Rizki, Mochammad Sudrajat Dwi (2019) Kontrol Pergerakan Omni-Directional Wheels Robot Berdasar Citra Obyek. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
07111240000044-Undergraduate_Theses.pdf Download (2MB) | Preview |
Abstract
Kebakaran merupakan salah satu kecelakaan yang dapat menyebabkan kerugian besar. Kebakaran dapat disebabkan oleh kebocoran gas yang mudah terbakar. Gas yang mudah terbakar dapat ditemukan di media seperti botol sehingga proses pendeteksian gas yang mudah terbakar dapat dilakukan dengan menggunakan kamera untuk menangkap gambar objek di mana ada gas yang mudah terbakar. Dalam penelitian ini, kontrol roda omni-directional robot berdasarkan gambar objek dilakukan pada platform segitiga dengan tiga roda omni yang dilengkapi dengan sensor gas Figaro TGS2600, kamera, dan Raspberry Pi 3 Model B. Gambar yang diambil oleh kamera adalah digunakan untuk deteksi objek dengan metode RGB dan HSV yang dinormalisasi. Sistem ini mampu mendeteksi gambar objek di lingkungan dengan intensitas cahaya di kisaran 0,6 - 57,9 lux. Sistem tidak dapat mendeteksi gambar objek di lingkungan dengan intensitas cahaya di kisaran 0-0,2 lux. Ukuran tinggi gambar botol (piksel) berkurang dengan meningkatnya jarak dari robot. Sensor gas mampu mendeteksi alkohol gas dalam kisaran 10-50cm. Dalam pengujian keseluruhan dengan posisi objek pada sudut 90, jarak 3 meter, dan intensitas cahaya 60,9 lux, tingkat keberhasilan gerakan robot menuju objek dan berhenti di dekat objek adalah 100%. Tingkat keberhasilan robot untuk mendeteksi gas alkohol adalah 80%.
================================================================================================
Fire is one of the accidents that can cause large losses. Fires can be caused by leaks of flammable gas. Flammable gas can be found in media such as bottles so that the process of detecting flammable gases can be carried out using a camera to capture image of object where combustible gases are present. In this study, control of the robot's omni-directional wheels based on object image was carried out on a triangular platform with three omni wheels equipped with Figaro TGS2600 gas sensor, camera, and Raspberry Pi 3 Model B. The image captured by the camera was used for object detection with the Normalized RGB and HSV method. The system is able to detect object images in the environment with light intensity in the range 0.6 - 57.9 lux. The system cannot detect object images in the environment with light intensity in the range 0-0.2 lux. The height size of the bottle image (pixel) decreases with increasing distance from the robot. The gas sensor is able to detect gas alcohol in the range of 10-50cm. In the overall test with the position of the object at an angle of 90, a distance of 3 meters, and light intensity of 60.9 lux, the success rate of the robot movement goes to the object and stops near the object is 100%. The success rate of the robot to detect alcohol gas is 80%.
| Item Type: | Thesis (Undergraduate) |
|---|---|
| Additional Information: | RSE 629.892 Riz k-1 2019 |
| Uncontrolled Keywords: | omni-directional wheels robot, normalized RGB, HSV, Raspberry Pi 3 Model B |
| Subjects: | T Technology > TA Engineering (General). Civil engineering (General) > TA1637 Image processing--Digital techniques T Technology > TJ Mechanical engineering and machinery > TJ211 Robotics. T Technology > TJ Mechanical engineering and machinery > TJ211.415 Mobile robots T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7882.P3 Pattern recognition systems |
| Divisions: | Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Electrical Engineering > 20201-(S1) Undergraduate Thesis |
| Depositing User: | Rizki Mochammad Sudrajat Dwi |
| Date Deposited: | 23 Mar 2022 09:09 |
| Last Modified: | 23 Mar 2022 09:09 |
| URI: | http://repository.its.ac.id/id/eprint/62215 |
Actions (login required)
 |
View Item |