Airbus:Autonomous Taxi, Take-Off and Landing
#1
Airbus:Autonomous Taxi, Take-Off and Landing
https://www.airbus.com/newsroom/pres...ght-tests.htmlToulouse, 29 June 2020 – Following an extensive two-year flight test programme, Airbus has successfully concluded its Autonomous Taxi, Take-Off and Landing (ATTOL) project.
In completing this project, Airbus has achieved autonomous taxiing, take-off and landing of a commercial aircraft through fully automatic vision-based flight tests using on-board image recognition technology - a world-first in aviation.
In total, over 500 test flights were conducted. Approximately 450 of those flights were dedicated to gathering raw video data, to support and fine tune algorithms, while a series of six test flights, each one including five take-offs and landings per run, were used to test autonomous flight capabilities.
The ATTOL project was initiated by Airbus to explore how autonomous technologies, including the use of machine learning algorithms and automated tools for data labelling, processing and model generation, could help pilots focus less on aircraft operations and more on strategic decision-making and mission management. Airbus is now able to analyse the potential of these technologies for enhancing future aircraft operations, all the while improving aircraft safety, ensuring today’s unprecedented levels are maintained.
Airbus will continue research into the application of autonomous technologies alongside other innovations in areas such as materials, alternative propulsion systems and connectivity. By leveraging these opportunities, Airbus is opening up possibilities for creating new business models that will transform how aircraft are developed, manufactured, flown, powered and serviced.
The rapid development and demonstration of ATTOL’s capabilities was made possible due to a cross-divisional, cross-functional, global team comprising of Airbus engineering and technology teams, Airbus Defence and Space, Acubed (Project Wayfinder), Airbus China and ONERA under the leadership of Airbus UpNext.
#autonomy #innovation #TheFutureOfFlight
To read more on ATTOL, please click here
For more information on UpNext please click here
In completing this project, Airbus has achieved autonomous taxiing, take-off and landing of a commercial aircraft through fully automatic vision-based flight tests using on-board image recognition technology - a world-first in aviation.
In total, over 500 test flights were conducted. Approximately 450 of those flights were dedicated to gathering raw video data, to support and fine tune algorithms, while a series of six test flights, each one including five take-offs and landings per run, were used to test autonomous flight capabilities.
The ATTOL project was initiated by Airbus to explore how autonomous technologies, including the use of machine learning algorithms and automated tools for data labelling, processing and model generation, could help pilots focus less on aircraft operations and more on strategic decision-making and mission management. Airbus is now able to analyse the potential of these technologies for enhancing future aircraft operations, all the while improving aircraft safety, ensuring today’s unprecedented levels are maintained.
Airbus will continue research into the application of autonomous technologies alongside other innovations in areas such as materials, alternative propulsion systems and connectivity. By leveraging these opportunities, Airbus is opening up possibilities for creating new business models that will transform how aircraft are developed, manufactured, flown, powered and serviced.
The rapid development and demonstration of ATTOL’s capabilities was made possible due to a cross-divisional, cross-functional, global team comprising of Airbus engineering and technology teams, Airbus Defence and Space, Acubed (Project Wayfinder), Airbus China and ONERA under the leadership of Airbus UpNext.
#autonomy #innovation #TheFutureOfFlight
To read more on ATTOL, please click here
For more information on UpNext please click here
#2
Gets Weekends Off
Joined APC: Feb 2006
Position: B-737NG preferably in first class with a glass of champagne and caviar
Posts: 5,995
#4
Gets Weekends Off
Joined APC: Mar 2020
Posts: 225
Better learn how to be a social media influencer. Soon that will be the only career available since we are turning everything over to computers. Of course AI and Bots go a long way in determining which social media influencers get noticed, so maybe that career path has sailed as well!
#5
Gets Weekends Off
Joined APC: Dec 2011
Position: A320 FO
Posts: 982
Amazon’s foray into box hauling probably accelerates the process. Bezos appears quite fond of eliminating labor at any opportunity.
#6
Uber tried to get a self-driving car to work and they killed a pedestrian in Arizona. Of course the government blamed the driver, not the system, which is exactly what we'll see the first time a fully automated aircraft crashes and hundreds of people are killed.
#7
Gets Weekends Off
Joined APC: Dec 2011
Position: A320 FO
Posts: 982
Yes, people will die in autonomous vehicles for a while but that will only slow them down not stop them. Tesla autopilots seem to kill someone every week but people keep lining up to buy the damn things.
#8
Because the Tesla has an installed scapegoat, who is "technically" supposed to have his hands on the wheel and his eyes on the road The autonomous car industry is at a major impasse, and the event in AZ was a big part of it. They cannot make the things smart enough to deal with the real-world 100% of the time. Because of emotions (which are played on by opportunistic lawyers and politicians), an autonomous vehicle must be far safer than one with a driver... otherwise the jury will punish the mfg, and for a multi-billion corporation, that means billions in punitive judgements to make them hurt. They can't write those checks, at least not more than once or twice. Their lawyers and insurance people simply won't let them sell autonomous road vehicles. They don't even know how good the things have to be in order to be certifiable and economically viable, they are still working on it but don't even know what metric they're trying to achieve.
Slightly different issues in aviation, but certification is huge. Machine learning is apparently required to even possibly make the things smart enough, but non-deterministic learning machines are 100% not certifiable for pax aviation. There may be a work around, but it would require literally years of pilot-supervised trials in the real world. And it's risky to deploy because if an MCAS-like glitch pops up in a non-deterministic program it cannot be "fixed"... you have to scrap it and start all over from scratch.
Everything you need to know about the progress of autonomous aircraft certification can be obtained by googling "MCAS". Airbus is apparently better than Boeing, but they're not that much better.
I wouldn't worry until heavy cargo aircraft are routinely automated.
#9
Gets Weekends Off
Joined APC: Nov 2016
Posts: 2,490
The automation won't have to be perfect. Just better than human. It will get there. The incidents and accidents that do happen will get a lot of attention. But when the public finally realizes that while it is imperfect, it's still better, full automation will take off everywhere.