A350-1000 autonomy tests aimed at supporting dual-pilot cockpit: Airbus
Thread Starter
Join Date: Jan 2010
Location: Marlow (mostly)
Posts: 305
Likes: 0
Received 0 Likes
on
0 Posts
A350-1000 autonomy tests aimed at supporting dual-pilot cockpit: Airbus
Item from Flight International: interesting twist on the manufacturer claimed objectives.
Airbus has trialled further autonomous flight concepts using an A350-1000 test aircraft, including emergency diversion and automatic landing, but insists they are aimed at supporting a dual-pilot, rather than single-pilot, cockpit.
Part of the airframer’s UpNext initiative the ‘DragonFly’ programme takes its inspiration from insects of the same name – using biomimicry of dragonflies’ combination of high-speed senses, spanning a wide field of view, feature recognition and precision flight control.
DragonFly has focused on three particular aspects of autonomous operation – diversion, landing and taxiing – including assistance during a simulated incident of pilot incapacitation.
The aircraft relies on automatic intelligent decision-making based on flight data obtained through a combination of sensors, including cameras on the A350’s nose, and backed up by vision algorithms and guidance calculations.
DragonFly head of demonstrator Isabelle Lacaze says the programme has been running for two years, but flight-testing using aircraft MSN59 commenced in July 2022 and the airframer is “enthusiastic about the first promising results” obtained towards the end of last year.
Among the achievements, she says, was the simulation of sudden pilot incapacitation over Limoges during a flight to Lyon, in a real air traffic environment.
“The system took over and diverted the [aircraft] safely to the nearest appropriate airport – Toulouse in that scenario,” says Lacaze.
“It was really amazing to see that all our stakeholders in this scenario [including test pilots and air traffic controllers] were really positive about the feasibility and the acceptability of the solution.”
She states that the diversion function can activate automatically or act as a support to the pilots.
Source: Airbus
Cameras mounted on the A350’s nose are part of the sensor array to gather external situation data
Addressing the possibility of incapacitation remains one of the contentious issues when considering a possible shift towards single-pilot operations.
But Lacaze insists that DragonFly is intended to develop and evaluate assistance to a two-pilot crew, to help manage workload during intensive phases of flight, such as diversion – with cases of incapacitation or medical emergency among the possible causes.
“We consider there is already huge value [in this],” she says. “We are in exploratory field of research. Our framework – to mature, to explore, see what we can do with the new technology – is really focusing on… assistance for dual-pilot operations, meaning the current crew composition.”
But DragonFly does envision support for extreme circumstances in which pilots are no longer able to control the aircraft.
The criteria for detecting incapacitation are “sensitive”, says Lacaze, and she does not elaborate on the techniques involved, but says that the system is designed to take over “seconds” after detection.
Lacaze says the DragonFly demonstration team has had to “fine tune” the implementation through a step-by-step process, gradually integrating different aspects, to ensure that safety was preserved as the aircraft took control. “It was not an easy walk in the park,” she says.
She says the programme is intended not only to offer diversion assistance but to support crews in taxiing at congested airports, through computer-vision obstacle detection, to maintain speed control and centreline tracking, as well as alerting pilots to the risk of runway crossing. The taxi functions have been tested at Toulouse airport.
Source: Airbus
DragonFly also used vision systems to support taxiing assistance
Prior autonomous flight testing using an A350-1000, under a programme named ATTOL, demonstrated a fully-autonomous take-off using vision systems to track the runway, and carry out automatic rotation.
DragonFly has extended this to automatic landing, including in low visibility conditions using sensors and vision systems, and Airbus believes the capability could be broadened to approaches to any airport, even those not equipped with the ground technology to support landing automation.
Airbus says its demonstrator takes into account a range of external factors – including terrain, weather and military flight zones – as part of its assessment of where to land, and generates a new trajectory.
It adds that the aircraft also uses constant communication with air traffic control and the airline operations centre to co-ordinate a safe approach.
Several Airbus divisions and a number of partner companies, including Collins Aerospace, Honeywell, Thales, Onera and Cobham, have co-operated with the DragonFly programme, which has embarked on its last three months of testing.
“These tests are one of several steps in the methodical research of technologies to further enhance operations and improve safety,” says Lacaze.
She says the UpNext initiative is launching a project to advance landing and taxi assistance with a view to taking advantage of new-generation computer-vision algorithms.
A350-1000 autonomy tests aimed at supporting dual-pilot cockpit: Airbus
By David Kaminski-Morrow13 January 2023Airbus has trialled further autonomous flight concepts using an A350-1000 test aircraft, including emergency diversion and automatic landing, but insists they are aimed at supporting a dual-pilot, rather than single-pilot, cockpit.
Part of the airframer’s UpNext initiative the ‘DragonFly’ programme takes its inspiration from insects of the same name – using biomimicry of dragonflies’ combination of high-speed senses, spanning a wide field of view, feature recognition and precision flight control.
DragonFly has focused on three particular aspects of autonomous operation – diversion, landing and taxiing – including assistance during a simulated incident of pilot incapacitation.
The aircraft relies on automatic intelligent decision-making based on flight data obtained through a combination of sensors, including cameras on the A350’s nose, and backed up by vision algorithms and guidance calculations.
DragonFly head of demonstrator Isabelle Lacaze says the programme has been running for two years, but flight-testing using aircraft MSN59 commenced in July 2022 and the airframer is “enthusiastic about the first promising results” obtained towards the end of last year.
Among the achievements, she says, was the simulation of sudden pilot incapacitation over Limoges during a flight to Lyon, in a real air traffic environment.
“The system took over and diverted the [aircraft] safely to the nearest appropriate airport – Toulouse in that scenario,” says Lacaze.
“It was really amazing to see that all our stakeholders in this scenario [including test pilots and air traffic controllers] were really positive about the feasibility and the acceptability of the solution.”
She states that the diversion function can activate automatically or act as a support to the pilots.
Source: Airbus
Cameras mounted on the A350’s nose are part of the sensor array to gather external situation data
Addressing the possibility of incapacitation remains one of the contentious issues when considering a possible shift towards single-pilot operations.
But Lacaze insists that DragonFly is intended to develop and evaluate assistance to a two-pilot crew, to help manage workload during intensive phases of flight, such as diversion – with cases of incapacitation or medical emergency among the possible causes.
“We consider there is already huge value [in this],” she says. “We are in exploratory field of research. Our framework – to mature, to explore, see what we can do with the new technology – is really focusing on… assistance for dual-pilot operations, meaning the current crew composition.”
But DragonFly does envision support for extreme circumstances in which pilots are no longer able to control the aircraft.
The criteria for detecting incapacitation are “sensitive”, says Lacaze, and she does not elaborate on the techniques involved, but says that the system is designed to take over “seconds” after detection.
Lacaze says the DragonFly demonstration team has had to “fine tune” the implementation through a step-by-step process, gradually integrating different aspects, to ensure that safety was preserved as the aircraft took control. “It was not an easy walk in the park,” she says.
She says the programme is intended not only to offer diversion assistance but to support crews in taxiing at congested airports, through computer-vision obstacle detection, to maintain speed control and centreline tracking, as well as alerting pilots to the risk of runway crossing. The taxi functions have been tested at Toulouse airport.
Source: Airbus
DragonFly also used vision systems to support taxiing assistance
Prior autonomous flight testing using an A350-1000, under a programme named ATTOL, demonstrated a fully-autonomous take-off using vision systems to track the runway, and carry out automatic rotation.
DragonFly has extended this to automatic landing, including in low visibility conditions using sensors and vision systems, and Airbus believes the capability could be broadened to approaches to any airport, even those not equipped with the ground technology to support landing automation.
Airbus says its demonstrator takes into account a range of external factors – including terrain, weather and military flight zones – as part of its assessment of where to land, and generates a new trajectory.
It adds that the aircraft also uses constant communication with air traffic control and the airline operations centre to co-ordinate a safe approach.
Several Airbus divisions and a number of partner companies, including Collins Aerospace, Honeywell, Thales, Onera and Cobham, have co-operated with the DragonFly programme, which has embarked on its last three months of testing.
“These tests are one of several steps in the methodical research of technologies to further enhance operations and improve safety,” says Lacaze.
She says the UpNext initiative is launching a project to advance landing and taxi assistance with a view to taking advantage of new-generation computer-vision algorithms.
Join Date: Jan 2006
Location: Between a rock and a hard place
Posts: 1,208
Likes: 0
Received 0 Likes
on
0 Posts
Is this the software developers having run out of ideas for yet another feature?
Isn't it already doing automatic TCAS maneuvers and emergency descents?
Isn't it already doing automatic TCAS maneuvers and emergency descents?
Pegase Driver
Join Date: May 1997
Location: Europe
Age: 72
Posts: 3,390
Likes: 0
Received 0 Likes
on
0 Posts
Originally Posted by 172_driver
Is this the software developers having run out of ideas for yet another feature?
Isn't it already doing automatic TCAS maneuvers and emergency descents?
Isn't it already doing automatic TCAS maneuvers and emergency descents?
Dragonfly here is another of thsose , but the long time aim is autonomous aircraft for sure. Wether some of hese features will see production , will it be standard or as an (expensive) option , time will tell.
As Less hair said the basic technology already exsists, ( Garmin for the auto diversion / land and Gulfstream for the recognaissance cameras ) putting iall this into practice and having it certified for a 300 seat aircraft will be the challenge I guess, But you have to admit it is very interesting .
Airbus is right to research such things and, remember, in all R&D there will be some projects which reach dead ends and some which will open up unexpected avenues.
However, while I don't think we will see pilotless airline operations in the near future, I do think it will be possible, in the not too distant future, to design and certificate aircraft for single pilot operations in the cruise so that, on very long flights, it would be possible either to reduce or even eliminating the need for 'heavy crews'. This would enable one pilot to take his statutory rest while the other is left alone at the controls. There would then be no need, depending on the length of the flight, to roster extra pilots.
You could then have, on ultra long flights, two at the controls for take-off and landing but only one at the controls during the quiet parts in the cruise with the other readily available in the crew rest area - much like the watch system at sea. I am sure this could work and would offer substantial financial benefits to the airlines.
It would also allow for co-pilots to be trained and to build up sufficient experience so that they could take sole control in the cruise. In practice, I think there would need to be an extra co-pilot or apprentice pilot period (call it what you will) for a long time until the necessary experience has been gained. Experience is not something that is acquired quickly and takes several years. As we all know, good piloting skill is not just about flying the aircraft but also about knowing what situations to avoid.
Finally, I think that long solo duty periods would be so ruddy boring I doubt any sensible person in their right mind would ever want to do the job. I know I wouldn't!!
However, while I don't think we will see pilotless airline operations in the near future, I do think it will be possible, in the not too distant future, to design and certificate aircraft for single pilot operations in the cruise so that, on very long flights, it would be possible either to reduce or even eliminating the need for 'heavy crews'. This would enable one pilot to take his statutory rest while the other is left alone at the controls. There would then be no need, depending on the length of the flight, to roster extra pilots.
You could then have, on ultra long flights, two at the controls for take-off and landing but only one at the controls during the quiet parts in the cruise with the other readily available in the crew rest area - much like the watch system at sea. I am sure this could work and would offer substantial financial benefits to the airlines.
It would also allow for co-pilots to be trained and to build up sufficient experience so that they could take sole control in the cruise. In practice, I think there would need to be an extra co-pilot or apprentice pilot period (call it what you will) for a long time until the necessary experience has been gained. Experience is not something that is acquired quickly and takes several years. As we all know, good piloting skill is not just about flying the aircraft but also about knowing what situations to avoid.
Finally, I think that long solo duty periods would be so ruddy boring I doubt any sensible person in their right mind would ever want to do the job. I know I wouldn't!!
Last edited by Bergerie1; 20th Jan 2023 at 11:08.
Originally Posted by Innaflap
For sure this is the type of feature that could help in the event of an incapacitated crew or nefarious forces
Join Date: Jun 2002
Location: Dubai
Age: 54
Posts: 290
Likes: 0
Received 0 Likes
on
0 Posts
Airbus today suffers from a LOC* anomaly where it sometime cannot properly capture the localiser. This is something aeroplanes have been doing for, like, 90 years and Airbus still can't get it right. I'm not too sure that their autonomous project is going to pass muster.
Autonomous & automated flying is coming, sooner or later, for the better or the worse
And how many times have those humans - because they sure as hell weren't 'pilots' yet alone aviators - flown perfectly serviceable aircraft into a hill, an ocean or elsewhere because they screwed up, yet alone committed suicide and decided to take their passengers with them?
You've cited three examples of tech errors, and I'll grant there are likely many more - but "pilot error" outstrips technological failure especially these days, by an order of magnitude. A computer isn't going to shut down the wrong engine, like the crew did at Kegworth or Taipei. A computer isn't going to fly a 777 into a sea wall on a CAVU day that my 10 year old can (and does) land in and a computer isn't going to panic and hold full back stick while falling 35,000' into the Atlantic. There'll be new and novel failures but they'll still be rarer than the number of crew-induced errors today.
That being said....What scares me about the pilotless airliner is the same thing that scares me about those robot trains around the world. I'm paraphrasing here but, there are known unknowns - things we know we don't know, and there are unknown unknowns - those things that no one knows they don't know. And those are the things that are going to limit the introduction and deployment of autonomous airliners, because "It's not supposed to do that" doesn't cut the mustard when things go pear shaped in the flight levels.
You've cited three examples of tech errors, and I'll grant there are likely many more - but "pilot error" outstrips technological failure especially these days, by an order of magnitude. A computer isn't going to shut down the wrong engine, like the crew did at Kegworth or Taipei. A computer isn't going to fly a 777 into a sea wall on a CAVU day that my 10 year old can (and does) land in and a computer isn't going to panic and hold full back stick while falling 35,000' into the Atlantic. There'll be new and novel failures but they'll still be rarer than the number of crew-induced errors today.
That being said....What scares me about the pilotless airliner is the same thing that scares me about those robot trains around the world. I'm paraphrasing here but, there are known unknowns - things we know we don't know, and there are unknown unknowns - those things that no one knows they don't know. And those are the things that are going to limit the introduction and deployment of autonomous airliners, because "It's not supposed to do that" doesn't cut the mustard when things go pear shaped in the flight levels.
Just picking a year at random 2019 there were 12 crashes with the loss of 261 lives, 157 of those were the Ethiopian MAX. I very much doubt pax would accept no crew, I certainly won't, particularly with QF 32 in mind.
Join Date: Jun 2007
Location: Wanderlust
Posts: 3,275
Likes: 0
Received 0 Likes
on
0 Posts
Originally Posted by megan
Just picking a year at random 2019 there were 12 crashes with the loss of 261 lives, 157 of those were the Ethiopian MAX. I very much doubt pax would accept no crew, I certainly won't, particularly with QF 32 in mind.
Pegase Driver
Join Date: May 1997
Location: Europe
Age: 72
Posts: 3,390
Likes: 0
Received 0 Likes
on
0 Posts
Originally Posted by megan
Just picking a year at random 2019 there were 12 crashes with the loss of 261 lives, 157 of those were the Ethiopian MAX. I very much doubt pax would accept no crew, I certainly won't, particularly with QF 32 in mind.
But to be even more the Devil's advocate. let's take the latest incident covered here : the AA near ground collsion at JFK. Had AA been fully automated , the ATC computer would have instructed dep 4L. cross 31L at K, and the aircrfaft would have just followed that and not end up crossing 4L. But that said. when dealing with full automation ( and ATC my line of work we have the same debate ) I keep on reminding engineers one of the good old Al Wiener law : "
Whenever you solve a problem you usually create another one. You can only hope that the one you created is less critical than the one you eliminated."
Originally Posted by VHOED191006
As long as it is used for things like that, and nothing further. I've always liked Airbus for what they're doing with technology. Hopefully they don't consider using it to remove the humans who are meant to fly it.
Join Date: Jan 2019
Location: UK
Posts: 558
Likes: 0
Received 0 Likes
on
0 Posts
Originally Posted by ATC Watcher
the AA near ground collsion at JFK. Had AA been fully automated , the ATC computer would have instructed dep 4L. cross 31L at K, and the aircrfaft would have just followed that and not end up crossing 4L.
Originally Posted by Busdriver01
So is ATC to be fully automated too? No reason to think human ATC is safer than human pilot...
Originally Posted by atakacs
Autonomous & automated flying is coming, sooner or later, for the better or the worse. These are all small steps in that direction.
