首页> 外文期刊>Neural computing & applications >Decentralized robust optimal control for modular robot manipulators via critic-identifier structure-based adaptive dynamic programming
【24h】

Decentralized robust optimal control for modular robot manipulators via critic-identifier structure-based adaptive dynamic programming

机译:通过批评标识符结构的自适应动态编程模块化机器人操纵器的分散鲁棒优化控制

获取原文
获取原文并翻译 | 示例
           

摘要

This paper presents a decentralized robust optimal control method for modular robot manipulators (MRMs) via a critic-identifier structure-based adaptive dynamic programming (ADP) scheme. The robust control problem of MRMs is transformed into an optimal compensation control issue, which consists of model-based compensation control, identifier-based learning control and ADP-based optimal control. The dynamic model of MRMs is deployed for each joint module where the local dynamic information is utilized to design the model compensation controller. A neural network (NN) identifier is established to approximate the interconnected dynamic coupling. Based on ADP and local online policy iteration algorithm, the Hamiltonian-Jacobi-Bellman equation is solved by constructing a critic NN, and then the approximate optimal control policy derivation is possible. The closed-loop robotic system is asymptotic stable by the implementation of a set of developed decentralized control policies. Simulations are presented to demonstrate the effectiveness of the proposed method.
机译:本文通过批评标识符结构的自适应动态编程(ADP)方案介绍了一种用于模块化机器人机械手(MRMS)的分散的鲁棒优化控制方法。 MRM的稳健控制问题转变为最佳补偿控制问题,由基于模型的补偿控制,基于标识符的学习控制和基于ADP的最优控制组成。为每个接合模块部署MRM的动态模型,其中利用本地动态信息来设计模型补偿控制器。建立神经网络(NN)标识符以近似于互连的动态耦合。基于ADP和本地在线策略迭代算法,通过构建批评NN来解决Hamiltonian-jacobi-Bellman方程,然后可以实现近似最佳控制策略推导。闭环机器人系统是通过实施一套发达的分散控制政策的渐近稳定性。提出了模拟以证明所提出的方法的有效性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号