DEVELOPMENT OF OBSTACLE DETECTION SYSTEM WITH 3D LIDAR CAMERA BASED ON MACHINE VISION
Health services are one of the important aspects in ensuring public welfare. However, amidst the dynamics of population growth and the complexity of health challenges, the problem of the lack of health workers is a major focus. The development of medical technology is one of the solutions that is be...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/83621 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Health services are one of the important aspects in ensuring public welfare. However, amidst the dynamics of population growth and the complexity of health challenges, the problem of the lack of health workers is a major focus. The development of medical technology is one of the solutions that is being widely developed. One of the medical technologies to deal with the problem of health workers is the development of medical robots. Medical robot technology consists of several features that can overcome the problem of the shortage of medical personnel. One of the features found in medical robots is the obstacle detection system. This study aims to develop an obstacle detection system using a 3D LiDAR camera integrated with the Robot Operating System (ROS) and the YOLOV8 detection algorithm. The machine sensing system is an integration between a 3D LiDAR camera and the YOLOV8 Algorithm. This system is designed to improve the robot's navigation ability to avoid obstacles in indoor environments. The 3D LiDAR camera is used as the main sensor to detect and map obstacles around the robot. The YOLOV8 algorithm is used to improve the ability to detect objects from visual data obtained by the 3D LiDAR camera. The ROS algorithm is able to measure the distance of obstacles in front of the robot using a 3D LiDAR camera with an accuracy of 97 - 99%. The YOLOV8 model successfully detected doors and tables with 90% and 92% accuracy, respectively. The system algorithm built was able to calculate the door width and table height with 94-96%. The system built is expected to be implemented in various autonomous robots operating in indoor environments to improve safety and navigation efficiency.
Keywords: Medical Robot, 3D LiDAR Camera, ROS, YOLOV8, Obstacle Detection, Navigation.
?
|
|---|