2nd September 2022
Can ‘Explainable AI’ provide a way to apply DO-178C for the safety assurance of neural networks in aviation applications? We think not, but there are a few subtle misconceptions to be unwrapped.
However, there does exist a different approach for ensuring the reliable performance of machine-learned (‘AI’) components for a new generation of flight control instruments: demonstrating Machine Learning Generalization and quantifying so-called “Domain Gaps”.
This 8-minute video provides a synopsis of the concepts for anyone who has a basic understanding of high school-level math.
00:19 How DO-178 works for the classical software systems in aviation
01:00 What is that ‘AI’ you speak of
03:44 Certainty and uncertainty
04:56 Traceability: Beware of what you wish for
06:16 How to design a system with a component working with uncertainty
06:56 Will it work ‘in vivo’ as well as it worked ‘in vitro’?
Daedalean hires Dr. Yemaya Bordain to lead its new office in Phoenix, AZ, as the company officially opens for business in the United States.
Daedalean has concluded a joint research project with the FAA on Neural Network-Based Runway Landing Guidance for General Aviation.
Use the form opposite to get in touch with Daedalean directly to discuss any requirements you might have.