The 6-degrees-of-freedom (6-DOF) motion platform system utilizes six types of motion—heave, roll, pitch, surge, sway, and yaw—to replicate real-world environmental movements and verify the operational durability and reliability of test products. Possesses Korea’s only proprietary 8-axis expansion technology (6-DOF + 2 additional axes), developed in-house. Duratek designs and manufactures fully domestic electric motion platforms, with integrated capabilities covering software control, user interface (UI), and sensor fusion technologies.

AI-based Intelligence, Surveillance and Reconnaissance Equipment

This product is designed and manufactured specific for customers’ demand and includes the power supply and signal transmission parts of weapon systems in all fields of the Korean army, navy, and air force, as well as for the civilian field. As all parts are localized and assembled into finished products, they are ensured of best performance and reliable quality.

It is designed to be suitable for difficult environments and can be applied to high torque and angle control. Applications are Missile defense, Torpedoes, Anti-drones system, Underwater drones.

STANAG 4695 & GOSSRA* * GENERIC OPEN SOLDIER SYSTEM REFERENCE ARCHITECTURE compatible with Nett Warrior BREAK-AWAY CONNECTOR

Based on our state-of-the-art facilities, the semi-conductor machinery component sector manufatctures parts including Chamber assembly, and Main Frame Assembly.

With more than 33,000 delivered to date, CFM56® engines mainly power single-aisle commercial jets from Airbus and Boeing. The CFM56®, developing 18,500 to 33,000 lb of thrust, set a standard in this market. It owes its impressive success to exceptional performance and reliability, the result of the two partners' technical excellence.

In collaboration with Hanwha Systems, we developed and optimized a Transformer-based AI model for ship and aircraft detection on embedded platforms. Targeting NVIDIA Jetson Orin AGX, the project utilized the MSAR (640×640) dataset along with large-scale training databases built from public sources. The RT-DETR model, currently under review, was optimized through hardware-friendly design, Int8 quantization, and specialized inference acceleration. As a result, the solution achieved up to 5x faster inference speed while maintaining accuracy, reaching 20% of NVIDIA TensorRT performance. This demonstrates the ability to deliver reliable, real-time detection capabilities in resource-constrained embedded environments, enabling next-generation defense and surveillance applications.