3D Robotics

Let Skynet Become Self-Aware!


Here's a crosspost of my article this morning in Hackaday. We'll see how many people get the Terminator joke. 

Not so long ago, it was hard to fly. Forget actual manned aircraft and pilots licenses; even flying model aircraft required hours of practice, often under the tutelage of a master at a flying field. But along with that training came an education in the rules of safe flight, including flying at a designated airfield and watching out for obstacles.

We accidentally messed that up. We in the drone industry made aircraft super easy to fly — perhaps too easy to fly. Thanks to smart autopilots and GPS, you can open a box, download an app and press “take off”. The copter will dutifully rise into the air and wait there for further instructions — no skill required. And it will do this even if you happen to be in an NFL football stadium in the middle of a big game. Or near an airport. Or in the midst of a forest fire.

The problem is that along with taking training out of the process of flying a drone, we inadvertently also took out the education process of learning about safe and responsible flight. Sure, we drone manufacturers include all sorts of warning and advisories in our instructions manual (which people don’t read) and our apps (which they swipe past), and companies such as DJI and my own 3DR include basic “geofencing” restrictions to try to keep operators below 400 feet and within “visual line of sight”. But it’s not enough.

Every day there are more reports of drone operators getting past these restrictions and flying near jetliners, crashing into stadiums, and interfering with first responders. So far it hasn’t ended in tragedy, but the way things are going it eventually will. And in the meantime, it’s making drones increasingly controversial and even feared. I call this epidemic of (mostly inadvertent) bad behavior “mass jackassery”. As drones go mass market, the odds of people doing dumb things with them reach the singularity of certainty.

We’ve got to do something about this before governments do it for us, with restrictions that catch the many good uses of drones in the crossfire. The reality is that most drone operators who get in trouble aren’t malicious and may not even know that what they’re doing is irresponsible or even illegal. Who can blame them? It’s devilishly hard to understand the patchwork quilt of federal, state and local regulations and guidelines, which change by the day and even the hour based on “airspace deconfliction” rules and FAA alerts written for licensed pilots and air traffic control. Many drone owners don’t even know that such rules exist.

Drones Themselves Should Know Rules of Each Area

Fortunately, they don’t have to. Our drones can be even smarter — smart enough to know where they should and shouldn’t fly. Because modern drones are connected to phones, they’re also connected to the cloud. Every time you open their app, that app can check online to find appropriate rules for flight where you are, right then and there.

Here’s how it works. The app sends four data fields to a cloud service: Who (operator identifier), What (aircraft identifier), Where (GPS and altitude position) and When (either right now or a scheduled time in the case of autonomous missions). The cloud service then returns a “red light” (flight not allowed), a “green light” (flight allowed, with basic restrictions such as a 400 feet altitude ceiling), or “yellow light” (additional restrictions or warnings, which can be explained to the operator in context and at the point of use).


Right now industry groups such as the Dronecode Foundation, the Small UAV Coalition (I help lead both of them, but this essay just reflects my own personal views) and individual manufacturers such as 3DR and DJI are working on these “safe flight” standards and APIs. Meanwhile, a number of companies such as Airmap and Skyward are building the cloud services to provide the up-to-date third-party data layer that any manufacturer can use. It will start with static no-fly zone data such as proximity to airports, US national parks and other banned airspace such as Washington DC. But it will quickly add dynamic data, too, such as forest fires, public events, and proximity to other aircraft.

(For more on this, you can read a white paper from one of the Dronecode working groups here and higher level description here.)

There’s Always a Catch

Of course, this system isn’t perfect. It’s only as good as the data it uses, which is still pretty patchy worldwide, and the ways that the manufacturers implement those restrictions. Some drone makers may choose to treat any area five miles from an airport as a hard ban and prohibit all flight in that zone, even at the cost of furious customers who had no idea they were five miles from an airport when they bought that toy at Wal-mart (nor do they think it should matter, since it’s just a “toy”). Other manufacturers may choose to make a more graduated restriction for the sake of user friendliness, adding a level of nuance that is not in the FAA regulation. They might ban, say, flight one mile from an airport, but only limit flight beyond that to something like 150ft of altitude (essentially backyard-level flying).

That’s a reasonable first step. But the ultimate safe flight system would go a lot further. It would essentially extend the international air traffic control system to millions of aircraft (there are already a million consumer drones in the air) flown by everything from children to Amazon. The only way to do that is to let the drones regulate themselves (yes, let Skynet become self-aware).

Peer-to-peer Air Traffic Control

There’s a precedent for such peer-to-peer air traffic control: WiFI. Back in the 1980s, the FCC released spectrum in the 2.4 Ghz band for unlicensed use. A decade later, the first 802.11 standards for Wifi were released, which was based on some principles that have application to drones, too.

  1. The airspace used is not otherwise occupied by commercial operators
  2. The potential for harm is low (in the case of WiFi, low transmission power. In the case of drones, low kinetic energy due to the weight restrictions of the “micro” category)
  3. The technology has the capability to self-”deconflict” the airspace by observing what else is using it and picking a channel/path that avoids collisions.

That “open spectrum” sandbox that the FCC created also created a massive new industry around WiFi. It put wireless in the hands of everyone and routed around the previous monopoly owners of the spectrum, cellphone carriers and media companies. The rest was history.

We can do the same thing with drones. Let’s create an innovation “sandbox” with de minimus regulatory barriers for small UAVs flying within very constrained environments. The parameters of the sandbox could be almost anything, as long as they’re clear, but it should be kinetic energy and range based (a limit of 2kg and 20m/s at 100m altitude and 1,000m range within visual line of sight would be a good starting point).

As in the case of open spectrum, in relatively low risk applications, such as micro-drones, technology can be allowed to “self-deconflict the airspace” without the need for monopoly exclusions such as exclusive licences or regulatory permits. How? By letting the drones report their position using the same cellphone networks they used to get permission to fly in the first place. The FAA already has a standard for this, called ADS-B, which is based on transponders in each aircraft reporting their position. But those transponders are expensive and unnecessary for small drones, which already know their position and are connected to the cloud. Instead, they can use “virtual ADS-B” to report their position via their cell network connections, and that data can be injected into the same cloud data services they used to check if their flight was safe in the first place.

Once this works, we’ll have a revolution. What WiFi did the telecoms industry, autonomous, cloud-connected drones can do to the aerospace industry. We can occupy the skies, and do it safely. Technology can solve the problems it creates.

E-mail me when people leave their comments –

You need to be a member of diydrones to add comments!

Join diydrones


  • @earthpatrol:

    True, but birds do not fly at 500 mph, through clouds.

  • Moderator

    Aviation authorities will never accept collision avoidance through LTE

  • Great article Chris...an insightful read. I have been saying for a while that all drones need their own version of a "registration plate". An electronic version using technology like NFC or wifi though, rather than a physical plate.

    At least this way it makes people responsible for their equipment :)

  • Good article Chris

    We are seeing drones are more similar to smartphones than to typical aircrafts. I like the architecture proposed, it similar to this http://goo.gl/YbWEMA

    It seems we are going towards the next architecture (see the order):
    A. Traffic management and deconfliction: LTE through operator (Connected to an ASP (Airspace Service Provider) through an API)
    B. Traffic avoidance: LTE vehicle-to-ASP connection (through an API. Is this "ADS-B like"?) and ADS-B "in" for manned
    C. Collision avoidance (Collaborative): WiFi and ADS-B transponder based
    D. Collision avoidance (non-collaborative): What do we do here?

    ADS-B transponders are still too expensive: Do you think it will be totally necessary for CA?
    And: Who is going to become an ASP: Transtrex, Skyward, Airmap, Botlink, Google? What about Dronecode?

    Some applications (like this) would be absolutely revolutionary if it would have the capability to place the pilot anywhere in the country, managing several deliveries at the same time with real time data.

    We (DBX team) are already enabling our drone with such capabilities and connectivity, but we (and many others) lack of a proper data provider (ASP): It would be perfect if we all join to Dronecode and build such services.

  • The original post and comments closely follows many posts of my own on the subject on drone safety and control here on DIYD. I'm happy that I can share the same underlying beliefs that are being developed here!

    Rob your comment is similar with earthpatrols statements to how "best" orchestrate control. Typically if there is no cell reception, it's likely that there is also less air traffic that needs control. Likewise, the "birdnet" approach is achievable if the overarching principles are right. I am a firm believer that de-centralisation of aircraft management is in many ways far superior than the centralised (through cell etc). A decentralised approach would use RF to sense and avoid other nearby airspace users directly without the need for accessing the web, although that could assist as well. 

    The solution for the FAA is with the FCC if they adopt a variation of a FCC principle (part 15): (1) This device may not cause harmful interference, and (2) this device must accept any interference received, including interference that may cause undesired operation.

    A airspace version of that principle might be: The aircraft (UAV) may not through it's inaction or action interfere with the flight of other aircraft, nor be affected by other aircraft in it's own safe operation.

    The way that birds do this is being aware of their environment. Without sense there is no aware, let alone detect and avoid. With UAV based RF this is achievable in safety margins of low EIRP range, aircraft approach speeds and altitudes. My personal preference would be to use SDR RF technology in the same fashion, essentially by opening up the spectrum to SDR RF by mandating a "sense and avoid" approach of other users to air band management as well.

    I still believe that within the next 5-10years SDR will become ubiquitous throughout technology, at which time it will be pointless to mandate RF control in order to monopolise RF use for big business. The same thing should happen with UAV regulation. Don't let the big guys dictate the use of technology for profit, rather avoid single points of failure and control by de-centralising and diversifying throughout all users. That way everyone can contribute, benefit and share responsibility too. For example UAV's could create self-healing mesh networks that not only supply typical UAV services like imaging etc, but also expand the reaches of the web via their own UAV RF network. The symbiosis of both UAV and SDR technology could then revolutionise airspace use; both for aircraft and radio communications and be resilient against all forms of internal or external bureaucratic or misuse attacks, simply by limiting the area affected by a single failure. 

    Nature employs strategies of resilience through diversity. Monocultures go the way of the dodo. Who are we to argue how nature already knows how best to organise?



  • I hope this frivolous intervention doesn't annoy anyone too much....Sorry...

    I work for a company that operates skynet, skynet5 actually. Its the communications provider for the british MOD ( and others)

    Self regulation ahead of government doing the job for us has to be the way to go though. If nothing else it demonstrates a responsible attitude

    Sure wish we'd copywritten that name.

  • Has anyone heard of BirdNet? No? (tongue in cheek) Birds manage to interact in our environment in a large scale and, for the most part, it's fairly harmonious. They don't require a centralized monitoring or shared network to go about their daily business. For the most part, folks don't talks about their safety or privacy when it comes to bird flight. So how do we design systems of that caliber?

    We, humans, consider ourselves the most autonomous organisms on the planet, and now, we find ourselves relying on a network that slowly erodes our autonomy with respect to the natural world. People, not so long ago, retained life preservation skills related to food, shelter, safety, craftsmanship, community, etc.... That's not the case anymore. Think about how reliant folks have become on "smart devices". Ironic term, is it not. In fact, the devices are detaching us from our own autonomy in the natural world.

    The "cart is before of the horse", so to speak with the idea of SkyNet as it relates to our current technical abilities to mange flying "drones". Battery technology is not up to the task yet. Lots of companies are building data abstractions and drone flight management system for infrastructure that does not exist. We don't manage our current airline infrastructure using what folks are proposing for drone infrastructure. Seems like another dot.com bubble, does it not?

    The current batch of "Consumer Drone" companies chose to identify the ease of use with that of a cell phone. It seems that approach is now biting them in the behind, so to speak, and they are quickly trying to pivot to a "higher ground". It turns out building systems for real world environments are difficult and subject to all the perils that go with it. I think, for the most part, the industry aspect of drones has become a hammer looking for a nail. Maybe we should slow down and do a little introspection about why we need/want these "drone" systems other than for profit. Maybe that will help us focus on developing technologies that really have value for improving our human condition.

    SkyNet Out. :)  

  • Developer

    Good article.

    From the ardupilot side I suspect/hope we will add the no-fly-zones / stay-out-zones to Copter-3.4.  The first step of that implementation is actually to make the vehicle stop at the edge of the circular fence instead of triggering RTL like it does in Copter-3.2.1/Copter-3.3.  So the vehicle will need to find the closest point on the fence wall and make sure that it slows down in time so that it doesn't hit it.  The next step after that is checking from a large database of walls.

    Like Chris says though this project requires changes at all levels of the system to ensure the latest data is there on the vehicle so the avoidance algorithm can work.

  • Moderator

    You can't take my rights away from me. That I think is the biggest issue, people believe they have a right to do things that they never had!

    Interestingly in the South African regulation, and I think this one is obvious if you are an adult the craft you are flying ceases to be a toy even if you bought it from a toy shop, as an adult you are held to a higher responsibility. Gary is right, weight and reduced endurance is the way forward. 

    Have a look at the South African airspace on mission planner, much more complete than the rest of the world. Perhaps its time to put our own house in order. I agree with Rob this sort of thing has to be baked in,

  • Very good article, and I also agree with the starting points, that these things have become too easy to fly which has led to many irresponsible people flying them.

    I also mostly like the solution you propose.  But it has a problem.

    What to do in places where there is no cell phone coverage?  This is not much of a problem in the US.  But it's a huge problem in places like Canada for example, where probably less than 10% of the land mass (maybe as little as 5%) actually has effective cell phone coverage.  The solution simply won't work in this case.  

    I think at least some subset of regional data will need to downloaded onto the aircraft for off-line use, much the same way it is done for Google Maps, etc.

This reply was deleted.