Slashdot Mirror
SwarmOS Demonstrated at Idea Festival
PacoCheezdom writes "Intelligent Life has short summary of a demonstration by MIT professor James McLurkin of his new group-minded robots, which run an operating system called 'Swarm OS'. The robots are able to work together as a group not by communicating with all members of the group at once, but by talking only to their neighbors, and model other similar behaviors performed by bees and ants. "
Bees and ants seem to be a good argument that it might be a good return on investment. So do search parties when looking for lost hikers.
Swarm of UAVs for surveillance of hostile (and friendly?) countries. UAVs work together to accomplish goals such as "make sure there is a flyover of areas X Y and Z every 10 minutes", "keep a unit no less than 5 minutes away from this location", "keep 20 units in the airspace, but make sure each unit charges to at least 40% at all times."
I was there, saw the demonstration, and wondered why this was being done on physical robots rather than on virtual robots. I guess its more impressive to see the little cars roaming around with their blinky lights.
The part of the presentation I didn't agree with was the myths about robots taking over. I think that robots alone won't take over, but once we supply them with the true ability to learn like the human brain learns, we will be dealing with something other than a robot, and its intelligence will quickly surpass a human's. Someone, somewhere, will give it (or a version of it) the means to replicate and improve upon itself, and eventually it will emerge from that as an unstoppable being. Some misguided country will give it human rights and sanctuary, and soon we won't hear from that country again...
Its not science fiction, its science reality. Given time, a brain will be created. The mistake we make today is assuming that we'd have to program it to be smart... We wouldn't. If we create the workings of a brain and expose it to experiences, it will make itself smart.
From TFA : "...James McLurkin, a PhD student at MIT Computer Science and Artificial Intelligence Laboratory..."
He's a student, not a professor. Way to read the article, Mr. submitter.
An application of what, specifically? Machines that talk to each other and not to the whole group and do something useful? You mean, like Bittorrent? :)
Seriously, though, this is some very cool research; the robots talk to each other via infrared, which is why they can only talk to their neighbors. But, with the infrared setup they're using, they can estimate direction and distance to each of their neighbors. You COULD do this with a bunch of robots talking bluetooth with GPS receivers, but it would be insanely expensive by comparison. These guys would be dirt cheap if mass produced. Dirt cheap means you don't care if you loose a few, which makes them excellent options in harsh environments.
A lot of the research in this area right now is in algorithms. Designing an algorithm to run distributed over a group of small, dumb, physical devices, where individual devices might suddenly disappear (batteries die, fall down a hole, consumed by fire, eaten by ewoks, etc...) is quite difficult.
If you're looking for a practical application; thousands of bug sized robots which scour a collapsed building for survivors, and direct rescue efforts. If you loose a few, who cares? They're cheap! Or how about thousands of small rovers which explore the surface of an alien planet? If you send a single rover to Mars, you're putting all your eggs in one basket; if something goes wrong with that rover, you're whole mission fails. A collection of cheaper robots which can work together dramatically looses your odds of failure, since the failure of 10% or 20% of the swarm would be immaterial.
Wow, self-healing minefield. Are we on newspeak yet?
-josh