Obstacle Tracking pada Unmanned Surface Vehicle Menggunakan Filter Kalman

Jagad, Gaung (2020) Obstacle Tracking pada Unmanned Surface Vehicle Menggunakan Filter Kalman. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[img] Text
07111640000079-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only

Download (3MB) | Request a copy

Abstract

Unmanned Surface Vehicle (USV) merupakan salah satu kendaraan tanpa awak yang beroperasi di atas permukaan air. USV dapat dikendalikan secara manual atau diberikan panduan dari jarak jauh atau beroperasi sendiri secara otonom. Agar dapat beroperasi secara otonom, USV memiliki serangkaian sistem pemanduan yang berfungsi untuk merencanakan lintasan agar kapal dapat mencapai titik tujuan. Kemampuan untuk mendeteksi halangan pada lintasan USV merupakan salah satu faktor yang krusial untuk merencanakan lintasan baru agar dapat menghindari halangan serta mencapai tujuan secara optimal. Sensor yang digunakan oleh USV untuk mendeteksi halangan dapat berupa kamera dan LiDar untuk mendeteksi posisi halangan pada lingkungan sekitar kapal. Pada penelitian ini dirancang sistem tracking halangan yang terdeteksi dengan mengintegrasikan sensor kamera dan LiDar untuk mengestimasi posisi relatif halangan terdeteksi dari kapal. Sistem yang dirancang juga mengestimasi lebar dari halangan yang terdeteksi. Informasi hasil tracking halangan pada lingkungan sekitar kapal selanjutnya dapat digunakan untuk menghindari halangan pada lintasan kapal. Untuk meningkatkan akurasi estimasi posisi relatif halangan dari kapal, digunakan filter Kalman untuk mengurangi noise pada pengukuran. Kemudian hasil rancangan sistem disimulasikan menggunakan software MATLAB sehingga dapat dianalisa performa dari sistem yang dirancang. Didapatkan hasil filter Kalman mengurangi noise pengukuran sebesar 12% dengan matriks kovarian Q = [2 0 0 0; 0 20 0 0; 0 0 2 0; 0 0 0 20] dan R =[1 0 0 0; 0 10 0 0; 0 0 1 0; 0 0 0 10]. ========================================================== Unmanned Surface Vehicles (USV) are one of the unmanned vehicles that operates on the water surface. USV can either be remote controlled or remote guided, or operating autonomously on their own. In order to be operated autonomously, USV has guidance system designed for path planning to reach its destination. The ability to detect obstacles in its paths is one of the important factors to plan a new path in order to avoid obstacles and reach its destination optimally. Sensors used by USV to detect obstacles consists of cameras and LiDars to locate the position of obstacles in the environment around the ship. This research will design an obstacle tracking system which is designed by integrating the sensors, camera and LiDar to estimate the relative position of the obstacle to the ship. The system designed will also estimate the width of the detected obstacle. Informations acquired from obstacle tracking on the environment around the ship can be used to avoid obstacles in its path. To improve the relative posisition estimation of the obstacles to the ship, a Kalman filter will be applied to reduce the measurements noises. Then the results of the system designed will be simulated using MATLAB software so that results can be analyzed to see the performance of the system designed. Results obtained using Kalman filter shows 12% noise reduction with covariance matrice Q = [2 0 0 0; 0 20 0 0; 0 0 2 0; 0 0 2 0] and R =[1 0 0 0; 0 10 0 0; 0 0 1 0; 0 0 0 10].

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Unmanned Surface Vehicle, Obstacle Tracking, filter Kalman.
Subjects: Q Science > QA Mathematics > QA402.3 Kalman filtering.
T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques
U Military Science > UG1242 Drone aircraft--Control systems. (unmanned vehicle)
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20201-(S1) Undergraduate Thesis
Depositing User: Gaung Jagad
Date Deposited: 13 Aug 2020 03:40
Last Modified: 13 Aug 2020 03:40
URI: http://repository.its.ac.id/id/eprint/77826

Actions (login required)

View Item View Item