This article is published in The Weekly of Business Aviation part of Aviation Week Intelligence Network (AWIN), and is complimentary through Nov 06, 2024. For information on becoming an AWIN Member to access more content like this, click here.
The nose-mounted forward-looking camera is used for traffic detection and landing guidance.
Eclipse Aerospace is flight testing Daedalean’s vision-based situational awareness system on the Eclipse 550 single-pilot very light jet, marking the first use of the technology beyond light helicopters and general aviation aircraft.
Using a convolutional neural network trained to recognize objects in camera images, Daedalean’s visual awareness system can provide landing guidance, traffic detection and navigation in GPS-denied environments.
Switzerland-based Daedalean is working with U.S. avionics manufacturer Avidyne to gain FAA supplemental type certification of the system, called PilotEye by Avidyne, as a traffic detection system for pilot assistance on Part 23 general aviation aircraft such as the Cessna 182.
Separately, Daedalean is working with the European Union Aviation Safety Agency (EASA) to certify the artificial intelligence (AI)-based system, which it calls Ailumina Vista, as a landing guidance system on Part 27 light helicopters, beginning with the Robinson R44 helicopter.
The Swiss company has also developed the OmniX visual awareness experimental demonstration kit, which aircraft manufacturers can use to test the system. Leonardo’s PZL-Swidnik subsidiary has installed the kit on two SW-4 light helicopters for testing under a European-funded research project.
Moog company Genesys Aerosystems has used the kit to flight test Daedalean’s system in a Bell OH-58 helicopter testbed and develop a road map for integration of the vision-based pilot assistance technology into its Genesys Avionics Suite.
“We are constantly on the lookout for technology that we can test and integrate to further reduce the pilot workload to increase safety,” says Jerry Chambers, vice president of engineering at Eclipse. “Collaborating with Daedalean enables us to evaluate AI-enhanced capabilities, whilst enabling the testing of the system on a certified Part 23 twin-engine jet.”
To assess the system, Eclipse equipped its 550 test aircraft with two cameras and conducted flight tests in Albuquerque, New Mexico, to evaluate the vision-based system’s ability to detect, identify and deconflict with both cooperative and noncooperative traffic.
One camera is mounted in the nose looking forward for traffic detection and landing guidance and a downward-looking fish-eye camera for navigation is mounted in the belly of the fuselage. For traffic detection, Daedalean normally uses three cameras to get 226-deg. field of view, but for testing Eclipse used a simplified setup. The pilot interface is a tablet in the cockpit.
“We are looking at how Daedalean’s systems can reduce pilot workload at more remote airports to maintain the highest levels of safety,” Fergus Flanagan of Eclipse Aerospace says. “We are primarily concerned with proper runway identification, traffic awareness, landing guidance and the ability to identify runway incursions.”
Related Content
