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 3D 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.
2021,43(11): 96-99 收稿日期：2020-11-13
DOI：10.3404/j.issn.1672-7649.2021.11.017
分类号：TP242
作者简介：周则兴(1995-)，男，助理工程师，主要研究潜水器与无人艇水动力与控制技术
参考文献：
[1] YUH J. Design and control of autonomous underwater robots: A survey[J]. Autonomous Robots, 2000, 8(1): 7–24
[2] NAKAMURA Y, SAVANT S. Nonlinear tracking control of autonomous underwater vehicles[C]// Robotics and Automation, 1992. Proceedings, 1992 IEEE International Conference, 1992(3): A4-A9.
[3] 夏国清, 杨莹, 赵为光. 欠驱动AUV模糊神经网络L_2增益鲁棒跟踪控制[J]. 控制与决策, 2013(3): 351–356
[4] 万磊, 崔士鹏, 张国成, 等. 欠驱动水下机器人航迹跟踪控制[J]. 电机与控制学报, 2013, 17(2): 103–111
[5] 张勋, 边信黔, 唐照东, 等. AUV均衡系统设计及垂直面运动控制研究[J]. 中国造船, 2012, 53(1): 28–36
[6] 陈东, 向先波, 郑金荣, 等. 欠驱动AUV三维轨迹跟踪控制[C]// 第三十二届中国控制会议, 2013: 6.
[7] 曾文静, 徐玉如, 万磊, 等. 自主式水下机器人的光视觉管道探测跟踪系统[J]. 上海交通大学学报, 2012(2): 178–183+189
[8] 唐旭东. 智能水下机器人水下管道检测与跟踪技术研究[D]. 哈尔滨: 哈尔滨工程大学, 2011.
[9] 张汝波, 李建军, 杨玉. 基于改进蚁群算法的 AUV 航路避障任务规划[J]. 华中科技大学学报(自然科学版), 2015(s1): 428–430
[10] XIANG X, LAPIERRE L, JOUVENCEL B J R. Smooth transition of AUV motion control: From fully-actuated to under-actuated configuration[J]. Robotics Autonomous Systems, 2015, 67: 14–22
[11] XU J, WANG M, QIAO L. Dynamical sliding mode control for the trajectory tracking of underactuated unmanned underwater vehicles[J]. Ocean Engineering, 2015, 105: 54–63
[12] SHOJAEI K, DOLATSHAHI M. Line-of-sight target tracking control of underactuated autonomous underwater vehicles[J]. Ocean Engineering, 2017, 133: 244–252
[13] 王宏健, 陈子印, 贾鹤鸣, 等. 基于滤波反步法的欠驱动AUV三维路径跟踪控制[J]. 自动化学报, 2015(3): 631–645
[14] 贾鹤鸣, 张利军, 齐雪, 等. 基于神经网络的水下机器人三维轨迹跟踪控制[J]. 控制理论与应用, 2012, 29(7): 56–62
[15] FOSSEN T I. Handbook of Marine Craft Hydrodynamics and Motion Control[M]. 2011.
[16] BREIVIK M, FOSSEN T I: Guidance-based path following for autonomous underwater vehicles[J]. Oceans, 2005(1-3): 2807−2814.
[17] BREIVIK M, FOSSEN T I, Ieee: A unified control concept for autonomous underwater vehicles[J]. American Control Conference, 2006(1-12): 4920.
[18] 李岳明, 庞永杰, 万磊. 水下机器人自适应S面控制[J]. 上海交通大学学报, 2012(2): 195–200+206
