基于DRNN-S控制的AUV三维轨迹跟踪方法  

3D trajectory tracking based on DRNN-S control for autonomous underwater vehicles

作　　者：周则兴 ZHOU Ze-xing(China Ship Scientific Research Center,Wuxi 214082,China)

机构地区：[1]中国船舶科学研究中心,江苏无锡214082

出　　处：《舰船科学技术》2021年第21期96-99,178,共5页Ship Science and Technology

摘　　要：本文基于对角回归神经网络(Diagonal Recurrent Neural Networks,DRNN)和自适应S面控制器与虚拟目标法,研究了欠驱动自主水下机器人(Autonomous Underwater Vehicle,AUV)的三维轨迹跟踪控制问题,并讨论了该非线性无模型控制器的效果。首先给出六自由度欠驱动AUV的动力学模型,之后建立三维轨迹跟踪运动误差方程。为验证轨迹跟踪效果,基于DRNN-S控制器进行了运动仿真.该控制器无需先验动力学模型信息,具有一定的鲁棒性,并能较好地克服模型不确定带来的影响。仿真结果显示,DRNN-S控制器能以较高精度完成欠驱动AUV三维曲线轨迹跟踪任务。This paper studies target tracking control method of under-actuated AUVs(autonomous underwater vehicles),based on DRNN(diagonal recurrent neural networks),adaptive S-plane controller and virtual target method.And the effect of the nonlinear modeless controller is discussed.The first,a dynamics model of 6-degree-of-freedom under-actuated AUVs is given.Then,the 3 D trajectory tacking error equations are established base on virtual target method.In order to verify the trajectory tracking effect,the motion simulations are performed based on the DRNN-S hybrid controller,which does not need a priori knowledge of vehicle dynamics and parameters.This hybrid controller is robust and can overcome the influence of model uncertainty.The results of simulations show that the trajectory tracking task can be completed with high precision based on DRNN-S controller for an under-actuated AUV.

关 键 词：自主水下机器人 三维轨迹跟踪 虚拟目标法 DRNN-S控制 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]