NATO Demonstration of Synthetic Aperture Sonar Made Possible by GE GPGPU Technology

The CMRE Autonomous Mine Search Using High-Frequency Synthetic Aperture Sonar project focuses on increasing the efficiency and effectiveness of the full range of mine search missions. This is accomplished in part by greatly improving the processing and decision-making capabilities on-board the MUSCLE (Minehunting UUV for Shallow water Covert Littoral Expeditions) Autonomous Underwater Vehicle (AUV), which uses multi-resolution, multi-aspect Synthetic Aperture Sonar to create detailed images of the seafloor.



According to CMRE, an executive body of NATO's Science and Technology Organization (STO), GPU technology and associated development tools like the CUDA™ libraries were a key component in the success of recent sea trials where the full sonar processing chain was executed on the autonomous vehicle during the mission.



The first objective of the CMRE project uses techniques from machine intelligence to develop AUV behaviors that can help ensure complete coverage of a mine hunting area. The second objective is to develop automatic target recognition (ATR) algorithms that can increase confidence that an object is classified as a mine. Accurate classification is key to efficient autonomous mine countermeasures. Moving the algorithms and behaviors on-board the AUV has the potential to significantly increase the speed of operation for mine countermeasure missions.



“The key to fulfilling these two objectives is the capability to process the sonar data on-board the vehicle in near real-time, producing detailed acoustic images of the seabed,” said Rod Rice, General Manager, Military & Aerospace Products at GE Intelligent Platforms. “GE’s MAGIC1 plays a key role in enabling this to happen by applying the significant parallel processing capability of the NVIDIA GPU.”



MAGIC1 is a rugged, small form factor subsystem that features a powerful NVIDIA® GPU, and is one of a broad range of GE products – including the GRA112, IPN251 and NPN240 - to include NVIDIA GPU functionality. GPU technology is increasingly being applied to non-graphics applications – general purpose computing using a GPU (GPGPU) - that can benefit from its inherent parallelism to process significant amounts of sensor-acquired data.



“GPU technology is being applied to the most challenging problems by military customers because of the unsurpassed ability it provides to process significant amounts of data collected by growing numbers of sensors,” said Rice., “These solutions are increasingly being deployed on autonomous vehicles, where size, weight and power – together with the ability to withstand the harshest environments – are critical. GE is an acknowledged leader in developing GPU-based solutions, and this successful trial by CMRE is an outstanding example of how they can be deployed to bring real benefits.”



The Centre for Maritime Research and Experimentation is an established, world-class scientific research and experimentation facility that organizes and conducts scientific research and technology development, centered on the maritime domain, delivering innovative and field tested Science & Technology (S&T) solutions to address defense and security needs of the NATO Alliance. It is located in La Spezia, Italy, and is built on more than 50 years of experience.