Airbus Validates Computer Vision-Based Technologies to Increase Safety Through Automation

Throughout Airbus’ robust history, the aviation giant has pioneered automation technologies, such as fly-by-wire, to increase safety and provide pilots with the necessary tools to react strategically on a day-to-day basis and during unlikely incidents. With increased air travel, these functionalities are continually more vital. As part of its unwavering commitment to safety, Airbus has developed technology in alignment with human skills to assist operations for increased safety, reliability and efficiency.

Acubed joined efforts with Airbus UpNext, Airbus’ flying demonstrator subsidiary, in 2020 to achieve an incredible milestone: the autonomous taxiing, take-off and landing (ATTOL) of a commercial aircraft. Through image recognition by artificial intelligence (AI) technology developed at Acubed, the aircraft was able to safely perceive and react to its surroundings, landing autonomously based on computer vision technology on board the A350. The global team applied that “2020 vision” to launch a new demonstrator in 2022, DragonFly, with the objective of performing autonomous landing and taxiing operations in the unlikely event a crew member is incapacitated.

Through the maturation and validation of autonomous flight systems, the demonstrator team has successfully performed autonomous emergency operations, including cruise, landing and taxi assistance. Taking into account external factors such as flight zones, terrain and weather conditions, the aircraft was able to generate a new flight trajectory plan and communicate with both Air Traffic Control (ATC) and the Operations Control Center (OCC).

The benefits, both realized and future-looking, of maturing these flight systems are tremendous. From the continued assurance of safe air travel for all passengers and crew, to lessening the workload of pilots and creating precise flight path management, automated functions have greatly benefited travelers worldwide. However, maturing and validating new, autonomous flight systems comes with some new challenges. As a key partner and contributor to the DragonFly demonstrator, our Acubed team is tackling the following challenges head-on:

Autonomy functions require an entirely new, data-driven development approach. These functions operate in a complex and changing environment. The challenge comes when attempting to capture this complexity and building a reliable AI algorithm.

Seeing is believing when it comes to unlikely events. To create a robust, certifiable algorithm, Airbus will have to capture enough “corner case” data to deliver an algorithm that can perceive and react to an extremely unlikely event, even as unlikely as an elephant on the runway - a case found on an African airport.

Data. Data. Data. How to collect at scale? Developing AI to robustly understand the environment and guide the aircraft during landing and taxiing will require massive amounts of data. Acubed is using its own aircraft, a Beechcraft Baron 58, to fast track the development of its data collection system and data management infrastructure, targeting scales in the tens of Petabytes.

Scalable data aggregation and processing is a topic that Silicon Valley-based Acubed engineers are intimately familiar with. Acubed is excited to partner with Airbus to prepare the next generation of AI algorithms to advance automated landing and taxi phases. This data capture initiative is key to be able to ramp up in data collection and optimization, putting algorithms on a clear path towards certification.

We are so grateful to our colleagues at Airbus UpNext, Airbus Space and Defense and NAVBLUE, along with all external partners, for the unique opportunity to integrate and test our technology on full-scale aircraft to prepare for the next age of aviation.

If you’re interested in joining our team and building the future of flight, apply here.

- Cedric Cocaud