Robot Boat Prototype System Based on Image Processing for Maritime Patrol Area

Enhancing maritime patrol to strengthen state border security has shown numerous interests over the year. Marine patrol is crucial in raising maritime awareness and surveying what is happening in the vast Indonesian sea area. Ship detection and identification are essential for marine patrol dealing with maritime traffic, sea border activity, and illegal fishery. Because of that, object detection integrated with the autonomous surface vehicle, like robot boats, is an advantageous method used in marine patrol. The robot boat used an object detection algorithm processed by Jetson Nano to determine its navigation. Preliminary experiments are conducted to verify if the proposed method can recognize an object and patrol the surrounding area in real-time using the integrated surface robot.

I. Introduction

Marine patrol is an urgent matter regarding the safety of a country’s border in marine areas, especially in Indonesia, which consists of over 70% of its territory with sea area [1]. The vast area of the Indonesian sea may cause several marine legal issues, such as undetected surface vehicles, safety concerns of the ship crew and consideration of the labor cost used for operations. Therefore, the development of artificial intelligent technology implemented in Unmanned Surface Vehicle (USV) provides possible solutions for operational efficiency in marine patrol. Additionally, USV embedded with AI improves navigators’ awareness to predict avoidance and capabilities encountering risks of possible collisions [2]. Marine security patrol areas are best observed using visual perception to understand the surrounding environment, but AI can improve final judgment due to the limitations of human vision [3]. In solving the problem, it is essential to achieve the goal for the following problem: (1) the detection of an object and (2) the development of the robot boat.