A Mobile Robot For Modeling The World In 3D

Roland Piquepaille writes "A German team from Fraunhofer AIS has coupled a fast autonomous robot with a 3D laser scanner to digitize the environment. The team reports about their work in this article, one of fifteen on the subject of machine perception published by ERCIM News. "Kurt3D is an autonomous mobile robot equipped with a reliable and precise 3D laser scanner that digitalizes environments. High quality geometric 3D maps with semantic information are automatically generated after the exploration by the robot." This overview tells you more about the four-step method used to generate 3D models with this robot and contains several pictures of Kurt3D and its 3D laser."

Comments

Out of curiousity...

[Pakaran2]

How does this thing figure out distances? Does it time the return of the laser reflections?

I also can't help wondering how it models the tops of things - it looks like it's fairly squat.

What's the advantage of a robot like this versus describing every object by hand, as 3d animators do (typically in some kind of interpreted language).

It seems like writing "there's a sphere of radius 3 centered here" would take less time than waiting for the robot to scan it.

Re:Out of curiousity...

[apraetor]

Parallax would make sense. That's how most (all?) optical rangefinders work.

--matt

Re:Out of curiousity...

[merlin_jim]

What's the advantage of a robot like this versus describing every object by hand, as 3d animators do (typically in some kind of interpreted language).

It seems like writing "there's a sphere of radius 3 centered here" would take less time than waiting for the robot to scan it.

well, it's like the difference between what the public perceives a dictionary as, and what a dictionary actually is.

For instance, when I was a senior in high school, Webster's started including the word ain't. Now some teachers were very upset by it while others were ecstatic.

Then my english teacher put it in perspective.

Many people belive that dictionaries define a language. They do not. They describe a language.

Same thing here. Sure you could model a building by hand, but what you get is a definition of an ideal building. Whereas 3-D laser scanning describes the building as it is, very precisely.

Real world examples where this is a good thing?

Well recently they did some 3-D scans of stonehenge. The scan data was precise enough to show markings on many stones that had never been seen before (too shallow / worn)

Or imagine a world of the future based on some form of 3d on-demand printing that's cheaper and stronger than traditional fabrication. We already have that in certain fields, BTW... it's quickly growing to be universal. You have a 3D laser system that precisely measures an existing building, and then a printer that prints new structures to be joined to the building instantly, automatically precisely sized and positioned.

Re:Out of curiousity...

[Squeebee]

Well, first of all laser rangefinders are nothing new, and yes, timing of the return trip is where it's at.

Modeling the tops of things is probably going to be a disadvantage for this one, but typically shape and height are enough for most scenarios, what the top looks like is not usually as much of an issue (though we can likely determine if the top is round/triangular/flat if we can get far enough away).

The advantage of this over an animator's definition is accuracy. If you want an exact 3d model of a building for, say architectual purposes, you want to know exactly where that sphere is in the room, not some abstract rendition by an artist (not to mention that my office has no spheres in it, but much more complex objects instead.

One practical use...

[cjpez]

I think this robot could have many practical applications in the field of mapping out office buildings for inclusion in FPS games. Frag your coworkers!

Not good for the construction industry

[Squeebee]

Man, as if it's bad enough for builders that some architect can come around and harass you for being 1 inch off with a divider wall, now the architect will just send the robot down to measure out the entire building in 3d and point out any screwups!

Digitize the environment?

[burgburgburg]

Or 3D digitize our human features, then contact the base station so that they can begin fabricating replicas. Considering how many times even semi-autonomous robots have conspired to overthrow humans, you'd think that researchers would stop giving them the tools to try, try again.

I, for one, do NOT welcome our human form replicated robot overlords. Who's with me? John and Sarah Conner? That makes three. Who else?

Find the power plug

[RobertB-DC]

Great article (hope it doesn't get /.'d). While they seem to be working on large-scale room features (wall, door, floor, ceiling), I can see the next step being an autonomous robot that can find and identify such basics as a light switch and a power (mains) outlet.

I remember years and years ago, a robot had been developed that could optically recognize a power outlet and plug itself in... but I don't think it did much else. This would have been early 80s, probably, so we're talking Z-80 vs. Pentium.

Future recognition goals:

* Refrigerator door (fetch beer, please)
* Small child (danger! sticky fingers! run away!)
* Other robots for romantic interludes:
(IF Query(Other_Bot, EXCHANGE_CODE) == TRUE Extend_Programming_Probe(Other_Bot))

Kurt3D *sucks* in practice.

[mr_luc]

I tried to get Kurt3D to create a laser scan of the Hall of Mirrors in my glass house, and the resulting mesh was almost complete gibberish.

Also, I am now blind.

Re:Mobile?

[mr_luc]

Err.

Well, the stated purpose of this thing says nothing about it being used outdoors or to model large-scale terrain features. I mean, that's implicit in its design. This thing is designed to reproduce controlled environments.

And I don't know why you would think that is limiting! Maybe if you're thinking from the standpoint of a modeller/animator. Or maybe you just read the headline, and said 'omg it si small it cannot model WORLD omgomgomg'.

I see a couple of truly kickass uses for this thing. The first is adding texturing ability (you'd probably have to get dozens and dozens of scans, and have some good algorithms, to come up with good and relatively complete texturing, but I gotta' think that would be trivial compared to the sorts of problems they've already solved in making this thing -- and you wouldn't have to recreate the mesh each time, just sync up the coordinates with the one already created.

Ok, the use I see:

Crime scenes.

Bring in, hell, let's say 20 of these. Maybe some of them would be able to raise themselves up (heh, little accordioning platform for the recording mechanism, right out of the cartoons). They would roll around, sense out the room, figure out optimal placements, and then they would all scan the room, creating a near-perfect model of the room, perhaps mere hours of minutes after a crime has taken place. The cops would seal off the room, and the recorders would laboriusly record and texture everything about the room, down to the finest details.

Sure, it wouldn't catch a fingerprint or a peice of hair, and the plane/shape detection that is done actually removes some of the captured information (also removes some 'noise', but the forensic work they'd probably prefer a little noise to averaging out potentially important information) -- but the bottom line is, there wouldn't be a need for crime scene 'reconstruction', from photographs and little sketches and things that come after the fact. This would be absolutely accurate, more accurate than subjective information relayed secondhand from paid expert testimony. "How close would you say they were probably standing, from this photograph of bloodstains?"

So just in forensics alone, I see massive potential.

They're just using a SICK LMS on a tilt head

[Animats]

I was hoping that the Franhofer Institute had a new laser rangefinder, but they're just using the clunky but reliable SICK LMS unit on a tilt head. That's not a 3D scanner. It's a line scanner you can tilt, slowly. You can do quite a bit with something like that, but it's slow.

The Franhofer Institute has been doing some nice work with MEMS mirrors, and I was expecting something new from them.

There's a very nice true 3D solid state rangefinder out of Switzerland, but it's a continuous beam device and thus very limited in range. Works fine indoors, though.

Imaging laser rangefinder technology is lousy, because product volume is so low. Five companies have exited the field in the last decade. There are several mechanical scanners available, all using scanning technologies abandoned by television in the 1940s. All-electronic solutions have been developed as prototypes, but they're not shipping yet.

Once this problem is cracked, mobile robotics is going to get much better.