A Japanese semiconductor company has demonstrated its edge AI platform in a U.S. Air Force exercise, validating its ability to run artificial intelligence workloads during flight while supporting future defense and space missions.

EdgeCortix said its SAKURA-II platform was integrated into a mission system and tested in a large-force exercise as part of a prototype project backed by the U.S. Defense Innovation Unit (DIU). The company also received a DIU Success Memorandum recognizing that it had successfully met all prototype project objectives.

The demonstration focused on delivering AI inference at the tactical edge, where computing must be performed locally with minimal power consumption instead of relying on cloud connectivity. Such systems are increasingly being explored for military aircraft, drones, autonomous platforms, and space missions.

In addition to flight testing, the project included independent AI benchmarking, radiation testing for space environments, and integration into a prototype gateway designed to improve multi-domain battlefield connectivity across joint and coalition forces.

Flight-tested edge intelligence

According to the company, the SAKURA-II platform completed AI benchmarking with independent validation support from Carnegie Mellon University’s Software Engineering Institute (CMU SEI).

The project also included heavy-ion radiation testing conducted by NASA to evaluate the platform’s resilience for orbital and lunar missions. EdgeCortix said the tests recorded no destructive events and only minimal transient effects, supporting the platform’s use in environments ranging from low Earth orbit to cislunar space.

The airborne demonstration evaluated the system’s ability to execute AI inference under operational conditions while maintaining low power consumption.

“The U.S. Air Force and EdgeCortix worked together to integrate SAKURA-II into a relevant mission system and fly it in a large force exercise, validating AI inference in flight with a tactically relevant application in operationally relevant scenarios,” said Lt Col Spencer Liedl, KC-135 Operational Test Director, Roland R. Wright ANGB, UT, Air National Guard Air Force Reserve Command Test Center (AATC).

Ready for deployment

The successful testing increased the platform’s Technology Readiness Level (TRL) for airborne deployments, according to the company. The DIU Success Memorandum also establishes a pathway for potential follow-on production and future deployment opportunities within U.S. defense programs.

Edge AI processors perform machine learning tasks directly on devices rather than sending data to remote servers. This approach reduces latency, improves resilience when communications are disrupted, and lowers power consumption, making it particularly attractive for defense, aerospace, and autonomous systems operating in contested environments.

“This milestone validates the readiness of the EdgeCortix SAKURA-II platform for demanding aerospace and defense environments,” said Dr. Sakyasingha Dasgupta, Founder and CEO of EdgeCortix.

“The successful benchmarking, radiation testing, airborne integration, and operational flight demonstration of SAKURA-II highlight the role of energy-efficient edge AI platforms in enabling trusted autonomy and resilient AI inference across next-generation defense and space systems.”

The Tokyo-headquartered company develops energy-efficient AI processors using its proprietary Dynamic Neural Accelerator architecture and MERA software stack. Its platforms target defense, aerospace, robotics, telecommunications, industrial automation, and other applications that require real-time AI processing at the edge.