DARPA’s Autonomous Microdrones Designed to Patrol Inside Houses

Tech Swarm – by Nicholas West

As drone expert, P.W. Singer said, “At this point, it doesn’t really matter if you are against the technology, because it’s coming.” According to Singer, “The miniaturization of drones is where it really gets interesting. You can use these things anywhere, put them anyplace, and the target will never even know they’re being watched.”

This has been the promise that the Air Force made quite clear in their video early last year about nanodrone tech that you can see below. According to the USAF, Micro Air Vehicles (MAVs), combined with the ability to harvest energy, will enable insect-sized drone swarms to be dropped from military aircraft to stay aloft for a prolonged amount of time, offering a host of functions, including assassination.  

DARPA is now announcing a new wave of these microdrones under the Fast Lightweight Autonomy program. As the name indicates, they ideally would like humans to be completely removed from the control process.

For now, they clearly state “overseas” as the theater of operation, but it doesn’t take much imagination to see how these microdrones could be applied in the U.S., especially amid an increasingly tense urban environment in the wake of confrontations with domestic police. And, as always, the tantalizing application in disaster relief paves the way for easy introduction.  

(My emphasis added in press release)


DARPA aims to give small unmanned aerial vehicles advanced perception and autonomy to rapidly search buildings or other cluttered environments without teleoperation.

Military teams patrolling dangerous urban environments overseas and rescue teams responding to disasters such as earthquakes or floods currently rely on remotely piloted unmanned aerial vehicles to provide a bird’s-eye view of the situation and spot threats that can’t be seen from the ground. But to know what’s going on inside an unstable building or a threatening indoor space often requires physical entry, which can put troops or civilian response teams in danger.

To address these challenges, DARPA issued a Broad Agency Announcement solicitation today for the Fast Lightweight Autonomy (FLA) program. FLA focuses on creating a new class of algorithms to enable small, unmanned aerial vehicles to quickly navigate a labyrinth of rooms, stairways and corridors or other obstacle-filled environments without a remote pilot. The solicitation is available here: http://go.usa.gov/MGWx

The program aims to develop and demonstrate autonomous UAVs small enough to fit through an open window and able to fly at speeds up to 20 meters per second (45 miles per hour)—while navigating within complex indoor spaces independent of communication with outside operators or sensors and without reliance on GPS waypoints.

“Birds of prey and flying insects exhibit the kinds of capabilities we want for small UAVs,” said Mark Micire, DARPA program manager. “Goshawks, for example, can fly very fast through a dense forest without smacking into a tree. Many insects, too, can dart and hover with incredible speed and precision. The goal of the FLA program is to explore non-traditional perception and autonomy methods that would give small UAVs the capacity to perform in a similar way, including an ability to easily navigate tight spaces at high speed and quickly recognize if it had already been in a room before.

If successful, the algorithms developed in the program could enhance unmanned system capabilities by reducing the amount of processing power, communications, and human intervention needed for low-level tasks, such as navigation around obstacles in a cluttered environment. The initial focus is on UAVs, but advances made through the FLA program could potentially be applied to ground, marine and underwater systems, which could be especially useful in GPS-degraded or denied environments.

“Urban and disaster relief operations would be obvious key beneficiaries, but applications for this technology could extend to a wide variety of missions using small and large unmanned systems linked together with manned platforms as a system of systems,” said Stefanie Tompkins, director of DARPA’s Defense Sciences Office. “By enabling unmanned systems to learn ‘muscle memory’ and perception for basic tasks like avoiding obstacles, it would relieve overload and stress on human operators so they can focus on supervising the systems and executing the larger mission.”

Since the focus of the program is improving perception and reducing dependence on external sources—as opposed to designing new small UAVs—DARPA will provide performers selected for the program with the same small UAV testbed as government-furnished equipment.

Source: DARPA

– See more at: http://www.techswarm.com/2014/12/darpas-autonomous-microdrones-designed.html#sthash.whHmqe9O.OsDD5VbB.dpuf


4 thoughts on “DARPA’s Autonomous Microdrones Designed to Patrol Inside Houses

  1. Time to upgrade my flyswatters.
    Maybe we’ll get lucky once the bugs are armed. The autonomous switch gets flipped and the bugs attack and kill everyone who works at DARPA.

  2. Well….if it’s running a microsoft…. OS…. it’s going to have to have monthly pushes for security updates from their HNB1 security slaves. Which means you’re going have to offer it curry and rice to stop it from giving you a haircut. Or an unexplainable black eye or bruise the next day at work…. ! Can you say….
    Domestic micro drone violence.. ?

    C’mon attorney’s

    Theirs some money to be made here.
    for future litigation.


    1. I’m sure those evil cowards would love to have something like this. The Empire has been working on it since 2006 at least, judging by the posting date on an Air Force YouTube video I saw. Of course, as soon as the Empire develops it, other countries will follow suit — just like with nukes. Way to make the world a better place, you rotten DARPA scumbags.

      Fortunately, the technology they’re describing here is a very long way off, if it’s even feasible at all. It’s really a clumsy thing they’re attempting to do.

      1. First, there’s the issue of battery life. Battery technology hasn’t developed nearly as quickly as computing power. For a drone the size of a really small insect, I’d be surprised if they could achieve five minutes of flight — and that’s before they add a payload. How much weight can a real insect carry in flight?

      2. While computing power has come a long way, we’re approaching the physical limits of Moore’s law. Good luck getting sufficient computing power for any kind of AI into such a tiny, lightweight package. And that computing power is yet another drain on the battery.

      3. How big are the antennas going to be on these things? They would have to be very small and light to work on something bug-sized. How well will these things transmit through walls or foliage? What will the range be? Ten yards in open space? And once again, this will be a drain on the battery.

      4. Reliability is still a nontrivial challenge even when designing relatively simple weapons such as firearms. How reliable do you think these tiny, fragile drones will be?

      5. Even if these can be built, they probably won’t be as stealthy as some might think. People tend to notice when things are flying around indoors, crawling on the wall, etc. Anything fly-sized or larger will be as subtle as a whore in church. And good luck making them quiet enough while still sufficiently powerful to carry any payload.

      6. Imagine that you have a tiny UAV like one of these, only rather than it being autonomous, you are controlling it. If you try to fly it into a building when someone opens a door, you risk being noticed and your toy captured. How easy do you think it would be to guide it into a modern home or building with its doors and windowscreens all closed? And without someone hearing it banging around in the AC vent as you try to find your way? And find your way around inside while looking through that tiny camera? Without getting stuck or damaged? It would be difficult enough for a person, so how is AI going to manage, let alone AI being run on such a tiny computer?

      Don’t get me wrong: UAVs the size of your thumb already exist and are in use. But they have limitations related to those mentioned above: short battery life, limited range, line-of-sight operation only, not autonomous, easily noticeable unless distant from the target, and VERY expensive (>$100K each for one model I read about).

  3. DARPA =


    Go to hell DARPA……

    I Put a curse on you to be reincarnated as toilet paper…. so you can see all the shit you have done to humanity ! You.. your children and grand children… ten fold…
    as the creator GOD as my witness and authority !

    F□ck you devil worshipping souless @ssholes.


    You’re Goddamn right !

Join the Conversation

Your email address will not be published.