192号资源-源程序：文档+程序 USV的自动驾驶模型预测控制---------已提供下载资源

电网论文源程序

于 2024-09-30 08:15:00 发布

阅读量591

点赞数 14

分类专栏：论文与完整源程序文章标签：自动驾驶人工智能机器学习

本文链接：https://blog.csdn.net/LIANG674027206/article/details/142552982

版权

论文与完整源程序专栏收录该内容

234 篇文章 221 订阅

订阅专栏

👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆下载资源链接👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆👆

《《《《《《《《更多资源还请持续关注本专栏》》》》》》》

论文与完整源程序_电网论文源程序的博客-CSDN博客https://blog.csdn.net/liang674027206/category_12531414.html

电网论文源程序-CSDN博客电网论文源程序擅长文章解读,论文与完整源程序,等方面的知识,电网论文源程序关注python,机器学习,计算机视觉,深度学习,神经网络,数据挖掘领域.https://blog.csdn.net/LIANG674027206?type=download

USV（无人水面艇）的自动驾驶模型预测控制（MPC）是一个前沿的研究领域，旨在实现无人水面艇在复杂水域中的自主导航和控制

。该项目结合了文档和程序，探索如何利用模型预测控制技术来优化USV的航行路径和行为。 MPC的核心在于实时预测和优化控制输入，通过动态模型和状态反馈来调节USV的航向、速度和位置。考虑到水面环境的不确定性，如波浪、风力和水流，MPC能够根据实时数据进行调整，从而提高控制精度和响应速度。

此外，该系统通常需要集成传感器数据，以实时更新环境状态，确保安全航行。在此项目中，文档部分可能包含理论背景、算法细节及应用案例，而程序部分则涉及具体的控制算法实现和模拟实验。这种结合不仅提供了理论支持，也为工程实践提供了可操作的工具。

总之，USV的自动驾驶模型预测控制是一个综合性强的研究方向，旨在推动无人水面艇技术的发展，提升其在航运、监测和救援等领域的应用潜力。

部分代码展示：

%%%%%%%%%%%%% - USV autonomous control algorithm using MPC - %%%%%%%%%%%%%%
%%% This code use and MPC algorithm to track an angle reference while   %%% 
%%% keeping a constant cruise speed.                                    %%% 
%%% Written by Colin Calas at Cardiff University on August 2017         %%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%%% TODO :
%%%     - Add the cruise velocity to the MPC
%%%     - Test with a testbench path

%Clean the workspace and close the open figures
clear
close all

%Boat and simulation parameters
m = 37;         %Mass of the boat
D = 0.7;        %Distance between the motors and the center of mass
I = 0.1;        %Moment of inertia      (arbitrary value, should be identified)
k = 0.1;        %Viscosity coefficient  (arbitrary value, should be identified)
ky = 0.1;       %Viscosity coefficient on the y axis (arbitrary value, should be identified)
Tfinal = 150;   %Total simulation time
Te = 0.1;       %Sampling period

%Vectors used to hold simulation data
x = zeros(9, ceil(Tfinal/Te));          %State vector
u = zeros(2, ceil(Tfinal/Te));          %Input vector
delta_u = zeros(2, ceil(Tfinal/Te));    %Input increment vector
a = zeros(3, ceil(Tfinal/Te));          %State vector
a_ref = zeros(1, ceil(Tfinal/Te));
i = 1;                                  %Loop index



%Ordered list of waypoints
x_list = [2 4 32 40 25 10 2]';  %X coordinates of the waypoints
y_list = [2 15 17 7 0 -5 2]';   %Y coordinates of the waypoints
a_list = zeros(7,1);            %Angle of the boat between two successive waypoints
current_obj = 2;                %As the boat starts in the first waypoint, the current objective is the next
                                %ie. the second waypoint

%Compute all the angles between two successive waypoints
%The angles returned are between -pi and pi
for j=1:7
   a_list(mod(j,7)+1,1) = angle(complex(x_list(mod(j,7)+1)-x_list(j), y_list(mod(j,7)+1)-y_list(j)));
   
   if a_list(j,1) < 0
      a_list(j,1) = a_list(j,1);
   end
end

%Objectives list containing X,Y and Theta coordinates
r_list = [x_list y_list a_list];
nb_obj = size(r_list,1);                %Number of objectives

%MPC horizons
nu = 2;         %Control horizon (dof of the optimization problem)  
ny = 30;        %Prediction horizon

%State-space system used for the MPC
a(:,i) = [0 0 1.4181]';                 %Initial conditions : the boat is in the correct orientation
                                        %And has null angular speed and acceleration
u(:,i) = [k/2 k/2]';                    %Initial condition on the command : to maintain a speed of 1m/s
delta_u(:,i) = [0 0]';                  %Initial condition on the input increments

效果展示