不确定机器人的自适应神经网络控制与学习  

Adaptive neural network control and learning for uncertain robot

作　　者：吴玉香[1] 王聪[1] 

机构地区：[1]华南理工大学自动化科学与工程学院,广东广州510640

出　　处：《控制理论与应用》2013年第8期990-997,共8页Control Theory & Applications

基　　金：国家自然科学基金资助项目(60934001;61075082);广东省战略性新兴产业专项项目(2011A081301017;2012A080304012);华南理工大学中央高校基本科研业务费(2012ZZ0106)

摘　　要：针对具有未知动态的电驱动机器人,研究其自适应神经网络控制与学习问题.首先,设计了稳定的自适应神经网络控制器,径向基函数(RBF)神经网络被用来逼近电驱动机器人的未知闭环系统动态,并根据李雅普诺夫稳定性理论推导了神经网络权值更新律.在对回归轨迹实现跟踪控制的过程中,闭环系统内部信号的部分持续激励(PE)条件得到满足.随着PE条件的满足,设计的自适应神经网络控制器被证明在稳定的跟踪控制过程中实现了电驱动机器人未知闭环系统动态的准确逼近.接着,使用学过的知识设计了新颖的学习控制器,实现了闭环系统稳定、改进了控制性能.最后,通过数字仿真验证了所提控制方法的正确性和有效性.This paper investigates the adaptive neural network control and learning for the electrically-driven robot with unknown system dynamics. A stable adaptive neural network （NN） controller is first designed, and the radial basis function （RBF） neural-network is used to approximate the unknown closed-loop system dynamics of electrically-driven robot. The stable adaptive tuning laws of network parameters are derived in the sense of the Lyapunov stability theory. Partial persistent excitation （PE） condition of some internal signals in the closed-loop system is satisfied in the control process of tracking a recurrent reference trajectory. Under the PE condition, the proposed adaptive NN controller is rigorously shown to be capable of accurate identification of the uncertain electrically-driven robot dynamics in the stable control process. Subsequently, a novel NN learning control method which effectively utilizes the learned knowledge without re-adapting to the unknown electrically driven robot dynamics is proposed to achieve the closed-loop stability and improve the control performance. Simulation studies are performed to demonstrate the effectiveness of the proposed method.

关 键 词：自适应神经网络控制 机器人 RBF神经网络 学习 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]