On-line extreme learning algorithm based identification and non-linear model predictive controller for way-point tracking application of an autonomous underwater vehicle

Cognitive Computation and Systems

Biranchi Narayan Rath¹  Bidyadhar Subudhi² 

[1] Department of Electrical Engineering, National Institute of Technology Rourkela;School of Electrical Sciences Indian Institute of Technology Goa, Goa College of Engineering Campus;

关键词: position control;    path planning;    optimal control;    self-adjusting systems;    mobile robots;    three-term control;    identification;    neurocontrollers;    optimisation;    autonomous underwater vehicles;    adaptive control;    nonlinear control systems;    predictive control;    remotely operated vehicles;    regression analysis;    robot dynamics;    learning systems;    control system synthesis;    desired surveillance region;    lampc;    reported optimal controller;    inverse optimal self-tuning pid controller;    iospid controller;    way-point tracking application;    autonomous underwater vehicle;    surveillance applications;    global positioning system coordinates;    underactuated auv;    heading dynamics;    adaptive model predictive controllers;    system identification;    fast convergence rate;    robustness property;    on-line sequential extreme learning machine;    os-elm neural network modelling performance;    jaya optimisation algorithm;    forward-regression orthogonal least square;    nonlinear model predictive controller;    os-elm model;    surveying application;    line-of-sight path;    on-line extreme learning algorithm based identification;    horizontal way-points;    nampc;    error reduction ratio;    err criteria;   

DOI  :  10.1049/ccs.2018.0008

来源: DOAJ

【 摘 要 】

In most of the surveillance applications of autonomous underwater vehicle (AUV), very often it is intended to follow the desired horizontal way-points, where some oceanography data need to be collected. In view of this, the motion planning algorithm using way-points is investigated in this study. The proposed work involves identification of dynamics of AUV and design of adaptive model predictive controllers which includes linear adaptive model predictive controller (LAMPC) and non-linear adaptive model predictive controller (NAMPC). Owing to the fast convergence rate and robustness property, on-line sequential extreme learning machine (OS-ELM) is employed for estimating the dynamics of AUV. To improve the OS-ELM modelling performance, Jaya optimisation algorithm is applied to optimise the hidden layer parameters. The desired surveillance region is formulated in terms of way-points using heading angle obtained from desired line-of-sight path. Simulations are performed using MATLAB by applying proposed NAMPC, LAMPC and a previously reported optimal controller, namely inverse optimal self-tuning PID (IOSPID) controller. Subsequently, real-time experimentation is performed using a prototype AUV in a swimming pool. From the simulation and experimental results, it is observed that the proposed controller exhibit efficient tracking performance in face of actuator constraints as compared to LAMPC and IOSPID controller.

【 授权许可】

Unknown