AI Sonobuoy

You can now do a lot more with a lot less when it comes to deploying AI systems. Power requirements of edge AI algorithms and edge inference processors continue to trend downward, enabling new designs for AI-powered systems.

The AI Sonobuoy project is intended to demonstrate the process and design methodology for developing an AI-enabled hydrophone. We are building an integrated system that detects ship propellers using hydrophones. Data is collected, stored, and processed locally using onboard microprocessors. Onboard detection algorithms trigger remote alerts when objects of interest are detected.