AI based underwater Remotely Operated Vehicle (ROV) for Inspection and surveillance

Abstract: Underwater inspection and surveillance are essential in marine research, dam structure monitoring, underwater pipeline inspection, defence surveillance, and search-and-rescue operations. Conventional inspection methods rely heavily on human divers, which involve high operational risk, limited working duration, and significant cost. Industrial- grade underwater robotic systems are available; however, they are often expensive and not easily accessible for academic or small-scale applications. This paper presents the design, development, and implementation of an Artificial Intelligence (AI) Based Underwater Remotely Operated Vehicle (ROV) intended for real-time surveillance and inspection. The system integrates a waterproof mechanical structure, multi-directional thruster system, embedded microcontroller-based control unit, high-definition underwater camera, and an AI-based object detection module. The proposed ROV enables stable underwater navigation, real-time video transmission, and intelligent detection of underwater objects and anomalies. The hardware prototype is developed at an approximate cost of ₹60,000, making it significantly more affordable than industrial systems. Experimental testing in shallow freshwater environments demonstrates reliable manoeuvrability, stable video streaming, and effective AI-assisted monitoring.

Keywords: Underwater ROV, Artificial Intelligence, Object Detection, Embedded Systems, Surveillance, Marine Robotics, Real-Time Monitoring.