Slashdot Mirror
Robot Swarm Control On Microsoft's Surface
zerOnIne writes "Dr. Mark Micire of UMass Lowell has built an intriguing new user interface on the Microsoft Surface, a multitouch-capable table computer. The interface is being used to control swarms of robots for disaster response, search, and rescue. One of the most interesting things about it is the intuitive tabletop joystick widget. Using a very fast hand-detection-and-identification algorithm, they can paint a touch joystick (dubbed the DREAM controller) directly underneath the hand. This joystick conforms to the size of the user's hand and tracks with hand movements, making sure that the control is always directly under the hand where the user expects it, even without haptic feedback. I've had a chance to go hands-on with this system, and I think it's truly remarkable."
Still somewhere over $5k?
I'd love to build this into something... if I could sell it to someone other than businesses looking for a way to waste money.
Out of modpoints but really liked a post? 1BDkF6TtmmeZ3yqXbz9yhdYVqRYnwFoXDj
This is amongst the coolest things that I have seen in a long time. Unbelievably cool and useful. Microsoft, I bow to you - the table seems to be the future of computing - if not amongst the masses - atleast amongst planners and decision makers.
Although it makes me sad about my existence as a person though - doing a 9x5 job which is neither cool, nor very useful for humanity as a whole.
rajmohan_h@yahoo.com
Using a Microsoft product to control a swarm of (potentially killer?) robots?
Finally. A decent interface for C&C.
-- I have a private email server in my basement.
The problem with RTS games path finding vs robot path finding is that the games have a flawless description of the environment (the description IS the environment) and no inherent physical limitations on the driven device, only ones programmed in.
A real obstacle can move, can be hard to spot or misrecognized as non-obstacle, can resist traditional methods of surmounting it (say, is slippery or crumbles). A real robot has to deal with traction slipping, in route deviating due to slipping on the surface, limited acceleration and braking power, environment behaving against specs (tell a crumbling building to follow the computational model...), communication shortages and so on.
Also, this is a demo, to let people see how that works. I believe it could be done 20 times faster by an experienced operator doing actual work instead of a demo.
45 5F E1 04 22 CA 29 C4 93 3F 95 05 2B 79 2A B2
Isn't the "swarm of robots" aspect slightly more interesting than the "touchscreen interface" aspect?
... and then they built the supercollider.
NOTICE: no robots swarms were actually controlled in the making of this story
The whole point of this is to micromanage troops. Sure, you can control large numbers of units efficiently using that, but can you control a trio of SCVs to heal each other, another 4 to poke a group of irritating zergling, swap roles to make sure all of them receive no casualties, and initiate an SCV rush on a zerg base? (well, unless you're korean)
I don't know weather to laugh or scream.
In case you're interested, there has been some nice work in using tabletop interfaces (ie. Microsoft Surface) to control home robots, like the iRobot Roomba.
Yeah, I saw that episode of Saturday Night Live too. I laughed at it. I enjoyed it. With me so far?
It aired April 8, 2000, more than ten years ago. It got old. You're not funny or clever. You're not some kind of deep, cultured, worldly guy. You're some dude on Slashdot who's repeating something from ten years ago that was amusing but not all that funny in the first place. It was a bit funny back when that ugly fuck Christopher Walken said it and it was a new skit. It's repetitive now.
You might as well parrot another predictable, cookie-cutter, assembly-line Slashdot meme. The only difference is that it would be a Slashdot meme and not a pop culture meme. Nothin' personal. Just that Slashdot will be greatly improved when we stop celebrating this bullshit.
Microsoft surface being used for search and rescue. Doesn't the EULA specifically state "not to be used for life saving operations or operations in which failure of the system could result in bodily injury"? A search and rescue robot certainly qualifies as a life saving device, the failure of which could result in people being dropped or crushed.
I wonder why the researchers that made this felt that disregarding the EULA was acceptable.
-1 disagree is not a modifier for a reason. -1 troll, flaimbait, redundant, overrated are NOT acceptable substitutes.
This demo was a simulation, so there really isn't that much difference from a good RTS. Motion control and local path planning are well understood.
While the demo looks cool, it is not really much different than the robot GUI I wrote for my robocup team that could control 10+ robots (real or simulated). It used a mouse and any number of ps3-style controllers. And yes, I got my ideas from RTS games, and some other teams had even better GUIs.
Also, it would have been nice if they didn't speed up the video, so we could better understand how well it worked. One thing I often find in touch interfaces is that selection is slower than you'd expect since you block the item with your finger. A mouse pointer is much smaller, and works well for skilled operators.
"Surface" is yet another piece of slightly-interesting-in-theory-but-kind-of-meh-in-reality tech that microsoft has been trying to get people enthused about for ages -- and consistently failing. You know, kind of like tablet computers before Apple actually made people want them.
I wouldn't be at all surprised if Apple suddenly teams up with Ikea and has every living room in the country computing with their coffee-table within 3 months though.
We live, as we dream -- alone....
The problem with RTS games path finding vs robot path finding is that the games have a flawless description of the environment (the description IS the environment) and no inherent physical limitations on the driven device, only ones programmed in.
Well, that and the utter LACK of any ACTUAL ROBOTS to guide. (Or those few that do exist are so damn expensive nobody can afford a swarm of three).
Oh, and those Surface tables... Those aren't exactly laying around anywhere either.
But overlooking that minor obstacle for the moment, the first thing that goes to hell when you actually NEED a robot swarm is that flawless environment description. And of course situations needing swarms never occur where you have maps, they happen annoyingly in some remote area, immediately adjacent to (but outside of) the area your funding covered.
Perhaps thats why the summary is so ga-ga about the joy stick simulation, because its the only part of this that seems remotely usable on Joe SixPack's touch screen device.
Sig Battery depleted. Reverting to safe mode.
1) User swats away a fly
2) A thousand robots charge off the edge of a cliff
3) ???
4) *Sigh* Back to the drawing board
Confucius say, "Find worm in apple - bad. Find half a worm - worse."