VOI - Voice of Indonesia | RRI - Radio Republik Indonesia

As a maritime country, Indonesia is required to be able to move quickly and efficiently in evacuating victims in an accident in the waters. In regard to this, a team of students from the Sepuluh Nopember (November Ten) Institute of Technology (ITS) created a computer vision-based autonomous ship drone for marine accident victims, called ‘YOLO-Boat’.

Andreas Raja Goklas Sitorus as the head of the YOLO-Boat design team said that this innovation is designed to assist the Search and Rescue (SAR) team in avoiding danger during the process of rescuing accident victims in the waters, especially at sea”. There are factors that can endanger the SAR team when carrying out rescues in the field, such as the weather and the location of the accident. Andreas added that this tool is designed to be able to work independently in detecting victims so that it can minimize the risk of danger in the rescue process.

 The YOLO-Boat name is an acronym from You Only Live Once. The name was chosen with the aim that this ship can be a hope for the victims. The Shipping Engineering Department student explained that YOLO-Boat uses many technologies. It uses a catamaran hull or double hull where this hull has been designed to have good stability in carrying out its mission. According to Andreas, the propulsion system uses an azimuth propulsion system that can increase the YOLO-Boat's capability to maneuver in waters. Andreas Dan and his team also designed the electrical system as efficiently as possible, both from the control system and the ship's power management. In addition, in its operations, YOLO-Boat uses the Robot Operating System (ROS) as the main framework. This ship uses several sensors that function to provide location and orientation data which will later be used in the guided navigation of the YOLO-Boat.

In using Computer Vision technology, a special object detection model was created, namely the YOLOv4 architecture based on Convolutional Neural Network (CNN). In its operation, computer vision identifies and allows YOLO-Boat to come to rescue victims.

 In its application, the YOLO-Boat must first be brought using a rescue ship to the waters designated as the accident site. Then, the YOLO-Boat will be released into the sea and begin the process of searching for victims. When the victim is detected, the YOLO-Boat will give the victim a lifebuoy. Afterwards, the YOLO-Boat sends a signal to the rescue ship to come to the location of the victim found. Ideally, it would take many YOLO-Boats working together to increase the effectiveness of rescue victims. The effectiveness of the YOLO-Boat in identifying victims is proven by its ability to detect victims even though the only part of the victim's body that can appear on the sea surface. The YOLO-Boat can operate for 44 minutes with a maximum distance of 6,780 meters. The success of making YOLO-Boat has been shown from the results of prototype testing at Kenjeran Beach in Surabaya, East Java. YOLO-Boat is able to identify and secure the volunteers who play the role of drowning victims. Thanks to this extraordinary innovation, Andreas and his team also managed to bring home a silver medal at the 2021 National Student Scientific Week (Pimnas) in the category of Student Creativity Program.