Cookies managing
Cookie Settings
Cookies necessary for the correct operation of the site are always enabled.
Other cookies are configurable.
Other cookies are configurable.
Do you have any questions? Contact us!
Robust & Safe
Our roadmap toward the certified product
DAL-C certification of
Traffic Detection –
the first vision-based
ML application (2023)
Traffic Detection –
the first vision-based
ML application (2023)
DAL-C certification of
Visual Landing Guidance
as pilot assistant (2023)
Visual Landing Guidance
as pilot assistant (2023)
Upgrade to DAL-B for
direct control of the aircraft (emergency autoland) (2024)
direct control of the aircraft (emergency autoland) (2024)
May 2020
A concept for Learning Assurance proposed, used by EASA in their "First usable guidance for Level 1 AI/ML application"
Dec 2021
STC application for Traffic Detection
Apr 2022
FAA issues Issue Paper, EASA issues a Certification Review Item
We are here
A specific application gets certified, referencing the NN policy among alternative means of compliance
Important pre-work for certifying Neural Networks in Europe
In two reports with EASA totaling over 200 pages, we discussed how classical software/hardware design assurance guidance could be adapted for ML in safety-critical settings, which partly led to EASA's "First usable guidance for Level 1 AI/ML application".
Read our blog posts to learn:
- Concepts of Design Assurance for Neural Networks (CoDANN) I, March 2020: Generic considerations + Visual Landing System use case
- CoDANN II, May 2021: Generic considerations + Visual Traffic Detection use case
Read our blog posts to learn:
Important pre-work for certifying Neural Networks in the US
In 2022, FAA published a 140-page report titled "Neural Network Based Runway Landing Guidance for General Aviation Autoland", the primary outcome of the joint research project between the FAA and Daedalean. The project included flight tests of Daedalean's VLS and had two goals:
- evaluating whether the W-shaped Learning Assurance process (developed within CoDANN) can satisfy the FAA's intent for setting the future certification policy;
- assessing a visual-based AI landing assistance as a backup for other navigation systems on a low-risk first implementation of AI-based systems.
