5
$\begingroup$

Or a new aircraft would have to be designed for such a thing? I have little knowledge of aviation, so please feel free to fill me in the required bits.

$\endgroup$
  • 10
    $\begingroup$ What is an "AI Copilot"? And how does it differ from a regular autopilot? $\endgroup$ – Ron Beyer Mar 27 '17 at 4:01
  • $\begingroup$ To make decisions for which you need a human inside the cockpit. It would turn the human pilot's role largely supervisory. It would be, as Canuk said, acting on its own high-probability inferences. $\endgroup$ – Shashank Mar 27 '17 at 5:09
  • $\begingroup$ I think the bigger question is if we can safely integrate the already working software used in Unmanned Aircraft Systems/Aerial Vehicles into the Commercial sector. Obviously we would not literally use the same software, but the ideas and methods that have been proven to work. $\endgroup$ – Prodnegel Mar 27 '17 at 20:51
3
$\begingroup$

I understand your question as: "do we have yet the required interfaces for a computer to fully interact with an aircraft". This is indeed the prerequisite before any intelligent system can pilot an aircraft.

That means could we yet plug a system into some bus to receive all signals available to a human pilot and send all commands a human pilot can issue.

The answer is no (e.g. a computer cannot lower the gears or receive electronic signals from the wet compass), but the required updates are not so large and involve limited retrofitting.

Of course, we don't have this computer yet, but this kind of software is not a huge step either (and anyway this is not in the scope of your question).

Would such system be economically profitable for an airline in term of safety, certification, operational cost, software maintenance, compared to a human first officer? If the answer is yes, then this is a matter of maybe 10 years before a full electronic pilot is tested. I doubt the answer is yes, it could be useful, but it will have an additional cost, so there could be a long time before we see it in a cockpit.

$\endgroup$
  • 4
    $\begingroup$ Aside from lowering the gear (which has been done, the Russian Space Shuttle Buran comes to mind, since at least the 1970's), a full auto-landing is conducted regularly. What we don't have yet is ground control (taxi in/out) and auto-take-off. $\endgroup$ – Ron Beyer Mar 27 '17 at 14:21
  • 1
    $\begingroup$ @RonBeyer Indeed, I am shocked to learn that lowering the landing gear is still not automatic, and one of the risks of flying is a gear-up landing: en.wikipedia.org/wiki/Belly_landing $\endgroup$ – DepressedDaniel Mar 27 '17 at 15:34
  • $\begingroup$ @RonBeyer: Starting with STS-121, each US orbiter had also a RCO IFM cable on-board. This cable could be used to connect different systems, so that commands for a complete automatic landing could be sent from the Mission Command Center in Houston. $\endgroup$ – mins Mar 27 '17 at 18:06
  • $\begingroup$ @mins Interesting, didn't know that the orbiter had that, but it doesn't look like it was ever used, and I'm not sure that it is an autonomous system (requires operators in Houston). The Boeing X-37 says that it is the second spacecraft with auto-land capabilities after the Buran. $\endgroup$ – Ron Beyer Mar 27 '17 at 18:13
  • $\begingroup$ @DepressedDaniel Piper used to have an auto-extend feature. See planeandpilotmag.com/article/…, item 4, for why they discontinued it. If I bought an airplane with the auto-extend feature, I would disable it. The decision as to when it's best to drop the gear is not always a straight forward one. It's a matter of opinion, but mine is that I'm willing to trust my ability to get the gear down rather than forego flexibility. $\endgroup$ – Terry Apr 12 '17 at 7:15
12
$\begingroup$

If an "AI Co-pilot" existed, it could likely be integrated on existing airplanes with an auto-pilot system.

Since your question is a little vague, I'm going to take a stab at some your hidden assumptions and go from there. I'm also making the assumption that you're talking about the enroute phase of flight, and leaving the taxiing, take-off and landing in the hands of the human pilot.

At the risk of (extreme) oversimplifying, an AI system is essentially something that takes in a lot of data, analyzes it (through different algorithms) and outputs data that can then be used to do something.

I'm going to assume that the AI algorithm is supervised and has been trained on a bunch of existing data, and it has been figured out what data is important to make high-probability inferences.

In-flight, there are multiple sources of data that could be fed to the AI algorithm for it to make probabilistic inferences on what it should do. These data sources are things like:

  • Engine monitors (my EDM 700 I think logs 60 data points/second on things such as cylinder head temperature, exhaust gas temperature, RPM, location, power setting, etc.)
  • GPS Receivers (3D position)
  • AHRS (attitude information)
  • ADS-B (Traffic and Weather)
  • On-board Weather Radar
  • XM Satellite Weather

(As an aside, SavvyAnalysis already does a bit of this type of analysis using the data from your engine monitor).

So, provided that your "AI Co-pilot" has been properly trained in advance on the same type of data that you are able get from your airplane while in-flight, your AI Co-pilot could ingest the data, and output signals to the auto-pilot which would then fly the airplane. The autopilot controller is simply sending information to a particular servo for a particular control surface (aileron, elevator, etc.) and if your AI Co-pilot can output the same signal, then it could control the servos the same as the autopilot.

One of the (many) difficulties lies in designing the system to safely handle things that it hasn't seen in the training data.

But to answer your question, it wouldn't require the design of a new aircraft, but rather a new autopilot control system.

EDIT: Extra thoughts

After thinking about your question some more, I was thinking why you might want an AI Co-pilot? I'm thinking the answer to that might would be for it to either make decisions for you that you are unaware you should be making or to help you make better decisions. There is existing software that does something like this, called Xavion, which continually figures out where you should land if your engine quits based on the current location and performance of your airplane. It's not hooked up to an autopilot, but it wouldn't be too far of a stretch to think that sometime in the future, something like this could be a part of the autopilot controller.

Furthermore, Xavion is constantly running engine-out flight simulations behind-the-scenes as you fly. The app imagines an engine failure every single second, and it checks how your plane would do in a power-off glides to every runway at every airport in gliding range.

For each of these simulated engine failures, Xavion estimates the likelihood of a successful landing based on the runway’s length, width, proximity to the aircraft, and glide path from your current location down to the threshold of that runway. When Xavion has found the runway that it believes is most likely to result in a safe engine-out landing, it builds a series of hoops from your current location to that runway—spiraling, circling, or extending as needed in order for the hoops to follow a constant descent angle that your airplane should be able to sustain without power.

When you start to think of something like this, you can start to imagine analyzing real-time weather data and having the system make (or help make) a decision to divert or land based on your performance and experience. However, this is all something that would happen in the auto-pilot controller, so retrofitting it to an airplane with an existing autopilot would be more of a software upgrade than a hardware redesign.

UPDATE:

Wired had a good article on this on 3/28/2017. It talks about all the different sources of data that could be used to make an AI learn about the airplane, figure out where the holes are in the data and who could fill them. An interesting place for data that I didn't think about (because it's not data generated in flight), is maintenance and service logs.

Particularly relevant to the intent (I think) of your question might be this passage:

Elsewhere, researchers are working to ensure AI can help pilots manage crises as they arise. At University College London, a team led by Haitham Baomar and Peter Bentley is developing a new autopilot system that learns how to manage emergencies by watching how well-trained pilots do so, and then behaving as they do in similar circumstances.

“We want to increase safety by trying to tackle the human-error factor that might be caused by stress, information overload, and sometimes a lack of sufficient and up-to-date training,” Baomar says. “Modern autopilots, unfortunately, can’t handle challenging flight conditions such as severe weather conditions or system failures.”

$\endgroup$
  • 1
    $\begingroup$ Anecdote comment: First time subway come full auto people are scared of boarding a train without a conductor. For the airliners co. a AI Copilot can cause some marketing concerns $\endgroup$ – jean Mar 27 '17 at 10:46
  • 1
    $\begingroup$ @jean I think people might have less problems with a system where an actual human pilot is still in the cockpit and able to take over at a moment's notice should something go wrong, than with a full-automatic system with no human pilot with "skin in the game". I think we have a question somewhere on completely automated passenger flights which discusses some of those issues; a case could probably be made that combining the good parts of technology and human pilots make for an overall improvement. Of course, that doesn't address the similarities between OP's proposal and eg modern autopilots. $\endgroup$ – a CVn Mar 27 '17 at 12:45
  • $\begingroup$ @MichaelKjörling I believe that this is the questions that you are referring to: Why do we still use pilots to fly airplanes? $\endgroup$ – Lnafziger Mar 27 '17 at 21:28
  • $\begingroup$ @Lnafziger Yes, that looks like it's the one. Thanks! $\endgroup$ – a CVn Mar 28 '17 at 7:17
  • $\begingroup$ That Xavion software sounds like a tremendous asset! It looks to solve a problem that seems to be happening with decreasing frequency, but I can see where it would be a great benefit to the pilots to recognize that they have an engine out, push a button, and a prepared solution pops up instantly. While pilots/ATC are cool as a cucumber, it would take away a lot of the stress and increase the likelihood of a safe outcome from an engine out situation. $\endgroup$ – FreeMan Mar 28 '17 at 12:51
2
$\begingroup$

We already have this - it's called the autopilot.

The autopilot has gone through continuous improvement. Modern ones are hooked up to GPS, can control the throttles for optimum fuel efficiency, and so on. They're a very sophisticated bit of kit.

More recently, autoland is standard on large aircraft, and is becoming more common on smaller passenger aircraft. Again, these vary in sophistication, up to full "zero-zero" landing completely under the autopilot's control.

$\endgroup$
  • $\begingroup$ Same for military planes too? $\endgroup$ – Shashank Mar 27 '17 at 11:43
  • 1
    $\begingroup$ "More recently, autoland is standard on large aircraft" Recently as in the late 60's and early 70's? Autoland has been around for more than 50 years. $\endgroup$ – Ron Beyer Mar 27 '17 at 14:22
  • $\begingroup$ @RonBeyer More recently than the original autopilot. :) And it became standard more recently than that. $\endgroup$ – Graham Mar 27 '17 at 16:17
  • 3
    $\begingroup$ An autopilot won't abort the landing if there is a runway incursion. A human will do it, and that's what is expected from an intelligent autopilot. Intelligent autopilot is as different from autopilot than cruise control is different from a self driving car. $\endgroup$ – mins Mar 27 '17 at 18:16
  • 1
    $\begingroup$ @Graham maybe I'm misreading you, but the equivalent to your "The learning phase MUST happen during development only, because that's the only way this is safe." statement is equivalent to "The pilot must only use what he learned in the classroom because those are the correct theories, anything else is unsafe." I'm not a pilot, but everything I've read about flying (and everything else in life) is that theories are good but practical experience is far better. An AI begins with a set of assumptions but learns from experience to make it better, just as humans do-hence artificial intelligence. $\endgroup$ – FreeMan Apr 12 '17 at 14:54

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.