检索结果-内蒙古大学图书馆

2024 International conference on Intelligent Robots and systems

作者： Islam, Sharfin He, Zhanpeng Ciocarlie, Matei Columbia Univ Dept Mech Engn New York NY 10027 USA Columbia Univ Dept Comp Sci New York NY USA

ISBN: (纸本)9798350377712;9798350377705

Underactuated manipulators reduce the number of bulky motors, thereby enabling compact and mechanically robust designs. However, fewer actuators than joints means that the manipulator can only access a specific manifold within the joint space, which is particular to a given hardware configuration and can be low-dimensional and/or discontinuous. Determining an appropriate set of hardware parameters for this class of mechanisms, therefore, is difficult - even for traditional task-based co-optimization methods. In this paper, our goal is to implement a task-based design and policy co-optimization method for underactuated, tendon-driven manipulators. We first formulate a general model for an underactuated, tendon-driven transmission. We then use this model to co-optimize a three-link, two-actuator kinematic chain using reinforcement learning. We demonstrate that our optimized tendon transmission and control policy can be transferred reliably to physical hardware with real-world reaching experiments.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

controller-Dynamic-Linearization-Based data-driven ILC for Nonlinear Discrete-Time systems With RBFNN

引用

ieee TRANSACTIONS ON systems MAN CYBERNETICS-systems 2022年第8期52卷 4981-4992页

作者： Yu, Xian Hou, Zhongsheng Polycarpou, Marios M. Chinese Univ Hong Kong Sch Data Sci Shenzhen 518172 Guangdong Peoples R China Qingdao Univ Sch Automat Qingdao 266071 Peoples R China Univ Cyprus KIOS Res & Innovat Ctr Excellence CY-1678 Nicosia Cyprus Univ Cyprus Dept Elect & Comp Engn CY-1678 Nicosia Cyprus

In this article a novel data-driven iterative learning control (ILC) approach is proposed for unknown nonlinear nonaffine repetitive discrete-time systems, where the dynamic linearization (DL) technique in the iteration domain is applied both on the controlled nonlinear system and on the unknown nonlinear ideal learning controller. Through updating the weight matrix of a radial basis function neural network (RBFNN), the learning control gain of the obtained iterative learning law is automatically tuned in reaching the optimal learning controller using only the input-output data of the nonlinear system. The uniformly ultimately bounded property is established for the tracking error of the proposed ILC scheme in the iteration domain through rigorous theoretical analysis. The effectiveness and applicability are validated by a simulation example and further demonstrated by simulation on a high-speed train model.

关键词： control systems data models Systematics Nonlinear dynamical systems Discrete-time systems Trajectory Time-domain analysis data-driven iterative learning control (ILC) dynamic linearization (DL) nonlinear repetitive systems radial basis function neural network (RBFNN)

来源：评论

学校读者我要写书评

暂无评论

data-driven Safe Formation control for Multi-Agent systems and Its Applications in Multi-UGV systems

Data-Driven Safe Formation Control for Multi-Agent Systems a...

引用

2023 ieee International conference on systems, Man, and Cybernetics, SMC 2023

作者： Yan, Bing Shi, Peng Zhang, Daotong Yang, Yize School of Electrical and Mechanical Engineering The University of Adelaide SA5005 Australia Obuda University Budapest1034 Hungary

ISBN: (纸本)9798350337020

In this paper, we propose a reinforcement learning-based safe control strategy for uncertain heterogeneous multi-agent systems. The objective is to achieve collision-free time-varying formations under switching topologies and with limited network resources. Without requiring global communication information, an event-triggered observer is designed to decouple the heterogeneous dynamics from switching networks and reduce data transmission frequency. A data-driven off-policy reinforcement learning algorithm is developed for addressing the robust safe formation control problem. The algorithm is capable of solving non-quadratic optimization problems without requiring model information. The proposed strategy is applied to a multi-unmanned ground vehicle (UGV) system for a patrolling mission, and the experimental results verified the effectiveness of the proposed strategy. © 2023 ieee.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed data-driven Iterative learning Consensus Tracking for Nonlinear Discrete-Time Multiagent systems

引用

ieee TRANSACTIONS ON AUTOMATIC control 2022年第7期67卷 3670-3677页

作者： Yu, Xian Hou, Zhongsheng Polycarpou, Marios M. Chinese Univ Hong Kong Sch Data Sci Shenzhen 518172 Peoples R China Qingdao Univ Sch Automat Qingdao 266071 Peoples R China Univ Cyprus KIOS Res & Innovat Ctr Excellence CY-1678 Nicosia Cyprus Univ Cyprus Dept Elect & Comp Engn CY-1678 Nicosia Cyprus

In this article, a data-driven distributed leader-follower iterative learning consensus tracking control approach is proposed for unknown repetitive nonlinear nonaffine discrete-time multi-agent systems. The leader's command is only communicated to a subset of the following agents and each following agent exchanges information only with its neighbors under a directed graph. A local iterative learning consensus control protocol is designed using only local measurements communicated among neighboring agents without the availability of physical and structural information of each agent by virtue of the dynamic linearization method both on the agent and the ideal distributed learning controller along the iteration axis. The convergent consensus properties of the tracking errors along the iteration axis are rigorously established under the strongly connected iteration-independent and iteration-varying communication topologies. One example is provided to validate the effectiveness of the proposed iterative learning consensus control protocol.

关键词： control systems data models Trajectory Heuristic algorithms Topology Task analysis Nonlinear dynamical systems Consensus tracking data-driven iterative learning control dynamic linearization technique nonlinear repetitive discrete-time multiagent systems

来源：评论

学校读者我要写书评

暂无评论

2024 ieee International conference on Fuzzy systems, FUZZ-ieee 2024 - Proceedings

2024 IEEE International Conference on Fuzzy Systems, FUZZ-IE...

引用

2024 ieee International conference on Fuzzy systems, FUZZ-ieee 2024

ISBN: (纸本)9798350319545

The proceedings contain 116 papers. The topics discussed include: federated learning with the Choquet integral as aggregation method;a tractable approach to fitting the Choquet integral for explainable prediction and analysis;autonomous cornering control based on sense of circular vision model;consistent post-hoc explainability in federated learning through federated fuzzy clustering;JFML-IoT: fuzzy control for IoT systems based on the ieee std 1855-2016;beyond large language models: rediscovering the role of classical statistics in modern data science;defense strategy against byzantine attacks in federated machine learning: developments towards explainability;a grey wolf-driven refinement of fuzzy-based controller for enhanced DC microgrid operation;and psychological effects of agents having complementary relationships with people.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Fault Diagnosis Method of Beam Pumping Units Based on Dynamic Warping Matching and Parallel Deep Network

引用

ieee TRANSACTIONS ON systems MAN CYBERNETICS-systems 2024年第3期54卷 1622-1632页

作者： Liu, Shuo Song, Chunhe Wu, Tingting Zeng, Peng Chinese Acad Sci Key Lab Networked Control Syst State Key Lab Robot Shenyang 110016 Peoples R China Chinese Acad Sci Shenyang Inst Automat Shenyang 110016 Peoples R China

Beam pumping units (BPUs) are key equipment in oilfield production. Currently, many fault diagnosis methods for BPUs have been developed, and most of them are based on feature or image classification of indicator diagrams. However, low-quality monitoring data and the limited proportion of effective pixels in indicator diagram greatly restrict the performances of these methods. This article proposes an efficient two-step fault diagnosis method for BPUs. In the first step, to overcome the impact of low-quality monitoring data, a dynamic time warping-based matching method is proposed to extract the period of the data, and then a physical model driven method optimized by Bayesian gradient descent is proposed to reconstruct the data. In the second step, to overcome the impact of the limited proportion of effective pixels in indicator diagram, a parallel deep network is proposed which directly takes the time series of the displacement and the load of BPUs as the inputs. Extensive experiments on dataset from 45 real oil wells have shown that, the proposed method can achieve the best performance compared with the state-of-the-art methods, meanwhile the computational load is only 5% of other deep learning-based methods.

关键词： Fault diagnosis Feature extraction data mining Monitoring Robots Production Employee welfare Beam pumping unit (BPU) deep learning dynamic time warping (DTW) fault diagnosis signal reconstruction

来源：评论

学校读者我要写书评

暂无评论

Replay-Based Continual learning for Test Case Prioritization

Replay-Based Continual Learning for Test Case Prioritization

引用

17th ieee International conference on Software Testing, Verification, and Validation (ICST)

作者： Fariha, Asma Azim, Akramul Liscano, Ramiro Ontario Tech Univ Dept Elect Comp & Software Engn Oshawa ON Canada

ISBN: (纸本)9798350344806;9798350344790

In a large-scale Continuous Integration (CI) environment, regression testing can encounter high time and resource demands in ad hoc execution. Therefore, Test Case Prioritization (TCP) is crucial for enhancing the regression testing efficiency of CI. TCP methods aim to optimize regression testing by ordering test cases to effectively cover new code changes and their potential side effects and to maximize early fault detection. Traditional prioritization processes use diverse data sources, including code coverage analysis, test execution history, and domain-specific features. Heuristic-based or code-coverage-driven prioritization techniques may not be sufficient for accurate results in a rapidly changing environment. For this reason, there has been a significant shift towards employing Machine learning (ML) techniques in TCP in recent years to harness the vast and complex datasets generated by CI practices. ML-based TCP approaches integrate multifaceted test case features from various sources to enhance the accuracy of test case prioritization. This trend reflects a broader movement towards data-driven decisionmaking in software testing, offering the potential to significantly reduce the regression testing burden by tailoring test suites more effectively to the needs of each software build, thereby saving time and resources while maintaining or improving the software quality. Recent studies have shown that the ML-based methods used in TCP can be categorized into four groups: Supervised learning, Unsupervised learning, Reinforcement learning, and Natural Language Processing. Codebases for software projects can be changed rapidly by introducing new feature distributions into the CI systems. We analyzed a Java application's CI and version control system (VCS) history data received from the International Business Machines Corporation (IBM) [1], [6], [7]. The frequent inclusion of new test suites introduced new patterns into the dataset properties. To keep up with these c

关键词： continual learning test case prioritization pre-training experience replay catastrophic forgetting

来源：评论

学校读者我要写书评

暂无评论

ADP-Based Optimal control of Linear Singularly Perturbed systems With Uncertain Dynamics: A Two-Stage Value Iteration Method

引用

ieee TRANSACTIONS ON CIRCUITS AND systems II-EXPRESS BRIEFS 2023年第12期70卷 4399-4403页

作者： Zhao, Jianguo Yang, Chunyu Gao, Weinan Park, Ju H. China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Peoples R China Yeungnam Univ Dept Elect Engn Gyongsan 38541 South Korea China Univ Min & Technol Engn Res Ctr IntelligentControl Underground Space Minist Educ Xuzhou 221116 Peoples R China China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Peoples R China Northeastern Univ State Key Lab Synthet Automat Process Ind Shenyang 110819 Peoples R China Yeungnam Univ Dept Elect Engn Gyongsan 38541 South Korea

We study the problem of adaptive dynamic programming (ADP) based on optimal control of linear singularly perturbed systems (SPSs) subject to completely unknown dynamics. Previous works on ADP-based optimal control of SPSs require that the fast dynamics of the system are either known a priori or unknown but asymptotically stable, and such results are limited to standard cases, i.e., the internal dynamics of their fast subsystems are nonsingular. In this brief, these conditions can be removed through a sequential procedure to design feedback gains of both fast and slow states in the framework of ADP. In this procedure, two optimal control problems are formulated for the prefeedback fast subsystem and the modified slow subsystem. Then, a data-driven two-stage value iteration algorithm is imposed to learn the optimal controller without using any system dynamics. Fundamentally different from existing works, an initial admissible control policy is no longer needed during learning. Finally, the effectiveness of the learning algorithm is proved by a simulation example.

关键词： Adaptive dynamic programming (ADP) optimal control singularly perturbed systems (SPSs) value iteration data-driven control

来源：评论

学校读者我要写书评

暂无评论

Finite-Time learning-Based Optimal Elliptical Encircling control for UAVs With Prescribed Constraints

引用

ieee TRANSACTIONS ON INTELLIGENT TRANSPORTATION systems 2025年第5期26卷 7065-7080页

作者： Shao, Xingling Zhang, Fei Liu, Jun Zhang, Qingzhen North Univ China Sch Elect & Control Engn Taiyuan 030051 Peoples R China Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China North Univ China Sch Instrument & Elect Taiyuan 030051 Peoples R China Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China

This paper addresses an optimal elliptical enclosing problem of Unmanned Aerial Vehicles (UAVs) under prescribed constraints, whose objective is to steer UAVs to fulfill accurate target encirclement while complying with arriving time restrictions and minimum efforts. A novel learning-based approximate optimal control policy including two-stage designs is presented. At the first stage, a steady-state robust control protocol is developed to steer UAVs to precisely travel along a predefined elliptical path based on concise filtering. At the second stage, to address specified-time constraints and gain the online optimization ability, a single-critic based enhanced learning rule is explored to generate an approximate optimal regulator that stabilizes error dynamics and minimizes value functions, wherein specified-time constraints can be handled by encoding inequality conditions as skilled barrier functions, and by making full use of historical data and current information, a finite-time learning mechanism driven by weight errors rather than Bellman errors is proposed to approximate the solution of Hamilton-Jacobi-Bellman (HJB) equation with faster decaying. The distinct merit is that an improved reinforcement learning (RL) paradigm is formulated to prescribe an elliptical circumnavigation with assured time requirements and optimization behaviors, which can greatly outperform non-RL alternatives in maintaining the optimal performance index while exhibiting restriction handling ability via online learning. Lyapunov stability demonstrates that involved error variables are ultimately limited and resultant controller obeys optimality. The feasibility and values of presented algorithm are accessed by comparisons and simulations.

关键词： Optimal control Autonomous aerial vehicles Artificial neural networks Costs Vehicle dynamics Time factors Steady-state Robust control Perturbation methods Constraint handling Optimal elliptical encircling prescribed constraints finite-time learning performance optimization UAVs

来源：评论

学校读者我要写书评

暂无评论

Adaptive Predefined-Time SMC for Uncertain Robotic systems 13

Adaptive Predefined-Time SMC for Uncertain Robotic Systems

引用

13th ieee data driven control and learning systems conference, DDCLS 2024

作者： Qiao, Chaoqian Zong, Guangdeng Chang, Zhenyu School of Electronics and Information Engineering Tiangong University Tianjin300387 China School of Control Science and Engineering Tiangong University Tianjin300387 China

ISBN: (纸本)9798350361674

This paper presents a novel adaptive predefined-time sliding-mode control (SMC) strategy for the tracking problem of uncertain robotic manipulators. Firstly, the unknown dynamic parameters and the bound vector of the disturbances are integrated into a compounded uncertainty. Considering that the boundary of the compounded uncertainty is not readily available in practical applications, the adaptive neural networks (NNs) are adopted to compensate for the compounded uncertainty of the robot. Moreover, to enhance the robustness and accelerate the system convergence, a novel nonsingular sliding surface approach is integrated into the controller design. Then, an NNs-based predefined-time controller is proposed to guarantee that the actual trajectory tracks the reference trajectory, allowing the maximum convergence time to be pre-adjusted using explicit parameters without losing robustness property. At last, simulation results conducted with a two-joint manipulator confirm both the exceptional performance and effectiveness of the developed method. © 2024 ieee.

关键词： Neural networks

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：