Slashdot Mirror

It is a Viconsystem. They are pretty standard in robotics research labs. They are used from motion capture and localization. I imagine at this point it is needed for them to function properly but could later be replaced with any method of localization, gps or the likes.

These flying bots remind me of you average Alaskan mosquito.

Those bots are not even half as advanced as a mosquito (and far from houseflies) though. Mosquitoes can fly for one to four HOURS: http://www.sove.org/Journal%20PDF/June%202004/Kaufmann.pdf

Mosquitoes can navigate and orient in dynamic environments without requiring external cameras and computers ( http://www.vicon.com/company/documents/UPENNGraspLab.pdf ). They can find their own sources of fuel, and avoid active and passive threats. They can even produce new mosquitoes in a few days/weeks without a factory.

They can get confused by bright/UV lights, but it's still quite impressive considering their brains are so tiny.

So these bots are interesting, but there's plenty of room for improvements :). We're still not in danger of Skynet bots yet...

I'm a cognitive scientist and am a member of one of the teams who have been working with the MS SenseCam device (now to be called Vicon Revue), doing memory research. Most of us are academics and clinicians collaborating with Microsoft Research.

This kind of technology (i.e., wearable automated sensors, cameras, etc. that capture massive troves of data about one's experiences) is becoming cheaper, better, and more ubiquitous. But we're still just beginning to explore the many possibilities for research and for clinical or everyday applications. And of course with these possibilities come a host of technical, ethical, and social issues for us to confront.

We just concluded the SenseCam 2009 symposium in Chicago, which featured a lot of really interesting research and discussion, amongst collaborators from cognitive psychology, neuroscience, computer science, clinical psychology, public health, etc.

The developmen of control laws that are able to fully control the aircraft flying in those conditions, (not to mention being able to handle the transitions between such flying modes) is a hard problem.

This is due to the fact that the overall system is highly nonlinear, scarcely controllable, (since the control surfaces have little to no effect), and also not very well known in such conditions.

What if you had a very high degree of positional awareness? Wouldn't that make it a lot easier? I'm asking because I suspect that is exactly what those red (probably LED based) lights around the room are for. Look at how they are pulsating in the slow motion video (towards the end of the youtoob clip).

Just one possible scenario; Those lights look a lot like the Vicon motion capture cameras with LED rings. (although different enough, those are probably not actual Vicon cameras). The Vicon system can measure the position of a bunch of retro-reflective dots pretty accurately. In other words, it could provide pretty accurate absolute position of few key positions on the airplane.

Not that that wouldn't be a cool hack, but to me would be really stretching the 'autonomous' part of the equation...

But software will only take you so far. There's a lot of unique PC to human interactions that are possible, but this world needs more hardware hackers.

In any case, this is a neat demo. People have been doing this on a much bigger, 3D, expensive $$$ scale with something called a Vicon Motion Capture System. They basically take a whole bunch of those cameras, and a whole bunch of LED arrays, and strobe them so that they get a picture of little reflective points from many different angles. They then use some trigonometry to figure out where, in 3D space, a particular point is. Cool stuff -- good to see it's being brought closer to everyone's homes, rather than the tens of thousands of dollars that Vicon charges.

--
Educational microcontroller kits for the digital generation.

To lump all computer vision together and say "it's not there yet" is phooey! There are lots of problems in vision, and they do get solved, but those problems are all specific-- you can't use a red-light-runner system to do facial tracking...

Its called motion capture. Vicon are among the best in the business hardware and software wise for this sort of thing. I believe they used vicon hardware in FF-TSW if I'm not mistaken.

But fifty years in the future, even 10 years hence for some cases, one would not need special gloves or such obvious markers. Computer vision should certainly be able to track subtle hand movements in 3-D space, as well as facial expressions.

The rest of the video scrubing stuff just looked like advanced Avid nonlinear editing software. Now, the AI in Blade Runner and 2001 is still way, way cutting edge, perhaps beyond our lifetimes, assuming average body mileage.

For hand-editing, the character animation software in Maya may be a good place to start. Or, look at any of the "bipedal toolkits" for other 3D animation packages. There are packages designed specifically for facilitating hand-animation of humanoid figures. Still, you're talking several grand and a relatively beefy computer for this.

I believe that AnimationMaster has basic support for this stuff as well, and it can be had as cheaply as $299. Possibly worth some extra investigation there.