Slashdot Mirror
Smart Flying Robots
Chernyakov writes "MARVIN, a fully autonomous RC helicopter built by the Technische Universitaet Berlin, won the
2000 International Aerial Robotics Competition.
MARVIN has a radio-linked ground station consisting of several networked Linux machines (which provide the computing power for vision, mapping and flight-course generation).
The robots' mission is to fly into a disaster area complete with fire, water and smoke hazards, to locate and avoid threats to itself, to find bodies, distinguish from survivors and the dead, identify hazardous materials containers, determine if the container contents are radioactive, biohazardous, or explosive (by reading the labels), generate a detailed map of the disaster area, photograph the area, and return safely back to base.
MARVIN pulled it off completely autonomously, with no human help or intervention. High quality (90 MB) and Low quality (12 MB) MPEGs of the robot are available."
***JUMP PAD ACTIVATION INITIATION START***
***TRANSPORT WHEN READY***
***JUMP PAD ACTIVATION INITIATION START***
***TRANSPORT WHEN READY***
This is excellent advancement. The more places we can use robotics to replace humans in places of danger, the better.
Heres a thought...how many of these sorts of "disasters" are created by humans? If more robotics are used in daily life, could human error be downplayed, therefore reducing the situations in which humans might be put into danger? Prevention is the best cure, they say...
-- Merc "And you thought you were your own worst critic."
It's going to do all of those things, eh?
I don't know how they're coding it, but they're probably going to hype it as "Artificial Intelligence"!!!!!
What if the person is unconcious? Is that a dead person or an alive person? What if they're alive, but not breathing? Could it even tell if they were breathing? Could I fool the machine into thinking I was dead?
The problem with these types of things is that they fall into two categories - machines that are so totally wrong in what and how they judge things that they aren't even worth looking at, and machines that are right some of the time, and so horrendously wrong when it counts that they aren't worth looking at.
Well that's my cynical $0.02 anyway.
-- Truth goes out the door when rumor comes innuendo. -- Groucho Marx
Neat, who would have thought my OS would help me survive one of Hotblacks shows??
"They do not preach that their god will rouse them, a little before the Nuts work loose." Kipling, 'The Sons of Martha'
"A brain the size of a Beowulf cluster, and what do they have me do? Fly around disasters taking pictures..." *sigh*
#!c
include kill.o
open missle compartment
missles = 20
fire missiles
/* if people dead 200 then goto 20
goto 10
20
missionaccomplished()
load destroyworld.h
destroyworld = 1
end()
Visit my website xpenguin.com -- A linux penguin website
Check out the aerobot. This VTOL aircraft uses ducted fans insead of a conventional rotating airfoil, and is capable of autonomous take-offs and landings. Also check out the wankel-powered Skycar.
--
The real Webmaven is user ID 27463. I don't rate an imposter, because my ID is such a lame-ass high number.
I'm of the opinion that Slashdot really needs to mirror a third of the sites that are linked to, or at least the giant gobs of multimedia content. I think VA can afford a few cheap servers to spit out static content. Seriously, 90MB in Germany. If the movies had been mirrored, the .de site would still be up.
In order to fly autonomously (by itself), MARVIN uses a LOT of hardware: 3 accelerometers, 3 gyroscopes, 3 compasses (redundancy), 2 ultrasonic range finders, a differential GPS system (accurate to 2 centimeters), a fire detector, and an altimeter. It also has an onboard CPU, communications equipment, power distribution, etc.
.60-size XCell.
The helicopter itself looks like a standard
Anyone who has ever flown an RC helicopter knows how difficult it is for a human, much less a computer. The software usually involves use of a Kalmon Filter to fuse the sensors, and neural networks to build fuzzy control rules for the flight surfaces (aileron, rudder, collective, etc) in real-time.
The video, boring for some, shows the helicopter taking off and flying over the disaster area. The heli adjusts its location constantly for better views of targets then flies away and lands. There are good shots of the ground station showing Mission Control, robot-vision, and flight-path mapping. Also some good shots of not-so-successful flights and what can go wrong.
This is the tenth year of the IAR Competition; each year the mission gets more complicated. In 1991, autonomous flying vehicles (no hovercraft) simply needed to pick up a disc at one end of the field and drop it off at a deposit-point on the other end. No one completed the mission that year.
As a side point, let me just say that technology can always be used for evil, but development of robots such as these are most useful in what the industry terms D^3 (D-cubed) environments: Dull, Dirty, and Dangerous.
Dull: Flying over thousands of acres of forest painstakingly examining almost each tree for insect damage.
Dirty: A disaster area with potential exposure to lethal gases and the like.
Dangerous: Photographing a volcano for threat analysis.
I have a copy of the 90 MB mpeg -- I'll try to mirror it on Mojo Nation, but my one-way cable modem might not like it.
----
Every year during my review, I just pray the words "slashdot.org" aren't mentioned.
I don't know about you all, but those "disaster areas" remind me an awful lot of my apartment.
____________________________
"File swapping on the internet is putting at risk nothing less than human progress and prosperity"
--Microsoft quote
Helicopter pioneer Igor Sikorsky
However, the helicopter did come to be
used for other purposes.
Party pooping away,
--Apuleius
Like a battlefield?
"to locate and avoid threats to itself, to find bodies, distinguish from survivors and the dead,"
So it can save ammunition?
"identify hazardous materials containers, determine if the container contents are radioactive, biohazardous, or explosive (by reading the labels),"
So it can identify vehicles which look like large metal containers, and to IFF by reading their markings?
"generate a detailed map of the disaster area, photograph the area, and return safely back to base."
Somebody wants this, and it isn't the Boy Scouts.
*whup* "Get along, little electrons. Heeyah!"
Actually, if you researched this, he aimed the device at a running car....and the engine ran roughly.
Oooooo. Scary!
I think they even had the hood up.
Later,
Erik Z
Democrats or Republicans. They are both taking us to the same place and they are not afraid of us anymore.
...can be pretty darn spectactular. Or so I've heard. I've seen (and been responsible for) my fair share of crashes, and they can be pretty impressive on their own. The momentum in a 4ft diameter set of wooden rotor blades revolving at 2000rpm is quite serious. And unlike those boring Battlebots that are all steel, industrial strength and semi-indestructible, stuff that's designed to fly has to be light and therefore not too strong. A Heli-Battlebot battle would be short but impressive!
Oooooooo.... You've made me verrry ANGRY,VERRRRY ANGRY INDEED! I will have to nuke you now, miserable earth creature...
With apologies to Mel Blanc.
"Depression is merely anger without enthusiasm." - Anonymous
Well, while there are certainly military applications of this technology, there are also genuine humanitarian ones - such as the claimed fire disaster area survey. Each year many firefighters lose their lives, particularly trying to combat forest fires and trying to rescue people - or whole towns - from such areas.
Some people have suggested other flight platforms, particularly from Moller, but while the Aerobot looks nice it is somewhat expensive, and the Skycar looks unsuited to perform an tasks for which the system was intended. What is really important, though is the control electronics, vision system, etc.
The German system seems to do a nice job with this (note also that Germans, at Mercedes-Benz, are the farthest along - at least in public - on autonomous robot land vehicles). What would be an interesting next challenge would be to try to scale-up from small helicopters to, say, a full-blown bell with stretcher pods and have the system be able to perform rescues of humans whom can be determined to still be mobile enough to get themselves onto the craft.
Regarding detecting the difference between dead humans, unconscious humans, and alive but not breathing humans - first of all, those are distinctions that are hard for humans to make from a helicopter, so it's an awkward comparison. Furthermore, using infrared technology, the system would be better at detecting humans who died long enough ago that they were starting to get cold from others - something a human can not do while airborne.
If you want to distinguish the unconscious, dead, and almost-dead you need to send in a land-based robot with some medical technology for making the distinction (but how do you TEST that system?)
Right now, I think humans will be used for this.
Also interesting would be to test the system for ability to deliver payloads (yeah, it could be bombs, but it would be interesting to test its accuracy in dropping medical supplies to those in a disaster area who are still mobile enough to use them...)
o/~ we are pissed, we are pissed, we have to resist... o/~ - ec8or
Well, when the fire broke out at the mannequin warehouse there were all these warm bodies scattered around...