Scholarlink

An advanced control strategy based on adaptive radial basis function neural network (RBFNN) estimator and event-triggered nonlinear model predictive control (ETNMPC) is designed for the three-dimensional (3D) trajectory tracking of autonomous underwater vehicle (AUV). In real marine environment, AUV inevitably faces hybrid disturbances from external current interference and system model uncertainties. To solve this problem, RBFNN is employed to fit these hybrid disturbances and then compensated into the controller. ETNMPC is used to control the AUV to accurately track the desired trajectory, which can dynamically adjust the optimization frequency according to the tracking error, thereby reducing the computational burden and improving the energy efficiency of the controller. The simulation comparison results show that the method has improvement in AUV trajectory tracking performance and computational efficiency.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Adaptive NN-Based Estimator and ETNMPC for Three-Dimensional Trajectory Tracking of AUV with Hybrid Disturbances

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Huangzhi Yu,
  • Kunzhong Miao,
  • Hong Zhang,
  • Bo Wang,
  • Jizhou Guo,
  • Yifeng Niu

摘要

An advanced control strategy based on adaptive radial basis function neural network (RBFNN) estimator and event-triggered nonlinear model predictive control (ETNMPC) is designed for the three-dimensional (3D) trajectory tracking of autonomous underwater vehicle (AUV). In real marine environment, AUV inevitably faces hybrid disturbances from external current interference and system model uncertainties. To solve this problem, RBFNN is employed to fit these hybrid disturbances and then compensated into the controller. ETNMPC is used to control the AUV to accurately track the desired trajectory, which can dynamically adjust the optimization frequency according to the tracking error, thereby reducing the computational burden and improving the energy efficiency of the controller. The simulation comparison results show that the method has improvement in AUV trajectory tracking performance and computational efficiency.