pilotless aircraft on the way?
 

https://www.airbus.com/newsroom/pres...d-takeoff.html

There we go, soon we'll see a "take-off" button on our MCP.
I hear a lot "passenger will not board a pilotless aircraft".
The question is...would you ? Is it preferable to a "normal" aircraft with two exhausted pilots pushed to the limit of their applicable FTL?
Food for thoughts

The subject has been discussed here several times before. Personally, I never say never, but it will take a while yet. Make that a long while by the way! :)

To answer your question, no I wouldn't. Call me old fashioned.

It's just a matter of time. Machine has many strengths over human. It can process multiple inputs simultaneously. it doesn't zone in one one item and forget on the others. It has no emotion, no panic, no fear. It's never tired. It can't get drunk. It does not forget. It does not miss details like "ohh, we have 27kt tailwind and the rwy is wet".

What's probably most important: it learns from experience from other machines. It doesn't have the "can't happen to me" bias. It would just collect the data, use it in the statistics and learn from it.

In fact, what airlines should be doing is recording everything they can about their flights and sell that data back to manufacturers. Every sensor measure, every pilot input, every outcome. Machine can learn from that and fly the airplane, even with today's tech.

Self driving plane is way easier than self driving car. Way less circumstances. Way more structured and organised.

The kids of today will not fear automation. It's generational thing.

I don't fear automation; as you say there are many things that it is potentially better at than humans. There are also things it is not so good at.
But to my mind the principal argument to say that it is not yet ready is reliability. How many times a day do crews around the world cope with failures? Not necessarily anything major, but enough that if they didn't intervene the aircraft would be in trouble.
Only when that figure is damn close to zero will we be ready for a fully autonomous aircraft.

I agree with Derjodel. AI is one thing, but the next generation of AI will learn things as it goes along. I think a lot of what we used to call "local knowledge" (such as knowing that a large poorly-sited hangar at a specific airfield creates turbulence at the threshold of RWY 25 when the wind is from 210 and greater than 20kt) a truly autonomous aircraft will 'learn'. A more interesting philosophical question could arise if the machine has to sacrifice itself. For example, when Sully choose the Hudson, he knew that aircraft would never fly again, but hoped that the passengers would survive. If it had been flying autonomously, would it have tried to 'save' itself by trying to reach a runway?

Oh, and I totally agree with BizJetJock - reliability has to improve.

I don't know....

They spend A LOT of money on things that are in fact working fine. Money that could wisely be spent elsewhere.

It seems like they have way too much money available, and a lot of people who doesn't know what to do, but come up with "problems" that needs solving.

Imagine if we used all that money, and those people on something that actually matters.

Get this past the Ozzie regulator and I’ll buy the whole country a beer!

Never say Never...expect in the land down under most certainly will be never!

The reliability is there, if manufacturers (and customers) will pay for it. That's not the problem.

Don't take today's aircraft as a guide, they're designed knowing that there's a crew to take over (and take the blame) when things go wrong. Airspeed disagree? autopilot trips off, let the crew figure out what's wrong. Failed AOA sensor causing the aircraft to trim nose down? - don't worry the crew will handle it even if we don't tell them about it. And so on.

An aircraft designed from the ground up for autonomous operation will be a very different beast.

I hope someone with a clipboard and pencil is watching over the design team's shoulder logging all the "what ifs"

Good question. Lets say the AI's "objectives" are to deliver the payload safely and if that's not possible, minimize loss of life. If the option to achieve this is to land on the river, so be it.

Will there be pilotless commercial aircraft in the future? Almost certainly yes. When will large jet transports reach the equivalent of Level 5 autonomy? Hard to say but I’d put money on at least a decade or two.

AFAIK the technology has existed to do an auto-takeoff since at least the 1950s, so this particular demonstration is not that amazing, albeit it was using machine vision.

I’ll be more interested when they send an A350 solo, with instructions to do a couple of touch-and-goes, a PFL then come in flapless. Block the runway then see what it does...

"It can't be bargained with. It can't be reasoned with. It doesn't feel pity, or remorse, or fear! And it absolutely will not stop, ever, until you are dead!"

I'll get me coat...

It would have, very quickly, calculated what was possible and executed the least dangerous course of action with the overriding goal of passenger safety, it is safer to land on a river than landing in a built up city, it's all relative and that's how the 'thinking' part works. Of course it can make that calculation in milliseconds, and in the hudson incident that 'speed of thought' may well have resulted in an airfield landing . . . as was proven.

Autonomous aircraft control systems will only happen if they are (long term) cheaper than using humans, part of that cost is the cost of killing people.

Already the reality of the implications of creating truly autonomous cars is losing its gloss . . . VW, for example, recently stated that full autonomy may never happen . . . the primary reason is that there is almost no way of recouping the return on investment required. R&D prototypes are one thing, sellable product is something else.

Also ref aircraft having to be completely reliable - that's simply not the case, a machine learning based system (almost certinaly NOT learning on the job) is probably ideally suited to dealnig with all manner of aircraft failures, because it can be systematically trained to deal with everything that can fail, and if that one in a million failure happens, it's seen it before and learned how to deal with it as safely as possible.

Would I get on an autonomous aircraft today, probably not, much like I would not get in an autonomous car . . . why ? . . . the people creating these systems are not good enough . . . yet . . .

I suspect for a while the human solution, although flawed, is far more palatable than the increased costs of full autonomy. How long that remains the case will be interesting to see.

Airbus writes:
"Airbus’ mission is not to move ahead with autonomy as a target in itself, but instead to explore autonomous technologies alongside other innovations in areas such as materials, electrification and connectivity. By doing so, Airbus is able to analyse the potential of these technologies in addressing the key industrial challenges of tomorrow, including improving air traffic management, addressing pilot shortages and enhancing future operations. At the same time Airbus is leveraging these opportunities to further improve aircraft safety while ensuring today’s unprecedented levels are maintained. "

AI or Artificial Intelligence is the popular expression used for what those of who work with it are calling machine learning. It is not very intelligent. And we still don't have anything resembling artificial awareness.

Nice video. I'd like to see it perform on a really bad day with cross winds and precipitation followed by engine failure after take off or failed sensors etc.

i was thinking the same thing...

The significant aspect of this demonstration was that it used vision-based technology; equivalent to a piloted visual takeoff.
Future developments might lead to an autonomous aircraft, which together with machine learning could provide a satisfactory model of 'manual flight'.

It is unlikely that a machine version of pilot would replace the pilot in the short term, but it could be a model for acceptable performance and for alerting deviation - similar to EGPWS being an 'error detector'.
A takeoff module could improve weather dependent FD commands or intervene with autoflight assistance, e.g. auto rudder / roll correction quicker than piloted response, like existing rudder input with engine failure
Further development for all flight phases could be the basis of a 'pilot assistant' for single pilot operations, and a solution for single pilot incapacitation.

As per mjohansen, AI is far from intelligent and learning normally requires baseline data so that comparisons can be made and performance improved. With human piloted aircraft, a challenge is to judge which data is representatively good or that not so; technology has to learn the boundaries of good piloting performance before it can alert or help.

A more immediate problem is that we all 'think' that we are good pilots; so in exceptional or extreme conditions when the machine suggests assistance how might we react - 'shut up gringo'; or a polite, CRM 'thank-you'.

P.S. ' A human-centric approach to AI in aviation'.
https://www.easa.europa.eu/sites/def...admap-v1.0.pdf

I LOLed. Too soon?
:E

Isnt the real problem that even with a driverless car there can be a sort of emergency override big red stop button or command from some central control aircraft cannot 'stop' as such . Sure they can autoland but from FL350 how long is that going to take compared to cutting the power to a car and gentle braking to a stop in 50 odd yards . In other words its not what happens when all is plain sailing but what is the default function and the two cases are very very different , for example car loses contact with central monitoring centre-(these things are not autonomous) it can just gently stop, same thing on an aircraft .-I think you guys have a job for a good while yet.

I predict that it will be a freighter. Cargo does not complain about missing pilots. It will be small, more like the military drones, with a payload less than 100kg. Removing the cost of the pilot, his weight and the bulk of a cockpit will make small freighter-drones cost-effective.