SU-30SM, SU-35S, and SU-34 flying in formation - Sputnik International, 1920
Military
Get the latest defense news from around the world: breaking stories, photos, videos, in-depth analysis and much more...

China’s New AI Torpedo Can Outsmart Decoys to Destroy Real Threats

© AP Photo / Xinhua, Zha Chunming, File In this April 26, 2012 file photo released by China's Xinhua News Agency, Chinese navy's submarine attends the fleet review of the China-Russia joint naval exercise in the Yellow Sea
 In this April 26, 2012 file photo released by China's Xinhua News Agency, Chinese navy's submarine attends the fleet review of the China-Russia joint naval exercise in the Yellow Sea - Sputnik International, 1920, 05.06.2025
Subscribe
Today’s underwater battlespace is crowded with threats like decoys, jammers, countermeasures, and weapons. In these high-pressure environments, systems must quickly identify real targets from fakes to avoid wasted shots and mission failure.
China is developing an AI-powered ultra-fast torpedo designed to dominate underwater warfare.
Researchers from the PLA Navy and China State Shipbuilding Corporation combined physics with machine learning to teach a torpedo to think before striking.
First, the team simulated decoy profiles using bubble-collapse and turbulence models.
They subsequently trained AI with generative adversarial networks (GANs) to refine and detect acoustic fakes.
The researchers then used deep-learning sonar analysis, converting signals into “spectral thumbnails” via a mathematical tool known as Fourier transforms, which breaks down a complex signal into its basic building blocks.
The result:
Boosted detection rates against advanced decoys from 61.3% to over 80%
The new system achieved a 92.2% success rate in identifying real submarines vs. decoys, a Command Control & Simulation report shows
China AI  - Sputnik International, 1920, 29.04.2025
Analysis
Pepe Escobar: China Steps Up Its Game in the Global AI Race
Newsfeed
0
To participate in the discussion
log in or register
loader
Chats
Заголовок открываемого материала