The maritime sector forms the backbone of India’s trade, handling about 95% of the country’s commerce. While there’s plenty of research on ship route planning, there aren’t many applications specifically designed for the Indian Ocean Region. One major challenge in maritime navigation obstacles in constantly changing sea conditions. To tackle this, we developed a hybrid system that combines Deep Q-Networks (DQN) and the Vector Field Algorithm (VFA). The system operates in two parts: VFA calculates forces that guide the ship towards its destination while steering it away from obstacles. Meanwhile, DQN helps the ship make intelligent decisions by learning from experience and considering factors such as ocean currents, wind, and moving obstacles. We tested this system in a simulated ocean environment modeled as a grid. The results were promising. Ship can successfully reach their destinations 81% of the time, with only a 10% collision rate. This performance is significantly better than using either method alone. The benefits of our system include safer navigation and a better ability to handle complex situations at sea. Because the DQN part keeps learning, the system gets better over time at finding the best routes. This makes our approach promising for the future of automated ship navigation and shipping logistics.