2024 Corporate Aviation Leadership Summit

Autonomous flight start-up Daedalean has published a roadmap outlining its path to developing self-flying aircraft by 2028.&nbsp;
The Swiss company is working on a vehicle-agnostic, fully autonomous flight system, starting with situational- awareness software and sensors that will be used as an aid for pilots. The company aims to eventually be able to convert any type of aircraft to fly fully&nbsp;autonomously—without the aid of an onboard safety pilot or remote pilot on the ground—using artificial intelligence (AI) and machine learning.&nbsp;
“If you want to actually replace the pilot, either remote or onboard, you have to make systems that can do that," Daedalean CEO Luuk van Dijk told FutureFlight. "So, for that, you need to have this complete situational awareness, and after that, you need sufficient sensors, and then you need these AI parts to make sense of these sensors.”
To start, Daedalean is working on getting its situational-awareness system certified for general aviation purposes, under design assurance level (DAL) C, with the aim of eventually certifying a fully autonomous flight system up to DAL A, the highest level of design assurance that can be applied to airborne software. The company plans to launch its <a href="https://www.futureflight.aero/news-article/2021-07-27/avidyne-teams-daedalean-offer-ai-based-pilot-eye-vision-system">PilotEye</a> machine learning-based onboard pilot aid for general aviation in 2023. It is&nbsp;developing the system in collaboration with the Florida-based avionics company Avidyne.
“Our partner Avidyne is making the boxes, and we're going through the certification exercise and when that's done, we'll have a supplemental type certificate,” van Dijk said. “That will be a big moment for the industry as a whole because it will be the first time a machine-learning component will have been certified to design assurance level C, which means appropriate for safety cases that have major impacts.”
The first implementation of Daedalean’s technologies is based on computer vision. “The system—we call it VXS for ‘visual everything system’—relies only on the input from visual cameras, which makes it suitable for visual meteorological conditions,” Daedalean wrote in the <a href="https://flyers.daedalean.ai/Roadmap_2022-2028_Whitepaper.pdf">white paper</a> describing its roadmap through 2028.&nbsp;
“Working on that, we solved the two tasks that were the hardest: first, to create the machine-learning-based technology able to recognize, categorize, and interpret the sensor input at the distances, velocities, and uncertainties of the real flight, working in a computing box of reasonable size, weight, and power consumption. Second, to establish the principles on which such technology can be certified, working side by side with the regulators on developing design assurance methods for it,” the paper adds.&nbsp;
The roadmap then describes what Daedalean calls the IXS, or “instrument everything system,” which will use data from cameras and other traditional instruments—such as GPS, altimeters, lidars, radars, and traffic information sources—to be able to operate in instrument meteorological conditions. “Daedalean’s IXS will provide fully certified terrain and traffic collision avoidance, as well as landing guidance and flight-plan following capabilities, in VMC and IMC, certified to appropriate levels to function with minimal crew oversight only (EASA Level 3),” the paper states.
Daedalean plans to further enhance the IXS system with vehicle-to-vehicle communications capabilities, allowing aircraft to share their map data and flight plans to coordinate safe guidance. This feature, called XXS, could be particularly useful for air traffic management in urban air mobility, according to the paper.
To get these new AI and machine-learning-based technologies certified, Daedalean is working closely with the European Union Aviation Safety Agency (EASA). In February 2020, that agency&nbsp;published its <a href="https://www.futureflight.aero/news-article/2021-05-25/joint-machine-learning-and-neural-network-study-support-easa-guidance">AI roadmap</a>, which formalized the stages of certification for machine-learning applications.&nbsp;
EASA’s AI roadmap is divided into three phases. The first phase, which extends through 2024, is an exploratory period. The next phase, from 2024 to 2028, is labeled as “framework consolidation,” which is when the agency plans to issue its first approvals of AI and machine-learning components. Phase three, labeled as “pushing barriers,” will see further innovation in AI technology and the first fully autonomous commercial air transport operations.&nbsp;&nbsp;
Daedalean has also participated in a joint research project with the U.S. Federal Aviation Administration (FAA) on <a href="http://www.tc.faa.gov/its/worldpac/techrpt/tc21-48.pdf">neural network-based runway landings</a>, which could help shape the agency's&nbsp;policies on AI and machine learning.&nbsp;
To get its fully autonomous flight technology certified, Daedalean expects regulators will require the company to complete several years and several thousand hours of flight and service hours.
“Technically, we're not flight testing yet because we don't have the qualification units from Avidyne,” van Dijk told FutureFlight. “But for the software purposes, we're gathering data and we're testing that our algorithms work in flight without connecting them to the aircraft. So that's an advantage of situational awareness. You can test it out on recordings.”
You can read Daedalean's full white paper, as well as several flyers describing&nbsp;its&nbsp;autonomous systems in detail, on the company's <a href="https://www.daedalean.ai/downloads">website</a>.

Science & Technology Editor

Hanneke Weitering

Daedalean Publishes Roadmap for Autonomous Flights by 2028

Artificial intelligence (AI) specialist Daedalean is teaming with Avidyne to develop a flight deck vision system for the general aviation, advanced air mobility, and special missions markets. Announcing the partnership at this week’s EAA AirVenture show, the companies said the AI-based PilotEye system will provide pilot “advisories” for the flight crew of existing fixed-wing aircraft and helicopters, while being ready to support fully autonomous operations in new designs, including eVTOL models.
According to Avidyne, the system will use cameras to scan for traffic and other airborne hazards, and also handle&nbsp;tasks such as identifying suitable places to land in the event of an emergency. Employing Daedalean’s AI software, it will use multiple, redundant guidance sources that could support autonomous operations. The system can incorporate other data sources and merge everything into a single intuitive display.
“Through this symbiotic partnership, we are combining the industry-leading artificial intelligence neural network software and certification methodology pioneered by Daedalean, with the proven design, manufacturing, and certification expertise here at Avidyne,” commented Avidyne president Dan Schwinn. “Leveraging advanced AI technologies, these solutions will initially include visual spectrum camera-based systems for visual positioning and traffic detection, hazard avoidance, and landing guidance, as well as providing data that pilots need for quicker and more accurate land-anywhere decision-making assistance in the event of an emergency.”
The two companies said they plan to announce pricing and availability for the PilotEye system later this year. They also expect to make other announcements about AI-based products in the next few months.
“Together, we will be bringing new products to market that improve the pilot’s situational awareness and enable safe and successful completion of any given mission being flown, whether its fixed-wing, rotorcraft, advanced air mobility, eVTOL, or larger autonomous drones,” said Daedalean founder and CEO Luuk van Dijk.
Switzerland-based Daedalean already has partnerships to develop AI technology for autonomous flight and other avionics systems with Reliable Robotics and Honeywell. The latter made an undisclosed investment in Daedalean in November 2020.
&nbsp;

Managing Editor

Charles Alcock

Avidyne Teams with Daedalean To Offer AI-based Pilot Eye Vision System

Autonomous flight systems developer Reliable Robotics is teaming with machine-learning-based avionics specialist Daedalean to develop advanced navigation and situation awareness systems for commercial aircraft operations. According to the partners, the proprietary flight-automation systems they are working on will support both onboard and remote pilots in making faster, better-informed operational decisions based on data from advanced sensors.
Last month, Reliable Robotics completed a series of&nbsp;test flights controlled by a ground-based pilot at its headquarters in Mountain View, California. From a distance of over 50 miles, the pilot instructed a Cessna 208 Grand Caravan to taxi, takeoff, and fly over a populated area, and then land, while communicating with air traffic controllers via the aircraft’s onboard radios.
According to Reliable Robotics, it expects to take another two years to achieve certification for its remote-pilot technology. Initially, the company is focused on converting Cessna Caravans mainly for freight operations, but it sees potential to do the same for other aircraft types and for other applications. 
The company maintains that automation will give cargo operators, in particular, greater flexibility in opening new routes and allow these to be launched more quickly in response to shifting demand. It would not comment on reports that express delivery giant Fedex has shown interest in using the system.
The business plan calls for increased service to smaller regional airports in underserved markets. The company claims that turnarounds between flights will be quicker and more efficient because they won’t depend on the availability of local flight crew in these locations.
“Pilots will no longer be limited to flying specific types of aircraft, the same routes, or only one or two flights a day,” it explained in a statement about the latest phase of flight testing. “Geographically distributed control centers will enable constant operation across time zones, giving remote operators the ability to fly more frequently than traditional airlines.”
Reliable Robotics was founded in 2017 by Robert Rose, who formerly led the development of flight software&nbsp;for SpaceX and the autopilot system for Tesla. It has attracted $33.5 million in funding, mainly from venture capital groups, and is pursuing a business model that would have it operating&nbsp;automated aircraft as a service. 
Switzerland-based Daedalean is developing machine-learning applications based on situational awareness technology that will meet safety standards now being defined by both FAA and EASA. In joint work with the European agency, it has developed high-performance machine-learning algorithms for safety-critical applications that formed the basis for "The Concepts of Design Assurance for Neural Networks," a&nbsp;<a href="https://www.easa.europa.eu/document-library/general-publications/concepts-design-assurance-neural-networks-codann">report</a> published in March 2020. The company is already partnered with avionics manufacturers Avidyne and Honeywell Aerospace, with the latter having invested in it last year.
“Our team has developed advanced machine learning that can adapt to the inherent uncertainties in airspace and increasing levels of onboard autonomy,” said Daedalean founder and CEO Luuk van Dijk. “Bringing our&nbsp;core competencies together was a logical next step to jointly develop a solution set that makes aircraft safer.”
Reliable Robotics started remotely piloted test flights in a smaller Cessna 172 Skyhawk aircraft in 2019. It began&nbsp;testing its system on the Cessna 208 Caravan in June 2020. 
The test flights have been conducted with a remote pilot based in a newly&nbsp;established control center, working in tandem with an onboard safety pilot who monitors flight performance. The company’s goal is to achieve incremental certification to support operations using gradually increasing levels of autonomy.
The Reliable Robotics team has been supported by colleagues from SpaceX’s Falcon 9 and Dragon 2 programs in developing the human interface for the control system and also cybersecurity protection. The company believes that successful commercial flights will depend on highly trained pilots who will transition into remote operations roles that will include communicating with ground and air traffic controllers so that the converted aircraft can use existing airspace and airport infrastructure. 
From the workstations, the remote pilots are expected to maintain situational awareness and manage flight plans similarly to how an onboard pilot would complete the task. The converted aircraft will feature a proprietary sensing and computing platform that will handle fault management in conjunction with added levels of mechanical redundancy.
Meanwhile, rival autonomous flight technology pioneer Xwing is working on what appears to be a similar plan for converting the Cessna Caravan single-engine turboprop aircraft. In December, the company started piloted commercial cargo flights after receiving FAA approval for its Part 135 charter operation in late November. It is using these flights as a means to continue development work on its Autoflight System. 
The California-based start-up has been conducting test flights since July 2020 as it prepares to seek approval for operations with its autonomous (non-piloted)&nbsp;Autoflight System, for which work started in 2017. It aims to secure FAA approval to begin autonomous commercial flights in 2022.
&nbsp;
&nbsp;
&nbsp;
&nbsp;
&nbsp;

Reliable Robotics Steps Up Remote Piloting Plan with New Partner Daedalean

Honeywell has boosted its stake in the electric vertical takeoff and landing (eVTOL) aircraft sector with an investment in artificial intelligence specialist Daedalean. The U.S. aircraft systems group will work with the Switzerland-based start-up to develop for light fixed-wing and eVTOL aircraft an AI-based system that will support autonomous takeoff and landings, as well as a vision-based navigation and collision avoidance capability that does not depend on GPS.
Under an agreement announced on November 15, Honeywell Ventures is making an undisclosed investment in Daedalean, which as of July 2019 had raised $12 million in funding. “Developing flight control software requires lots of flight data,” commented Daedalean CEO Luuk van Dijk. “That’s why the collaboration with prominent industry partners such as Honeywell is critical for us to speed up the development of our technology. We are preparing for the joint flight testing of our solutions for various types of aircraft and are excited to carry out flight trials on the planes we haven’t tried before.”
As well as supporting the operation of fully autonomous eVTOL aircraft in controlled airspace, Daedalean believes its technology could also benefit piloted aircraft. It says its systems will be able to process visual images in a way that is similar to human situational awareness, allowing pilots to give more attention to safety-critical oversight of flights.
&nbsp;

Honeywell Invests in Artificial Intelligence Pioneer Daedalean

New developments and products in avionics, specifically about aircraft electronics in the cockpit.

News and issues relating to business, corporate and private aviation, primarily regarding turbine-engine-powered airplanes and helicopters. Subjects include aircraft, engines, maintenance, operations, personnel, acquisitions, accidents, safety, security, and training.

Daedalean

News

Daedalean Publishes Roadmap for Autonomous Flights by 2028

Avidyne Teams with Daedalean To Offer AI-based Pilot Eye Vision System

Reliable Robotics Steps Up Remote Piloting Plan with New Partner Daedalean

Honeywell Invests in Artificial Intelligence Pioneer Daedalean

Daedalean Steps Up Autonomous Flight Control Efforts

AIN Products

SUBSCRIPTIONS

RESOURCES

ABOUT AIN