Perancangan Sistem Navigasi Leader-Follower berbasiskan Pedestrian Dead-Reckoning (PDR) untuk Navigasi Wheeled Mobile Robot

Farih, Muhammad (2019) Perancangan Sistem Navigasi Leader-Follower berbasiskan Pedestrian Dead-Reckoning (PDR) untuk Navigasi Wheeled Mobile Robot. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 07111540000104-Undergraduate_Theses.pdf]
Preview
Text
07111540000104-Undergraduate_Theses.pdf

Download (2MB) | Preview

Abstract

Sistem navigasi merupakan hal yang wajib dimiliki seluruh wahana tak berawak saat ini baik itu wahana darat, air, maupun udara. Sistem navigasi dapat dibagi menjadi independen dan leader-follower. Sistem pemosisian global (GPS) saat ini berperan sangat penting untuk pemosisian setiap wahana. Namun GPS memiliki kekurangan dimana sinyalnya akan terdistorsi ketika penerima GPS berada didalam ruangan. Pada penelitian ini, dirancang sistem navigasi leader-follower berbasiskan pedestrian dead-reckoning (PDR) dengan follower berupa robot beroda. Model artificial neural network digunakan sebagai model panjang langkah leader sedangkan leader heading didapat dari magnetometer. Kedua data tersebut kemudian dikirim ke follower melalui wi-fi. Model linear digunakan untuk memodelkan jarak tempuh robot dengan heading berasal dari magnetometer. Hasil percobaan menunjukkan model terbaik untuk panjang langkah adalah model ANN dengan satu hidden layer dengan empat neuron dimana memiliki eror training 4.65 cm dan eror testing 5.04 cm dengan menggunakan total 614 sampel langkah. Kemudian model jarak tempuh robot dengan regresi linear 25 data menghasilkan eror 2.0956 cm. Akhirnya eror terbesar untuk heading dari dua magnetometer dengan 28 titik pengujian adalah 39.262°.
===============================================================================================================================
Navigation systems are the first things to have for all types of unmanned vehicles whether it is land, water, or air vehicles. Navigation systems are divided to independent and leader-follower. Today, Global Positioning System (GPS) plays an important role for vehicle positioning. Nevertheless, GPS has a weakness that the signals will be distorted when the GPS receivers are located indoor environments. In this research, leader-follower navigation systems based on pedestrian dead reckoning (PDR) are designed with wheeled mobile robot as follower. Artificial Neural Network (ANN) is used as stride length model and the leader heading is obtained from magnetometer. Both data are then sent to follower through wi-fi. Linear model is used as robot distance model and follower heading are also obtained from it’s magnetometer. The test show that the best model for predicting stride length is ANN model with one hidden layer and four neuron units which has 4.65 cm training error and 5.04 cm testing error using 614 stride examples. As for robot distance model shows that the error is 2.0956 cm using 25 data samples. Finally, the biggest heading error is 39.262 ° which is tested from two magnetometers with 28 testing points.

Item Type: Thesis (Other)
Additional Information: RSE 629.893 2 Far p-1 2019
Uncontrolled Keywords: Sistem Navigasi Leader-Follower, Pedestrian Dead Reckoning, Magnetometer, Artificial Neural Network
Subjects: Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science)
T Technology > T Technology (General) > T57.5 Data Processing
T Technology > TJ Mechanical engineering and machinery > TJ211.415 Mobile robots
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5103.2 Wireless communication systems. Two way wireless communication
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7871.674 Detectors. Sensors
T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL589.2.N3 Navigation computer
Divisions: Faculty of Electrical Technology > Electrical Engineering > 20201-(S1) Undergraduate Thesis
Depositing User: Muhammad Farih
Date Deposited: 15 Mar 2023 06:43
Last Modified: 15 Mar 2023 06:43
URI: http://repository.its.ac.id/id/eprint/63693

Actions (login required)

View Item View Item