBN: (纸本)9783030052041;9783030052034

This paper proposes a new approach to grasp novel objects while avoiding real-time obstacles. The general idea is to perform grasping of novel objects and do collision avoidance at the same time. There are two main contributions. Firstly, a fast and robust method of real-time grasp detection is presented based on morphological image processing and machine learning. Secondly, we integrate our robotic grasping algorithms with some existing collision prediction strategies. It is really helpful to grasp objects on the condition that a robot is surrounded by obstacles. Additionally, it is very practical, runs in real-time and can be easily adaptable with respect to different robots and working conditions. We demonstrate our approaches using the Kinect sensor and the Baxter robot with a series of experiments.

关键词： Grasp novel objects Avoid real-time obstacles Morphological image processing Machine learning

来源：评论

学校读者我要写书评

暂无评论

Emotion-aroused human behaviors Perception Using RNNPB 10

Emotion-aroused human behaviors Perception Using RNNPB

引用

10th International Conference on Modelling, Identification and control (ICMIC)

作者： Li, Jie Yang, Chenguang Zhong, Junpei Dai, Shilu South China Univ Guangzhou Sch Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Guangzhou 510641 Guangdong Peoples R China Natl Inst Adv Ind Sci & Technol Tokyo Japan

ISBN: (纸本)9781538654163

This paper proposes a novel framework to recognize emotions using the algorithm of a recurrent neural network with parameter bias (RNNPB). For this purpose, we performed three simulation experiments aim to explore the relationship between the perception and action. Three types of emotion-driven sequences are fed into the network for training. The training of RNNPB utilizes back-propagation through time (BPTT) method and the parametric bias unit (PB unit) updates in a self-organizing way. The results of the experiments show that the merged sequences can distinguish the emotion better compared to the other two kinds of information.

关键词： Emotion Recognition RNNPB BPTT

来源：评论

学校读者我要写书评

暂无评论

A Novel Robot Teaching System Based on Mixed Reality 3

A Novel Robot Teaching System Based on Mixed Reality

引用

3rd IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Xu, Yang Yang, Chenguang Liu, Xiaofeng Li, Zhijun South China Univ Technol Sch Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Guangzhou 510641 Guangdong Peoples R China Hohai Univ Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781538670668

In this paper, we have developed a robot teaching system where the robot learns the point-to-point motions from human demonstrations. In the demonstration phase, the operator's gestures and palm position are used to guide the robot to complete the task. At the same time, the scene of robots and its work environment, and the virtual model of the palms are integrated into Unity. Then the mixed reality scene is transferred to a virtual reality(VR) helmet, which provides operator real-lime visual feedback. In the learning and reproduction phase, the Extreme Learning Machine(ELM) is used to generate a new trajectory from the training data. The experimental result shows that the robot teaching system based on mixed reality has more realistic and natural interaction. And the learning algorithm based on ELM has a good fitting ability.

关键词： Robot Teaching Mixed Reality Teaching by Demonstration Extreme Learning Machine

来源：评论

学校读者我要写书评

暂无评论

BoostTree and BoostForest for Ensemble Learning

arXiv

引用

arXiv 2020年

作者： Zhao, Changming Wu, Dongrui Huang, Jian Yuan, Ye Zhang, Hai-Tao Peng, Ruimin Shi, Zhenhua 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 Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen China The Autonomous Intelligence Unmanned Systems Engineering Research Center of Ministry of Education of China The State Key Lab of Digital Manufacturing Equipment and Technology Wuhan China

Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and more reliable performance. They have been widely used in biology, engineering, healthcare, etc. This paper proposes BoostForest, which is an ensemble learning approach using BoostTree as base learners and can be used for both classification and regression. BoostTree constructs a tree model by gradient boosting. It increases the randomness (diversity) by drawing the cut-points randomly at node splitting. BoostForest further increases the randomness by bootstrapping the training data in constructing different BoostTrees. BoostForest generally outperformed four classical ensemble learning approaches (Random Forest, Extra-Trees, XGBoost and LightGBM) on 35 classification and regression datasets. Remarkably, BoostForest tunes its parameters by simply sampling them randomly from a parameter pool, which can be easily specified, and its ensemble learning framework can also be used to combine many other base learners. Copyright © 2020, The Authors. All rights reserved.

关键词： Classification (of information)

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：