University of Dayton to steer artificial intelligence (AI) and machine learning technologies to flight test

Nov. 15, 2021
Soaring Otter seeks to speed development and deployment of AI, machine learning, neural networks, neuromorphic computing, and data exploitation.

WRIGHT-PATTERSON AFB, Ohio – U.S. Air Force artificial intelligence (AI) experts are working with university researchers to develop fast and efficient ways of moving enabling technologies for machine autonomy from the laboratory to flight testing.

Officials of the Air Force Research Laboratory at Wright-Patterson Air Force Base, Ohio, announced an $88 million contract last week to the University of Dayton Research Institute in Dayton, Ohio, for the Soaring Otter program to speed development and deployment of machine autonomy enabling technologies like AI, machine learning, neural networks, neuromorphic computing, and data exploitation.

The Air Force increasingly is employing machine autonomy to solve complex problems related to global persistent awareness, resilient information sharing, and rapid decision making, researchers say. Enabling technologies include autonomy algorithms, hardware, and software to support autonomy.

Although these new computing solutions bring new capabilities, but they also confront systems designers with challenges like how best to develop applications and integrate them into military applications like target identification and recognition; positioning, navigation and timing (PNT); and unmanned aerial vehicle (UAV) route planning.

Related: Artificial intelligence and machine learning for unmanned vehicles

The problem revolves around how to integrate and test these new solutions with acceptable costs and risks; there is need for a well-defined progression from lab prototype, through realistic system integration lab testing, and finally through field and flight testing.

On the Soaring Otter project, University of Dayton researchers will investigate ways to capitalize on the latest advancements in autonomy and machine learning in six areas: autonomy development and testing; evaluation of autonomy capabilities; computing approaches; new application areas; open-systems architectures for autonomy; and autonomy technology integration and testing.

Autonomy development and testing seeks to solve autonomy problems with machine learning, neural networks, and AI by maturing existing technologies, and determining early what is necessary to switch these autonomy technologies to the warfighter.

Evaluation of autonomy capabilities seeks to provide neutral third-party evaluation of algorithms from government, academia, and industry. The top-secret program will be for about five years.

Related: PhysicsAI to develop artificial intelligence (AI) algorithms for high-performance unmanned combat aircraft

Computing approaches focuses on compact computing solutions for the warfighter operating on the edge of the battlefield. New application spaces, meanwhile, seek to determine where autonomy can bring the greatest benefit in intelligence, surveillance, and reconnaissance (ISR) applications.

Open-systems architectures for autonomy will be fundamental elements of future autonomous systems. Autonomy technology integration and testing, finally, seeks new ways of integrating new autonomy technologies into larger systems for laboratory, field, and flight testing.

For more information contact the University of Dayton Research Institute online at https://udayton.edu/udri

About the Author

John Keller | Editor-in-Chief

John Keller is the Editor-in-Chief, Military & Aerospace Electronics Magazine--provides extensive coverage and analysis of enabling electronics and optoelectronic technologies in military, space and commercial aviation applications. John has been a member of the Military & Aerospace Electronics staff since 1989 and chief editor since 1995.

Voice your opinion!

To join the conversation, and become an exclusive member of Military Aerospace, create an account today!