CHENNAI: In a step towards advancing autonomous shipping, researchers at the Indian Institute of Technology Madras (IIT-M) have developed a digital twin platform that can simulate real-world maritime conditions, enabling autonomous navigation systems to be tested and trained without the cost and risks associated with trials at sea.
Named SEANAV (Sea Navigation), the platform, developed by the Department of Ocean Engineering, recreates ocean conditions, vessel movements and shipping traffic in a virtual environment. It enables researchers to test navigation algorithms, evaluate collision-avoidance strategies and train both autonomous systems and human operators.
The development comes amid India’s efforts to modernise its maritime infrastructure under the Sagarmala Programme and Maritime India Vision 2030, which place emphasis on smart ports, digital technologies and safer shipping operations. The global shipping industry carries more than 80% of world trade, underlining the importance of improving navigational safety and efficiency.
Built on the Unity3D engine, SEANAV has been calibrated using a benchmark tanker measuring around 320 metres long. Its multi-sensor framework integrates inputs from LiDAR and stereo-vision cameras to detect nearby vessels and assess their positions. The system uses sensor-fusion techniques, including a Kalman filter, to improve the reliability of navigation information.
An important component of the research is DetectShips, a dataset containing 14,000 real-world ship images developed to support ship detection and classification. The researchers have also examined the performance of computer-vision models under varying lighting conditions and visual obstructions.
Unlike conventional simulators that assume perfect sensor inputs, SEANAV accounts for practical limitations such as noise and delays. It also incorporates marine radar and a virtual reality interface powered by Meta Quest headsets, allowing maritime professionals to experience simulated ship-bridge environments and train for vessel manoeuvring, port approaches and emergency situations.
The research team has demonstrated autonomous path-following and AI-driven collision avoidance under simulated wave and sensing conditions. Its multi-vessel simulation capabilities could also support research into navigation in congested shipping channels, coastal surveillance and search-and-rescue operations.
“SEANAV provides a realistic and scalable platform for developing and validating autonomous maritime navigation technologies. By combining digital twins, AI, advanced sensor fusion and virtual reality, we are creating an environment where both autonomous systems and human operators can be trained safely and efficiently before deployment in real-world maritime settings,” said Suresh Rajendran, associate professor, Department of Ocean Engineering, IIT-M, who led the research. “The technology can eventually support AI-assisted navigation at major Indian ports, including Chennai, Mumbai, Visakhapatnam and Kochi, helping reduce collision and grounding risks. Improved navigation strategies can also lower fuel consumption, carbon emissions and the risk of environmental accidents.”
The multisensor-fusion findings were published in the peer-reviewed Journal of Offshore Mechanics and Arctic Engineering. Related research was presented at international conferences in Vancouver in 2025 and Tokyo in 2026.