检索结果-内蒙古大学图书馆

11th International Conference on Modelling, Identification and control (ICMIC)

作者： Chen, Yiwen Yang, Chenguang Feng, Ying South China Univ Technol Sch Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Guangzhou 510640 Peoples R China Univ West England Bristol Robot Lab Bristol BS16 1QY Avon England

ISBN: (纸本)9789811504747;9789811504730

Reinforcement learning enables robot to learn plentiful skills through training. The control based on end-to-end reinforcement learning output joint angle to the robot with image as input. However, using the deep network for end-to-end reinforcement learning makes it hard to converge and need much training time. And it's also difficult to expand to other tasks because of custom-designed network. In this paper, we propose a reinforcement learning structure with variational auto-encoder that can be applied to different goals and reduce training time. Firstly the auto-encoder is trained with images that capture random robot actions. Then the reinforcement learning network is trained with the latent space vectors from auto-encoder instead of raw image. After finish training, the robot can reach a state similar to the state in expected image that we input.

关键词： Reinforcement learning Variational auto-encoder Goal

来源：评论

学校读者我要写书评

暂无评论

Hysteresis Modeling for IPMC Actuators with Rate-Dependent Preisach Model 11

Hysteresis Modeling for IPMC Actuators with Rate-Dependent P...

引用

11th World Congress on Intelligent control and Automation

作者： Feng, Ying Kumkongkaew, Wirut Du, Juan Rakheja, Subhash Su, Chun-Yi South China Univ Technol Sch Automat Sci & Engn Minist Educ Key Lab Autonomous Syst & Networked Control Guangzhou 510640 Guangdong Peoples R China Concordia Univ Dept Mech & Ind Engn Montreal PQ Canada

ISBN: (纸本)9781479958252

Ionic polymer-metal composites(IPMCs) is a class of new smart materials, which can generate large bending motions under a low driving voltage, and this property of IPMCs can be used as artificial muscle driving devices without the traditional components. However, one strong non-smooth nonlinearity, hysteresis, exists between its bending curvature and the applied input voltage. The hysteresis curve is altered with the change of the input voltage rate, which causes the hysteresis in IPMCs with rate-dependent characteristics. In this paper, one modified Preisach hysteresis model is proposed to describe the rate-dependent hysteresis in IPMCs. In order to identify the effectiveness of the proposed modeling method, the comparison results between the experiment measured output and the computing output are given in this paper.

关键词： Hysteresis Preisach model Rate-independence IPMCs

来源：评论

学校读者我要写书评

暂无评论

Robot grasping based on object shape approximation and LightGBM

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第3期83卷 9103-9119页

作者： Lin, Shifeng Zeng, Chao Yang, Chenguang South China Univ Technol Coll Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Minist Educ Guangzhou 510640 Peoples R China South China Univ Technol Coll Automat Sci & Engn GuangDong Engn Technol Res Ctr Control Intelligent Guangzhou 510640 Peoples R China Univ Hamburg Dept Informat TAMS Grp D-22527 Hamburg Germany

Object grasp planning is a challenging task. Recently, methods based on deep learning have made great progress in this area, but they are highly dependent on datasets, which means that they may encounter some difficulties when facing novel objects that are not available in the datasets. In this paper, a novel method is proposed to generate grasping candidate rectangles for object based on shape approximation, without datasets or shape priori of objects. Specifically, combining K-means and the minimum oriented bounding box algorithm for point sets, an adaptive K-means algorithm is applied for decomposing objects into multiple rectangles. The algorithm can independently select the number of K-means cores and automatically select the number of rectangles used to approximate the shape of the object. According to the parameters of each rectangle, a candidate grasping rectangle of the object is generated. In addition, using the Cornell grasping dataset, a LightGBM classifier is trained for the classification and evaluation of object candidate grasping rectangles. Experimental results show that our classification accuracy rate has reached 94.5% and the detection time is only 0.0003s. Among the candidate rectangles, the one with the highest score in the LightGBM model would be selected for real robot grasping. Finally, a multi-object grasping experiment conducted on a real robot platform shows that our algorithm can help the robot grasp new objects with an average success rate of 91.81%.

关键词： Grasp planning Novel object grasping Shape approximation LightGBM

来源：评论

学校读者我要写书评

暂无评论

Two New Discrete-Time Neurodynamic Algorithms Applied to Online Future Matrix Inversion With Nonsingular or Sometimes-Singular Coefficient

引用

IEEE TRANSACTIONS ON CYBERNETICS 2019年第6期49卷 2032-2045页

作者： Qiu, Binbin Zhang, Yunong Sun Yat Sen Univ Sch Informat Sci & Technol Guangzhou 510006 Guangdong Peoples R China Minist Educ Key Lab Autonomous Syst & Networked Control Guangzhou 510640 Guangdong Peoples R China SYSU CMU Shunde Int Joint Res Inst Foshan 528300 Peoples R China Minist Educ Key Lab Machine Intelligence & Adv Comp Guangzhou 510006 Guangdong Peoples R China

In this paper, a high-precision general discretization formula using six time instants is first proposed to approximate the first-order derivative. Then, such a formula is studied to discretize two continuous-time neurodynamic models, both of which are derived by applying the neurodynamic approaches based on neural networks (i.e., zeroing neurodynamics and gradient neurodynamics). Originating from the general six-instant discretization (6ID) formula, a specific 6ID formula is further presented. Subsequently, two new discrete-time neurodynamic algorithms, i.e., 6ID-type discrete-time zeroing neurodynamic (DTZN) algorithm and 6ID-type discrete-time gradient neurodynamic (DTGN) algorithm, are proposed and investigated for online future matrix inversion (OFMI). In addition to analyzing the usual nonsingular situation of the coefficient, this paper investigates the sometimes-singular situation of the coefficient for OFMI. Finally, two illustrative numerical examples, including an application to the inverse-kinematic control of a PUMA560 robot manipulator, are provided to show respective characteristics and advantages of the proposed 6ID-type DTZN and DTGN algorithms for OFMI in different situations, where the coefficient matrix to be inverted is always-nonsingular or sometimes-singular during time evolution.

关键词： General six-instant discretization (6ID) formula online future matrix inversion (OFMI) six-instant discretization-type discrete-time gradient neurodynamic (DTCN) algorithm six-instant discretization-type discrete-time zeroing neurodynamic (DTZN) algorithm sometimes-singular coefficient

来源：评论

学校读者我要写书评

暂无评论

A practical PID variable stiffness control and its enhancement for compliant force-tracking interactions with unknown environments

引用

Science China(Technological Sciences) 2023年第10期66卷 2882-2896页

作者： ZHANG Xin ZHOU Hao LIU JinGuo JU ZhaoJie LENG YuQuan YANG ChenGuang State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China University of Chinese Academy of Sciences Beijing 100049China School of Computing University of PortsmouthPortsmouth PO13HEUK Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems Department of Mechanical and Energy EngineeringSouthern University of Science and TechnologyShenzhen 518055China Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and EngineeringSouth China University of TechnologyGuangzhou 510640China

Compliant interaction control is a key technology for robots performing contact-rich manipulation *** design of the compliant controller needs to consider the robot hardware because complex control algorithms may not be compatible with the hardware performance,especially for some industrial robots with low bandwidth *** paper focuses on effective and easy-to-use compliant control algorithms for position/velocity-controlled *** by human arm stiffness adaptation behavior,a novel variable target stiffness(NVTS)admittance control strategy is proposed for adaptive force tracking,in which a proportional integral derivative(PID)variable stiffness law is designed to update the stiffness coefficient of the admittance function by the force and position ***,its stability and force-tracking capability are theoretically *** addition,an impact compensator(Impc)is integrated into the NVTS controller to enhance its disturbance-suppression capability when the robot is subjected to strong vibration disturbances in complicated surface polishing *** proposed controllers are validated through four groups of experimental tests using different robots and the corresponding results demonstrate that they have high-accuracy tracking capability and strong adaptability in unknown environments.

关键词： compliant interaction control force tracking PID variable stiffness impact compensator unknown environments

来源：评论

学校读者我要写书评

暂无评论

A Framework of Hybrid Force/Motion Skills Learning for Robots

引用

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL systems 2021年第1期13卷 162-170页

作者： Wang, Ning Chen, Chuize Di Nuovo, Alessandro Univ West England Bristol Robot Lab Bristol BS16 1QY Avon England South China Univ Technol Coll Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Guangzhou 510640 Peoples R China Sheffield Hallam Univ Ctr Automat & Robot Res Sheffield S11WB S Yorkshire England

Human factors and human-centered design philosophy are highly desired in today's robotics applications such as human-robot interaction (HRI). Several studies showed that endowing robots of human-like interaction skills can not only make them more likeable but also improve their performance. In particular, skill transfer by imitation learning can increase the usability and acceptability of robots by users without computer programming skills. In fact, besides positional information, muscle stiffness of the human arm and contact force with the environment also play important roles in understanding and generating human-like manipulation behaviors for robots, e.g., in physical HRI and teleoperation. To this end, we present a novel robot learning framework based on dynamic movement primitives (DMPs), taking into consideration both the positional and contact force profiles for human-robot skills transferring. Distinguished from the conventional method involving only the motion information, the proposed framework combines two sets of DMPs, which are built to model the motion trajectory and the force variation of the robot manipulator, respectively. Thus, a hybrid force/motion control approach is taken to ensure the accurate tracking and reproduction of the desired positional and force motor skills. Meanwhile, in order to simplify the control system, a momentum-based force observer is applied to estimate the contact force instead of employing force sensors. To deploy the learned motion-force robot manipulation skills to a broader variety of tasks, the generalization of these DMP models in actual situations is also considered. Comparative experiments have been conducted using a Baxter robot to verify the effectiveness of the proposed learning framework on real-world scenarios like cleaning a table.

关键词： Force Robot sensing systems Task analysis Observers Dynamics Force sensors Dynamic movement primitives (DMPs) force observer generalization hybrid force motion control robot learning skill transfer

来源：评论

学校读者我要写书评

暂无评论

Multi-Loss Function for Distance-to-collision Estimation

Multi-Loss Function for Distance-to-collision Estimation

引用

2021 International Conference on Information, Cybernetics, and Computational Social systems, ICCSS 2021

作者： Zhang, Xiangzhu Zhang, Lijia Xu, DIng Pei, Hailong South China University of Technology Key Laboratory of Autonomous Systems and Networked Control Min. of Educ. Unmanned Aerial Vehicle Systems Engineering Technology Research Center of Guangdong Guangzhou China Guangdong University of Technology School of Computer Science and Technology Guangzhou China

ISBN: (纸本)9781665402453

Estimation of the drone's distance-to-collision is the key to the indoor autonomous obstacle avoidance and navigation of monocular UAVs. At present, the distance-to-collision model mainly uses regression loss or ordinal regression for training Regression loss utilizes the continuity of distance, and ordinal regression loss utilizes the order of distance. To improve the prediction performance of the model, this paper proposes a multi-loss function trained deep learning model based on the linear combination of ordinal regression loss and regression loss. The regression loss can be obtained by adding a distance decoder after the ordinal regression estimation, without changing the original structure of the model. Finally, we test the model performance in public datasets and obtain good results. © 2021 IEEE.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

From Unmanned systems to autonomous Intelligent systems

引用

Engineering 2022年第5期8卷 16-19页

作者： Jie Chen Jian Sun Gang Wang Department of Control Science and Engineering Tongji UniversityShanghai 201804China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai 200092China Key Lab of Intelligent Control and Decision of Complex Systems Beijing Institute of TechnologyBeijing 100081China Beijing Institute of Technology Chongqing Innovation Center Chongqing 401120China

*** Artificial intelligence(AI)is a rapidly growing field of technol-ogy,which“will enliven inert objects,much as electricity did more than a century *** that we formerly electrified will now cognitize”[1].AI advances are constantly pushing the frontier of what machines can *** attention is being placed on AI research,as well as its development and deployment by commer-cial investors,defense strategists,and policy makers[2].

关键词： frontier inert policy

来源：评论

学校读者我要写书评

暂无评论

Haptics Electromyogrphy Perception and Learning Enhanced Intelligence for Teleoperated Robot

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2019年第4期16卷 1512-1521页

作者： Yang, Chenguang Luo, Jing Liu, Chao Li, Miao Dai, Shi-Lu South China Univ Technol Sch Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Guangzhou 510640 Guangdong Peoples R China Univ Montpellier CNRS UMR5506 Dept RobotLIRMM F-34095 Montpellier France Wuhan Univ Sch Power & Mech Engn Wuhan 430074 Hubei Peoples R China

Due to the lack of transparent and friendly human-robot interaction (HRI) interface, as well as various uncertainties, it is usually a challenge to remotely manipulate a robot to accomplish a complicated task. To improve the teleoperation performance, we propose a new perception mechanism by integrating a novel learning method to operate the robots in the distance. In order to enhance the perception of the teleoperation system, we utilize a surface electromyogram signal to extract the human operator's muscle activation. As a response to the changes in the external environment, as sensed through haptic and visual feedback, a human operator naturally reacts with various muscle activations. By imitating the human behaviors in task execution, not only motion trajectory but also arm stiffness adjusted by muscle activation, it is expected that the robot would be able to carry out the repetitive tasks autonomously or uncertain tasks with improved intelligence. To this end, we develop a robot learning algorithm based on probability statistics under an integrated framework of the hidden semi-Markov model (HSMM) and the Gaussian mixture method. This method is employed to obtain a generative task model based on the robot's trajectory. Then, Gaussian mixture regression based on HSMM is applied to correct the robot trajectory with the reproduced results from the learned task model. The execution procedures consist of a learning phase and a reproduction phase. To guarantee the stability, immersion, and maneuverability of the teleoperation system, a variable gain control method that involves electromyography (EMG) is introduced. Experimental results have demonstrated the effectiveness of the proposed method. Note to Practitioners - This paper is inspired by the limitations of teleoperation to perform a task with unfriendly HRI and lack of intelligence. The human operators need to concentrate on the manipulation in the traditional setup of a teleoperation system;thus, it is quite a

关键词： Human-robot interaction Electromyography Robot sensing systems Robot learning Hidden Markov models Gaussian mixture model Gaussian mixture model (GMM) haptics electromyogrphy (EMG) perception hidden semi-Markov model (HSMM) human-robot interaction (HRI) robot intelligence teleoperated robot learning

来源：评论

学校读者我要写书评

暂无评论

A PD controller of Flexible Joint Manipulator Based on Neuro-Adaptive Observer 24th

A PD Controller of Flexible Joint Manipulator Based on Neuro...

引用

24th International Conference on Neural Information Processing (ICONIP)

作者： Liu, Xin Yang, Chenguang Wang, Min He, Wei South China Univ Technol Coll Automat Sci & Engn Key Lab Autonomous Syst & Networked Control Guangzhou 510640 Peoples R China Univ Sci & Technol Beijing Sch Automat & Elect Engn Beijing 100083 Peoples R China

ISBN: (纸本)9783319701363;9783319701356

Due to inevitable uncertainties associated with the dynamics and kinematics of flexible joint manipulators, accurate models would not be available for control design. Furthermore, practically we may face the problem that state variables required by the controller are not measurable. In this paper, we focus on the control system design using a neural network observer to solve the aforementioned unmeasurable problem. A state observer of a general multivariable nonlinear systems based on neural network is proposed. It can be applied to systems with unknown dynamic model. To test the effectiveness of the state observer we design a PD controller combining with the observer proposed for the flexible joint manipulator whose model is unknown. The stability of the controlled system is shown by Lyapunov method. To test and verify the effectiveness of the state controller simulation studies are performed.

关键词： State observer RBF Neural network Flexible joint manipulator system

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：