检索结果-内蒙古大学图书馆

Graph-geometric message passing via a graph convolution transformer for FKP regression

Science China(Information Sciences) 2024年第12期67卷 176-190页

作者： Huizhi ZHU Wenxia XU Jian HUANG Baocheng YU Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology

In this paper, the forward kinematics problem(FKP) of the Gough-Stewart platform(GSP) with six degrees of freedom(6 DoFs) is estimated via deep learning. We propose a graph convolution transformer model by systematically analyzing some challenges encountered with using deep learning regression on largescale data. We attempt to leverage the graph-geometric message as input and singular value decomposition(SVD) orthogonalization for SO(3) manifold learning. This study is the first in which a robot with a sophisticated closed-loop mechanism is described by a graph structure and a specific deep learning model is proposed to solve the FKP of the GSP. Qualitative and quantitative experiments on our dataset demonstrate that our model is feasible and superior to other methods. Our method can guarantee error percentages of translation and rotation less than 1 mm and 1° of 81.9% and 96.7%, respectively.

关键词： deep learning graph-structured learning graph convolution transformer forward kinematics problem Gough-Stewart platform

来源：评论

学校读者我要写书评

暂无评论

Distributed Solving Linear Algebraic Equations with Switched Fractional Order Dynamics

引用

Journal of Systems Science & Complexity 2023年第2期36卷 613-631页

作者： YU Wenqiang CHENG Songsong HE Shuping Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and AutomationAnhui UniversityHefei 230601China

This paper proposes a novel distributed optimization algorithm with fractional order dynamics to solve linear algebraic ***,the authors proposed“Consensus+Projection”flow with fractional order dynamics,which has more design freedom and the potential to obtain a better convergent performance than that of conventional first order ***,the authors prove that the proposed algorithm is convergent under certain iteration order and ***,the authors develop iteration order switching scheme with initial condition design to improve the convergence performance of the proposed ***,the authors illustrate the effectiveness of the proposed method with several numerical examples.

关键词： Distributed optimization fractional order dynamics initial condition iteration order linear equations

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Optimal Nonlinear Systems Control Based on State Observer and Neural Network

引用

Journal of Systems Science & Complexity 2023年第1期36卷 222-238页

作者： CHENG Songsong LI Haoyun GUO Yuchao PAN Tianhong FAN Yuan Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and AutomationAnhui UniversityHefei 230601China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and AutomationAnhui UniversityHefei 230601China

This paper develops a novel event-triggered optimal control approach based on state observer and neural network(NN)for nonlinear continuous-time ***,the authors propose an online algorithm with critic and actor NNs to solve the optimal control problem and provide an event-triggered method to reduce communication and computation ***,the authors design weight estimation for critic and actor NNs based on gradient descent method and achieve uniformly ultimate boundednesss(UUB)estimation ***,by using bounded NN weight estimation and dead-zone operator,the authors propose a triggering condition,prove the asymptotic stability of closed-loop system from Lyapunov stability perspective,and exclude the Zeno ***,the authors provide a numerical example to illustrate the effectiveness of the proposed method.

关键词： Event-triggered control neural network optimal control state observer

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimization and Scaling Design for Solving Sylvester Equations

引用

Journal of Systems Science & Complexity 2024年第6期37卷 2487-2510页

作者： CHENG Songsong YU Xin ZENG Xianlin LIANG Shu HONG Yiguang Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and AutomationAnhui UniversityHefei 230601China Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of TechnologyBeijing 100081China Department of Control Science and Engineering Tongji UniversityShanghai 201804China Shanghai Research Institute for Intelligent Autonomous Systems Tongji UniversityShanghai 201210China

This paper develops distributed algorithms for solving Sylvester *** authors transform solving Sylvester equations into a distributed optimization problem,unifying all eight standard distributed matrix *** the authors propose a distributed algorithm to find the least squares solution and achieve an explicit linear convergence *** results are obtained by carefully choosing the step-size of the algorithm,which requires particular information of data and Laplacian *** avoid these centralized quantities,the authors further develop a distributed scaling technique by using local information *** a result,the proposed distributed algorithm along with the distributed scaling design yields a universal method for solving Sylvester equations over a multi-agent network with the constant step-size freely chosen from configurable ***,the authors provide three examples to illustrate the effectiveness of the proposed algorithms.

关键词： Distributed optimization least squares solution linear convergence rate step-size interval Sylvester equation

来源：评论

学校读者我要写书评

暂无评论

Fractional Order Iteration for Gradient Descent Method Based on Event-Triggered Mechanism

引用

Journal of Systems Science & Complexity 2023年第5期36卷 1927-1948页

作者： LU Jiajie WANG Yong FAN Yuan Department of Automation University of Science and Technology of ChinaHefei 230026China Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and AutomationAnhui UniversityHefei 230601China

In this work,a novel gradient descent method based on event-triggered strategy has been proposed,which involves integer and fractional order ***,the convergence of integer order iterative optimization method and the stability of its associated system with integrator dynamics are *** on this result,a fractional order iteration approach has been developed by modelling the system with fractional order ***,to reduce the comsumption of computation,a feedback based event-triggered mechanism has been introduced to the gradient descent *** convergence of this new event-triggered optimization algorithm is guaranteed by using a Lyapunov method,and Zeno behavior is proved to be avoided ***,the effectiveness and advantages of the proposed algorithms are verified by numerical simulations.

关键词： Event-triggered mechanism fractional order iteration gradient descent Zeno behavior

来源：评论

学校读者我要写书评

暂无评论

Policy iteration-based adaptive optimal control for Markov jump systems: a transition-probability-free asynchronous approach

引用

Science China(Information Sciences) 2024年第11期67卷 363-364页

作者： Weidi CHENG Chengcheng REN Shuping HE Changyin SUN Key Laboratory of Intelligent Computing and Signal Processing (Ministry of Education) School of Electrical Engineering and Automation Anhui University Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and Automation Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Engineering Research Center of Autonomous Unmanned System Technology (Ministry of Education) School of Artificial Intelligence Anhui University

The controller and filter design problems of Markov jump systems(MJSs) have gained significant attention over the past few decades. These studies include various aspects,including stochastic stabilization [1], optimal tracking control [2], and dissipative filter design [3]. Although numerous publications address the optimal controller design for MJSs, the issue of hidden MJSs, particularly those with mismatched jumping modes between the system and the controller, has rarely been explored.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

SGT-Net: A Transformer-Based Stratified Graph Convolutional Network for 3D Point Cloud Semantic Segmentation

引用

Computers, Materials & Continua 2024年第6期79卷 4471-4489页

作者： Suyi Liu Jianning Chi Chengdong Wu Fang Xu Xiaosheng Yu Faculty of Robot Science and Engineering Northeastern UniversityShenyang110167China State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang110169China SIASUN Robot&Automation Co. Ltd.Shenyang110169China

In recent years,semantic segmentation on 3D point cloud data has attracted much *** 2D images where pixels distribute regularly in the image domain,3D point clouds in non-Euclidean space are irregular and inherently ***,it is very difficult to extract long-range contexts and effectively aggregate local features for semantic segmentation in 3D point cloud *** current methods either focus on local feature aggregation or long-range context dependency,but fail to directly establish a global-local feature extractor to complete the point cloud semantic segmentation *** this paper,we propose a Transformer-based stratified graph convolutional network(SGT-Net),which enlarges the effective receptive field and builds direct long-range ***,we first propose a novel dense-sparse sampling strategy that provides dense local vertices and sparse long-distance vertices for subsequent graph convolutional network(GCN).Secondly,we propose a multi-key self-attention mechanism based on the Transformer to further weight augmentation for crucial neighboring relationships and enlarge the effective receptive *** addition,to further improve the efficiency of the network,we propose a similarity measurement module to determine whether the neighborhood near the center point is *** demonstrate the validity and superiority of our method on the S3DIS and ShapeNet *** ablation experiments and segmentation visualization,we verify that the SGT model can improve the performance of the point cloud semantic segmentation.

关键词： 3D point cloud semantic segmentation long-range contexts global-local feature graph convolutional network dense-sparse sampling strategy

来源：评论

学校读者我要写书评

暂无评论

Attitude Tracking Control for Rigid Spacecraft with Arbitrary Convergence Time

引用

Journal of Systems Science & Complexity 2024年第6期37卷 2579-2594页

作者： XU Yu-Tian WU Ai-Guo Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Harbin Institute of Technology(Shenzhen)Shenzhen 518055China Key University Laboratory of Mechanism&Machine Theory and Intelligent Unmanned Systems of Guangdong Harbin Institute of Technology(Shenzhen)Shenzhen 518055China Department of Automation Harbin Institute of Technology(Shenzhen)Shenzhen 518055China HIT Wuhu Robot Technology Research Institute Wuhu 241060China

In this paper,attitude tracking control with arbitrary convergence time for rigid spacecraft is ***,a novel time-varying sliding function is proposed to achieve free-will arbitrary time convergence when the system states reside on the sliding *** such a sliding function,an attitude tracking controller is designed to guarantee that the states of the closed-loop system converge to the sliding surface within a predetermined time in the presence of external *** free-will arbitrary time convergences of the closed-loop system and sliding function are illustrated by numerical simulations.

关键词： Attitude tracking free-will arbitrary time stability rigid spacecraft sliding mode control

来源：评论

学校读者我要写书评

暂无评论

DGConv: A Novel Convolutional Neural Network Approach for Weld Seam Depth Image Detection

引用

Computers, Materials & Continua 2024年第2期78卷 1755-1771页

作者： Pengchao Li Fang Xu Jintao Wang Haibing Guo Mingmin Liu Zhenjun Du State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang110169China University of Chinese Academy of Sciences Beijing100049China Shenyang SIASUN Robot&Automation Co. Ltd.Shenyang110168China

We propose a novel image segmentation algorithm to tackle the challenge of limited recognition and segmentation performance in identifying welding seam images during robotic intelligent ***,to enhance the capability of deep neural networks in extracting geometric attributes from depth images,we developed a novel deep geometric convolution operator(DGConv).DGConv is utilized to construct a deep local geometric feature extraction module,facilitating a more comprehensive exploration of the intrinsic geometric information within depth ***,we integrate the newly proposed deep geometric feature module with the Fully Convolutional Network(FCN8)to establish a high-performance deep neural network algorithm tailored for depth image ***,we enhance the FCN8 detection head by separating the segmentation and classification *** enhancement significantly boosts the network’s overall detection ***,for a comprehensive assessment of our proposed algorithm and its applicability in real-world industrial settings,we curated a line-scan image dataset featuring weld *** dataset,named the Standardized Linear Depth Profile(SLDP)dataset,was collected from actual industrial sites where autonomous robots are in ***,we conducted experiments utilizing the SLDP dataset,achieving an average accuracy of 92.7%.Our proposed approach exhibited a remarkable performance improvement over the prior method on the identical ***,we have successfully deployed the proposed algorithm in genuine industrial environments,fulfilling the prerequisites of unmanned robot operations.

关键词： Weld image detection deep learning semantic segmentation depth map geometric feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Real-Time VSLAM Based on Deep Features and Object Detection for Dynamic Environments 38

A Real-Time VSLAM Based on Deep Features and Object Detectio...

引用

38th Youth Academic Annual Conference of Chinese Association of automation, YAC 2023

作者： Jiang, Yuanhui Li, Teng Fan, Yuan Anhui University Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering Automation Hefei230601 China

ISBN: (纸本)9798350303636

The current simultaneous localization and mapping (SLAM) relies heavily on the hypothesis of static environments, and the localization accuracy and stability of the algorithm will be extremely affected when facing dynamic and complex environment. In response to this problem, a real-time visual SLAM system for dynamic environments is presented in this work, based on the ORB-SLAM3 algorithm for improvement. After obtaining the RGB images, the features are first extracted by the GCNv2 neural network, while the semantic information about the images is initially obtained using the lightweight target detection network YOLOv5. Then, based on the dynamic characteristics of the object between consecutive frames, the static feature points are obtained by eliminating its dynamic features to complete the pose estimation. The proposed algorithm is validated using the publicly available TUM dataset, and the experimental results show that the root mean square error of absolute trajectory error is reduced to 93.96% and 33.3% compared with ORB-SLAM3 and DS-SLAM, which improves the localization accuracy in dynamic scenes and also ensures the real-time performance of the system. © 2023 IEEE.

关键词： deep learning dynamic environments object detection ORB-SLAM3

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：