Rafid, Firzannabeel Aqila (2026) DESIGN AND IMPLEMENTATION OF AN AUTOMATIC BICYCLE BRAKING SYSTEM USING YOLOV11N AND ESP32 BASED ON HG680P SET-TOP BOX. Undergraduate thesis, Universitas Pembangunan Nasional Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text
22081010285_cover.pdf Download (1MB) |
|
Text (Bab 1)
22081010285_bab 1.pdf Download (444kB) |
|
Text (Bab 2)
22081010285_bab 2.pdf Restricted to Repository staff only until 25 June 2028. Download (931kB) |
|
Text (Bab 3)
22081010285_bab 3.pdf Restricted to Repository staff only until 25 January 2028. Download (798kB) |
|
Text (Bab 4)
22081010285_bab 4.pdf Restricted to Repository staff only until 25 June 2028. Download (1MB) |
|
Text (Bab 5)
22081010285_bab 5.pdf Download (286kB) |
|
Text (Daftar Pustaka)
22071010285_daftar pustaka.pdf Download (277kB) |
|
Text (Lampiran)
22081010285_lampiran.pdf Restricted to Repository staff only Download (500kB) |
Abstract
Bicycle rider safety, particularly for young children, represents a highly significant concern due to the high risk of accidents caused by delayed human reaction times when encountering sudden obstacles on the road. To address this, this research successfully designs and implements an intelligent automatic braking system for bicycles using the advanced YOLOv11n object detection algorithm executed on a Set-top Box HG680P as a localized edge computing device, utilizing an ESP32 microcontroller for interfacing the hardware sensors and actuators. The system effectively employs a sensor fusion approach integrating a standard USB camera for visual input, an HC-SR04 ultrasonic sensor for distance measurement, and an MG-996R servo motor acting as the mechanical braking actuator. Comprehensive experimental results show the STB HG680P performs YOLOv11n inference in real-time at 3.9 FPS with a system latency of 312 ms. The detection system achieved an accuracy of 95.0%, precision of 95.96%, and recall of 92.24% based on confusion matrix evaluation, while the ultrasonic sensor recorded an average accuracy of 98.9% over a 20 to 250 cm range. This empirical study confirms that the STB HG680P is a viable, practical, and highly cost effective edge computing platform for running YOLO based artificial intelligence models in lightweight vehicle safety applications. Keywords: Edge Computing, YOLO, Set-Top Box, Microcontroller, ESP32, Automatic Brake
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science | ||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||||||
| Depositing User: | firzan F W | ||||||||||||
| Date Deposited: | 25 Jun 2026 07:36 | ||||||||||||
| Last Modified: | 25 Jun 2026 08:22 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/54207 |
Actions (login required)
 |
View Item |