小脑模型关节机器人自适应近似最优鲁棒控制  

Adaptive Near Optimal Robust Control of Robot Based on Cerebellar Model Joint

作　　者：刘芬[1] 张超勇[2] LIU Fen;ZHANG Chao-yong(Jingzhou Vocational and Technical College,Hubei Jingzhou 434020,China;Huazhong University of Science and Technology,Hubei Wuhan 430000,China)

机构地区：[1]荆州职业技术学院,湖北荆州434020 [2]华中科技大学,湖北武汉430000

出　　处：《机械设计与制造》2024年第7期77-83,共7页Machinery Design & Manufacture

基　　金：广东省重点领域研发计划项目(2019B090921001)。

摘　　要：为了提升控制性能,降低训练时间与稳态误差,提出了一种小脑模型关节机器人自适应近似最优鲁棒控制方法。首先找到克服诸如重力等非线性的最佳权重集,控制函数保持不变,从而消除存在偏差项时的稳态误差。然后寻找实现原点近似最优控制的附加权重集,从而在搜索优化时惩罚控制作用不会导致由于重力引起的任何稳态误差。无功权值和无功权值之和提供了一个鲁棒权值更新的监督终端,Lyapunov方法保证了信号的一致最终有界性,保证了权值漂移和突发不发生。最后通过柔性关节机器人的实验验证了提出方法的有效性。In order to improve the control performance and reduce the training time and steady-state error,an adaptive near optimal robust control method based on cerebellar model joint was put forward.Firstly,the optimal weight set to overcome the nonlinearity such as gravity was found,and the control function remained unchanged,so as to eliminate the steady-state error when there was a deviation term.Then the additional weight was set to realize the origin approximate optimal control,so that the penalty control effect would not lead to any steady-state error due to gravity when searching for optimization.The sum of the reactive power weights and the reactive power weights provided a monitoring terminal for robust weight updating.The Lyapunov method ensured the consistent ultimate boundedness of the signal and ensured that the weight drift and burst did not occur.Finally,the effectiveness of the proposed method is verified by the experiment of flexible joint robot.

关 键 词：机器人 鲁棒控制 最佳权重集 自适应 

分 类 号：TH16[机械工程—机械制造及自动化] TH133.33[自动化与计算机技术—检测技术与自动化装置] TP277[自动化与计算机技术—控制科学与工程]