Rancang Bangun Model Deep Learning Pada Sistem Navigasi Mobil Otonom Dengan Sensor Kamera

Winangun, I Made Guna (2021) Rancang Bangun Model Deep Learning Pada Sistem Navigasi Mobil Otonom Dengan Sensor Kamera. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

Text 07111740000050_Undergraduate_Thesis.pdf Restricted to Repository staff only until August 2023. Download (3MB) | Request a copy

Abstract

Fenomena yang melatar belakangi penelitian ini yaitu susahnya computer vision dalam menavigasi mobil pada situasi yang belum pernah dilalui oleh mobil sebelumnya. Untuk mengatasi fenomena tersebut diperlukan pendekatan baru dalam menavigasi mobil. Pendekatan tersebut yaitu penggunaan deep learning dalam menavigasi mobil. Pada penelitian ini didapatkan suatu rancangan model deep learning yang dapat menavigasi mobil. Model menggunakan salah satu arsitektur deep learning yaitu convolutional neural network. Model ini dilatih berdasarkan data yang didapat dari simulator. Data yang diambil adalah data berupa arah kemudi dengan gambar yang berasal dari kamera yang terpasang pada mobil di simulator. Dengan adanya model ini, mobil dapat dikatakan sebagai mobil otonom karena dapat menavigasi dirinya sendiri. Model ini memiliki validasi galat sebesar 0.0827 derajat. Model ini dapat menavigasi mobil dengan baik pada kecepatan 15 – 20 satuan kecepatan pada simulator.
==================================================================================================================
The phenomenon behind this research is the difficulty of computer vision in navigating a car in a situation that has never been passed by a car before. To overcome this phenomenon requires a new approach in navigating the car. The approach is the use of deep learning in navigating the car. In this study, we obtained a design of a deep learning model that can navigate the car. The model uses one of the deep learning architectures, namely convolutional neural network. This model is trained based on the data obtained from the simulator. The data taken is data in the form of steering direction with images coming from the camera installed on the car in the simulator. With this model, the car can be said to be an autonomous car because it can navigate itself. This model has a validation error of 0.0827 degrees. This model can navigate the car well at 15 – 20 speed units on the simulator.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Deep Learning, Mobil Otonom, Navigasi, Sensor Kamera, Autonomous Car, Camera Sensors, Deep Learning, Navigation
Subjects:	A General Works > AI Indexes (General) A General Works > AI Indexes (General) T Technology > T Technology (General) > T57.5 Data Processing T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5102.9 Signal processing. T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101 Telecommunication T Technology > TL Motor vehicles. Aeronautics. Astronautics > TL589.2.N3 Navigation computer
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20201-(S1) Undergraduate Thesis
Depositing User:	I Made Guna Winangun
Date Deposited:	19 Aug 2021 02:48
Last Modified:	19 Aug 2021 02:48
URI:	http://repository.its.ac.id/id/eprint/87344

Actions (login required)

View Item