基于神经网络的四旋翼无人机环绕跟踪控制  

Neural network based encircling tracking control with quadrotor UAV

作　　者：谭华 曹志斌 孙山林[1,2] TAN Hua;CAO Zhibin;SUN Shanlin(School of Aeronautics and Astronautics,Guilin University of Aerospace Technology,Guilin 541004,China;Guangxi Colleges and Universities Key Laboratory of Unmanned Aerial Vehicle(UAV)Remote Sensing,Guilin 541004,China;School of Computer Science and Information Security,Guilin University of Electronic Technology,Guilin 541004,China)

机构地区：[1]桂林航天工业学院航空宇航学院,广西桂林541004 [2]广西高校无人机遥测重点实验室,广西桂林541004 [3]桂林电子科技大学计算机与信息安全学院,广西桂林541004

出　　处：《现代电子技术》2025年第5期135-141,共7页Modern Electronics Technique

基　　金：国家自然科学基金项目(61966010);广西重点研发计划基金项目(2021AB33013);广西高校中青年教师科研基础能力提升项目(2022KY0793)。

摘　　要：针对参数不确定性和外部环境干扰影响下的四旋翼无人机目标跟踪问题,提出一种基于神经网络的四旋翼无人机目标环绕跟踪控制方法,并设计了具有三级闭环控制结构的四旋翼无人机目标环绕跟踪抗干扰控制器。根据四旋翼无人机的运动/动力学模型和跟踪目标对应的坐标建立无人机目标跟踪基本模型。结合导航向量场原理并引入四旋翼无人机位置信息反馈回路,构建基于导航向量场的动态反馈控制器。同时,为了消除四旋翼无人机位置环和姿态环受到的集总扰动影响,引入基于最小参数学习的自适应神经网络干扰观测器进行在线估计与补偿,以构建基于神经网络干扰观测器的轨迹和姿态跟踪控制器。通过仿真验证了该控制方法的有效性,仿真结果表明该控制方法能有效地实现四旋翼无人机对目标的环绕跟踪,而且具有较强的抗干扰性和鲁棒性。The target tracking with quadrotor UAV is confronted with parameter uncertainty and external environment disturbance,so a neural network based method for target encircling tracking control with quadrotor UAV is proposed,and an anti-disturbance controller with a three-level closed-loop control structure for target encircling tracking with quadrotor UAV is designed.According to the motion/dynamics model of the quadrotor UAV and the coordinates corresponding to the target under tracking,the basic model of UAV target tracking is established.In combination with the principle of guiding vector field(GVF),a dynamic feedback controller based on GVF is constructed by introducing the position information feedback loop of the quadrotor UAV.An adaptive neural network interference observer based on minimum parameter learning is introduced for online estimation and compensation,so that the influence of aggregate disturbances on the position loop and attitude loop of quadrotor UAV can be eliminated,and a trajectory and attitude tracking controller based on a neural network interference observer is constructed.The effectiveness of the control method is verified by simulation.The simulation results show that the proposed approach can effectively achieve target encircling tracking with quadrotor UAV while exhibiting strong disturbance rejection and robustness.

关 键 词：四旋翼无人机 神经网络 目标跟踪 环绕控制 动态反馈 导航向量场 

分 类 号：TN876.3-34[电子电信—信息与通信工程] V271.4[航空宇航科学与技术—飞行器设计]