Maybe I missed it, but contra the title, I did not see any robots flying in the TED venue. Since I've seen most of these other vids (but not that), that's what I was looking for :(
On of the students is carrying an RC remote when he comes on stage at the end.
It would be very hard to fly these little guys autonomously at TED, since they use the off-board Vicon multi-camera IR motion-tracking system in their control loop. That's a big, expensive installation in the lab.
Kumar's group is very well respected in the field. They've had several years of strong innovation. Vijay is really good at what he does, and a nice guy.
It might have been too much effort to set up the multi-camera Vicon motion capture system at TED, calibrate it, etc.
And unless they put them inside an aviary, which would also obscure the drones, I'd be a little worried about losing control of a machine with several exposed spinning blades in an auditorium full of people.
The Kinect-mapping quadrotor was the most interesting demo; that could be useful today. Imagine letting loose a swarm of quadrotors in a large building and having a complete map and textured 3D model of the interior and exterior within just a few hours.
The Kinect has a very limited range, is not accurate and works only in certain lightning condition. That's why they added a laser scanner. Those are over $1000.
Then in order to build the map via SLAM in real time you need a really powerfull PC/Laptop. Even a netbook is not going to do it, at least for the SLAM in ROS(ros.org).
Then it looks like they added a all angles are 90° assumtion, because normally the map does not look that nice because little errors accumulate.
So it will take a while till we see something like that outside universities.
Kinect-like sensors are going to improve very quickly (http://www.theverge.com/2012/2/29/2834088/samsung-camera-sen...), as are SLAM algorithms using Kinect-like data. High cost isn't necessarily a problem for this application, as one team of copters could map many facilities. Computing power can be mostly centralized at a base station that can be as beefy as you want. Certainly a commercial product is years rather than months away, but I think even this limited demo could already be useful for e.g. mapping the nuclear reactors at Fukushima.
Hey quit being a letdown, this really amazing stuff. You should reword it more like:
"The video is showing amazing new thingamabobs that will get less expensive over the next few years, and pretty soon you will all be able to use robots like this in your everyday life".
For many (perhaps most) buildings, I imagine a simpler wheeled or tracked vehicle would be just as effective and surely cheaper, more reliable, and more robust.
Navigation for land based robots is a much harder problem. I would expect quadrotors to be more reliable actually (only four moving parts! No ground contact!) with the ability to map areas inaccessible to wheeled robots, and much faster to boot.
It sounds cool, but this seems like a very expensive way to accomplish a fairly mundane and useless task...
The problem with trying to make money using robots is that we still have plenty of people on the planet looking for unskilled work. I don't think we will reach the economies of scale necessary to make robots practical unless that changes.
Um, many industries, auto, electrons assembly have All ready been robotized. People are expensive, have short work cycles and break down often, and require much more maintenance and infrastructure. You have missed the revolution buy a hundred years
"Imagine letting loose a swarm of quadrotors in a large building and having a complete map and textured 3D model of the interior and exterior within just a few hours."
This reminds me of: "I’ve long been interested in Navicubes, which is what I call a small and not-quite-here yet $5 box that always knows where it is, which direction it is facing, and which way is up. Besides vehicle nav, intelligent toys, and robotics, these would open up all sorts of neat tricks, such as a ball you could simply bounce off cave walls for mapping."
That was weird. I read, "Aerial robots swarm the stage at TED". I thought how rad of a demo that would be. Then I saw "[video]". And got excited to see video of a TED talk with robots swarming the stage.
The canned video they had was riggin' rad, but I was disappointed. Damn you, Ken Fisher!
After seeing these mind-blowing quadracopter videos from UPenn popping up online all over the place for the past couple years, its great to finally see a culminating talk about the work being done there. Congrats guys!
This is just the thing I love to see on Hacker News. Every time you see this I remember why I spend all those hours hacking and learning. Really lights a fire under your ass.
The second thing I thought of was how cross-border and urban illegal drug distribution is gonna be made much easier with this. I won't be part of it, but, just sayin'.
One of the things I think of when I see autonomous quadrotors is a localized missile defense shield.
A swarm of disposable quadrotors surrounding a ship, set on a rotating recharge schedule, that intercept missiles and detonate a small explosive payload.
Unfortunately, I agree. From the first time I saw this technology the top application that jumped off the page to me was of a military nature. Perhaps a day will come when this may not be so. Until that day comes, tech like this, I believe, will save lives; on and off the battlefield.
The scariest part of inventing/innovation; the realization that what one creates may fall into the hands of those with aims that are less than noble...
These things might be too slow to intercept an incoming missile, especially the super sonic ones. The quadrotor doesn't look like very energy efficient. There are 4 rotors to draw energy. They must need to recharge pretty quick. With a large number of them, the energy draw from the ship is pretty demanding.
>With a large number of them, the energy draw from the ship is pretty demanding.
There are destroyers on the drawing board with enough excess capacity to power rail guns, and the latest aircraft carriers have upgraded reactor units to power the electromagnetic launch systems they use instead of steam catapults.
The reactors that supply these large ships should have plenty of excess power for a few hundred drones.
>These things might be too slow to intercept an incoming missile, especially the super sonic ones.
They don't have to match speed, they just need to place themselves in the path of the missile; they are incredibly agile and shouldn't have trouble doing so.
It would be much harder to overwhelm with multiple missiles.
You have to place Phalanx systems all around the ship in order to provide 360 degree protection. However, an enemy could concentrate multiple missiles on a space covered by only 1 Phalanx.
If radar detects multiple missiles inbound, more drones could be easily be routed to the appropriate area to intercept. To overwhelm the defense you'd have to fire more missiles than the ship has drones (and since drones could be made much more cheaply than supersonic missiles, that would be fairly hard to do).
Would make an excellent start-up idea. :-) Please do it, someone. I don't have the time, but need a burrito. For pure zeitgeist win, add grilled cheese to the menu, too.
