基于自适应机器学习的视觉机械臂控制方法  

Adaptive Machine Learning Based Control Method for Visual Robot Manipulator System

作　　者：丁亚琼[1] 贾寒光 万凯 DING Yaqiong;JIA Hanguang;WAN Kai(School of Computer Science and Engineering,Sun Yat-sen University,Guangzhou 510006,China;School of Automation Science and Engineering,South China University of Technology,Guangzhou 510641,China;National Key Laboratory of Science and Technology on Reliability Physics and Application of Electronic Component/The Fifth Electronics Research Institute of the Ministry of Industry and Information Technology,Guangzhou 511370,China;School of Electronic Information and Electrical Engineering,Huizhou University,Huizhou 516007,China)

机构地区：[1]中山大学计算机学院,广州510006 [2]华南理工大学自动化科学与工程学院,广州510641 [3]工业和信息化部电子第五研究所/电子元器件可靠性物理及应用国家级重点实验室,广州511370 [4]惠州学院电子信息与电气工程学院,惠州516007

出　　处：《华南师范大学学报（自然科学版）》2024年第3期50-57,共8页Journal of South China Normal University(Natural Science Edition)

基　　金：国家自然科学基金项目(62103159)。

摘　　要：针对多输入多输出视觉机械臂系统中控制增益矩阵存在不确定性的问题,提出了一种基于自适应机器学习的控制方法。通过放宽对系统控制增益矩阵已知性的要求,设计了复合能量函数来证明系统的收敛性。通过模拟机械臂系统运动并使用未标定摄像机进行验证,证明了自适应迭代学习方法的有效性。The control method proposed in this study is based on adaptive machine learning for a multi-input multi-output visual robotic arm system with uncertain control gain matrices.By relaxing the requirement for known control gain matrices in traditional adaptive learning methods,a composite energy function is designed to prove the convergence of the system.The effectiveness of the adaptive iterative learning method is demonstrated through simulating the motion of the robotic arm system and using an uncalibrated camera for validation.

关 键 词：自适应机器学习 控制增益矩阵 非线性系统 机械臂 

分 类 号：TP273.2[自动化与计算机技术—检测技术与自动化装置]