Intel publishes Future of Avionics White Paper

Intel has partnered with Daedalean, a Swiss startup that creates machine solutions for the aviation industry. Their latest white paper presents a reference design for an AI application that acts as a never-distracting pilot and is certified, meaning it meets regulatory tests. By publishing this white paper, Daedalean and Intel hope to provide guidance to other companies looking to integrate certifiable machine-learned electronics and applications into their aircraft.

Debra Aubrey is a technical product marketing manager at Intel Corporation.

“The aviation industry still needs a first step into the future with versatile embedded computing; a reference architecture or a specific list of requirements to build the right kind of computers,” he said. “The reference architecture includes regulatory requirements, low- and high-level software, and silicon solutions for machined applications. Regulators should review the reference architecture to confirm that it will produce predictable, safe behavior in the sky.”

Daedalean worked on a machine learning algorithm and a reference architecture for a computer capable of implementing it. They tested the reference architecture in labs and on airplanes to develop situational intelligence, the ability of machine-learned applications to predict and respond to future events. To make time to market faster for companies interested in their applications, Daedalean has partnered with Intel, which provides the silicon for manufacturing these applications. The two companies have collaborated on a reference architecture that accelerates time-to-market, allowing companies to more quickly integrate machine-learning computing into their onboarding.

The white paper presents the reference architecture for certifiable embedded electronics, including the challenges of implementing software in machined devices, the visual awareness system they use, and the current and future role of embedded computing in industry. The report also considers the software and hardware requirements that ensure the safety and efficiency of aviation systems.

According to a statement provided by Intel and Daedalean, the reference architecture “can significantly reduce time to market for companies interested in incorporating the situational intelligence they create; also predict and react to the future situation in the cockpit”.

Dr. Niels Haandbaek is Daedalean’s Director of Engineering.

“This is the first paper ever to present a real-world working example and provide guidance on how to approach the challenges of implementing a machine learning application in flight embedded systems in general; requirements, certification requirements and size, weight and power (SWaP) limitations simultaneously. The approach described in the paper drives the aviation industry’s need for high-performance embedded computing,” he said.

This white paper can help bring the power of AI to avionics. This is the first paper to present a working example of a machine learning system and provide guidance on how to overcome application challenges. Actionable recommendations and findings in the new report may fuel the industry’s desire for high-performance embedded computing. This fundamental real-world example has the potential to drive a new wave of machine-learning flight-ready applications.

You can download the white paper here.

Source link