News

2020-02-02

Airbus Debuts First Fully Automatic Take-Off

With its test aircraft flown from Toulouse-Blagnac airport, Airbus has successfully performed the first fully automatic take-off. A crew comprising of two pilots, two test engineers and a flight engineer conducted a total of eight take-offs over a period of four-and-a-half hours.

Rather than relying on the ground Instrument Landing System (ILS) currently used by in-service passenger aircraft everywhere, this vision-based take-off is enabled by image recognition technology installed directly on the aircraft.

“The aircraft performed as expected during these milestone tests. While completing alignment on the runway and waiting for clearance from air traffic control, we engaged the auto- pilot,” said Captain Yann Beaufils, Airbus Test Pilot. “We moved the throttle levers to the take-off setting and monitored the aircraft. It started to move and accelerate automatically, maintaining the runway centre line at the exact rotation speed as entered in the system. The nose of the aircraft began to lift up automatically to take the expected take-off pitch value and a few seconds later we were airborne.”

Launched in June 2018, automatic take-off is an important milestone in Airbus’ Autonomous Taxi, Take-Off & Landing (ATTOL) flight demonstrator project. Having been tested by Airbus to understand the impact of autonomy on aircraft, the ATTOL project will conduct automatic vision-based taxi and landing sequences in mid-2020.

From Automated to Autonomous

Only 10 years ago the idea of autonomous vehicles on our roads was still a distant reality, but rapid advances in machine learning, sensor, camera and mapping technology have made great progress. Moreover, autonomous technologies do not stop at cars and are now influencing the development of more autonomous flight.

According to the International Air Transport Association (IATA), air traffic is expected to double by 2037, necessitating approximately 37,000 new passenger or freight aircraft and more than half a million new pilots to fly them. Given this expected increase in air travel, autonomous aircraft technologies appear foremost amongst the solutions required to support pilots in aircraft operations.

In fact, technology has already reduced the number of pilots in the cockpit from three to two, while autopilot is routinely used in many flight phases. In addition to addressing pilot shortages, autonomous technologies also have the potential to improve air traffic management, enhance sustainability performance and further increase aircraft safety while ensuring today’s unprecedented safety levels are maintained.

At Airbus, the development of autonomous technologies is moving forward rapidly complementary to the ATTOL demonstrator project, with the Airbus UpNext project aiming to develop and test computer vision algorithms. This technology will enable Airbus aircraft to taxi, take off and land autonomously without the help of the airport or satellite systems.

“Many aircraft are already able to land automatically,” Sébastien Giuliano, ATTOL Project Lead, says. “But they’re reliant on external infrastructure like Instrument Landing System (ILS) or GPS signals. ATTOL aims to make this possible solely using on-board technology to maximise efficiency and to reduce infrastructure cost.”

Sébastien says the ATTOL team is working closely with the Wayfinder team to advance autonomous flight technology at Airbus. Based at Acubed, the Silicon Valley innovation hub used by Airbus, the Wayfinder project aims to develop scalable, certifiable aircraft autonomy systems ranging from small urban air vehicles to large commercial aircraft.

Based on computer vision and machine learning, the Wayfinder software enables an aircraft to detect its surrounding environment and so calculate how best to navigate within it. Much like an autonomous car, Wayfinder uses sensors such as cameras, radar and the LiDA laser-based detection method, all working with powerful on-board computers.

“The key challenge for self-piloting capabilities is how the system reacts to unforeseen events,” explains Arne Stoschek, Wayfinder Project Executive. “That’s the big jump from automated to autonomous.”

Tailored Human-Machine Interaction

It is a mistake to use automation and autonomy interchangeably because they are far from synonymous. The difference between the two terms can be summarised as follows:

• Automation refers to the ability of a system to control a vehicle, as autopilot or cruise control.

• Autonomy is the ability of a system not only to control a vehicle but respond to unexpected hazards.

In line with this logic, two very different paths can be taken to achieve a fully autonomous aircraft:

• The fall-back pilot: During development, a ‘fall-back’ or safety pilot is always on board to take control at any time for any reason. As the autonomy system becomes more reliable, the fall-back pilot will eventually become redundant.

• Full autonomy from the beginning: Operating solely in constrained environments enables the autonomy system to be implemented from the very beginning for safe and extensive testing.

Using the fall-back pilot may enable aircraft to become airborne more quickly, but this operation requires significant investment in systems that will not ultimately be required. Nonetheless, working from the starting-point of full autonomy certainly eliminates the need for human-machine interfaces, although obtaining certification and public acceptance may prove to be a challenge.

Airbus stands amongst the manufacturers that are taking the road to autonomy, while new urban air mobility vehicles like Vahana have already been designed to integrate self-piloting functionalities from the outset. The rationale behind this production decision is that flying taxi missions involve short, point-to-point flights along a restricted selection of routes using limited landing infrastructure, entailing that urban air vehicles are an ideal choice for testing self-piloting operations in aircraft.

Now that the Vahana programme has been completed, the Airbus project team is looking forward to applying the lessons learned to future urban air vehicles. Although the technology is still not mature enough to transport passengers, autonomy in aircraft operations will undoubtedly be shaped by self-piloting, flying taxi demonstrators.

In addition to the technical challenges, autonomous flight technologies must also gain public acceptance. Clearly, passengers are used to having two pilots on the flight deck but this can change over time just as elevators moved away from having operators in the past.

The mission of Airbus is not to move ahead with autonomy as its only goal, but to present autonomous technologies alongside other innovations in areas such as materials, electrification and connectivity. By doing so, Airbus is well-placed to analyse the potential of these technologies in addressing the key industrial challenges of tomorrow, including improved air traffic management, less pilot shortages and generally enhanced future operations.

Airbus is leveraging these opportunities to improve aircraft safety further while ensuring today’s unprecedented levels are maintained. In this sense, the company does not regard autonomous flight as an all-or-nothing proposition but as a tailored combination of human and machine that will evolve over time.

Airbus systems are focused on managing the aircraft to keep the pilot at the heart of the operation, continuing to take decisions and being presented with all the necessary information in the time needed for analysis. The sense-and-avoid image processing technology behind ATTOL and Wayfinder will prove essential in making pilots’ jobs more efficient rather than eliminating them.

Reference Text/Photo:www.airbus.com

Comments () Views (11582 ) Print

Send To Friend