Innovation from collaboration: Xwing and Daedalean to share knowledge
Xwing and Daedalean are coming together to share their knowledge and processes of machine learning and artificial intelligence (AI) to accelerate market entry and boost safety.
As yet, no machine learning-based applications have made their way into a civil aviation cockpit. According to Xwing, this requires a paradigm shift in how software and hardware have traditionally been assessed and certified as safe. As both Xwing and Daedalean are working closely with the FAA and EASA to certify their software, they believed a consensus on their approaches and sharing of information would be the best way advance certification standards, work out a means of compliance and accelerate market entry.
“We see Xwing and Daedalean as the technical leaders in this space,” Maxime Gariel, president and CTO of Xwing tells us. “We have complementary approaches toward the development of machine-learning (ML) based software, a commitment to safety, and active certification programmes. Over the past couple of years, we have shared information and flight test data informally, and because of our positive working relationship, we formalized the agreement to both deepen our data sharing and define a common language to facilitate collaboration with regulators on both sides of the Atlantic.”
Although Daedalean and Xwing have independently developed frameworks for the certification of their AI-based systems, both agree that higher levels of safety can be achieved on a shorter timeline by sharing knowledge and relevant flight data. This should lead all stakeholders – industry, regulators, and the public – to make progress on the path to certifying AI systems.
“In this emerging industry, it’s as crucial to collaborate with fellow pioneers as it is to partner with regulators around the world,” said Luuk van Dijk, co-founder and CEO of Daedalean. “With this shared undertaking, we will be able to demonstrate that increasing safety is driving innovation and that a collaborative approach to harmonise regulations and standards ensures that best practices are universally adopted.”
Gariel continues: “At Xwing, we balance our commitment to a strong safety culture with our push for technical innovation. Our collaboration with Daedalean underscores this philosophy and the importance we place on sharing data, knowledge, and processes to inform a credible path forward toward certification for the industry as a whole as we work closely with regulators.”
Both firms have published award-winning papers that outline their approaches to certification. Two examples are, Xwing’s Formal and Practical Elements for the Certification of Machine Learning Systems and Daedalean’s Concepts of Design Assurance for Neural Networks series.