<![CDATA[The development of robotics technology, especially in the field of autonomous vehicles, has made rapid progress in recent years. This study focuses on the development of a trajectory detection and localization system on an Autonomous Surface Vehicle (ASV) using the Robot Operating System (ROS) and the You Only Look Once algorithm version five (YOLOv5). ASV is an autonomous surface vehicle used for various applications, such as underwater mapping and environmental monitoring. In this study, ROS is implemented as a hardware and software integration platform to improve the accuracy of object detection and localization, especially the red and green buoys as trajectory boundaries. Testing was carried out in a real environment to assess the performance of the system, which was previously only based on simulation. The results showed that the integration of ROS and YOLOv5 increased the navigation speed of the ASV, with an increase in the average travel time from 1 minute 16.2 seconds to 1 minute 11.2 seconds, and the success of object detection reached 70% out of 50 trials. This study contributes to the development of ASV technology by increasing the accuracy, efficiency, and reliability of the system in detecting and localizing objects in complex trajectory areas.]]>
Copyrights © 2024
