Slashdot Mirror

Do you really believe that future cars will have a kinect sitting in the grill for accident avoidance?

Actually they're using sensors from Velodyne, which are doing to LIDARs what the Kinect is doing to 3D sensors. It used to be that you needed an array of 2D LIDARS to create a 3D image. These could cost upwards of $100,000, where prone to failure, time consuming to create, and one of a kind. Then came Velodyne with their $70,000 3D LIDAR now being used on any serious autonomous vehicle. Of all the cars that finished the DARPA urban challenge, only one didn't use a Velodyne. Even Google's autonomous car has one. Now Velodyne released a new model for $20,000 the size of a coffee mug.

Yes in 2005 we could create a 3D image using lidars. That was 5 years ago, and at the time we couldn't get a car to drive through the desert. Now, because of Velodyne and the ubiquity of their sensors, cars are driving themselves through crowded streets.

Was the Velodyne revolutionary? Absolutely. Was it brand new? No, we had 3D sensors on our cars before. But it was smaller, cheaper, and easier to integrate, which is exactly what the kinect is.

this is bad advertisement. And timothy ought not have posted it.

Right. It's 3D from stereoscopy, not a depth camera. The baseline between imagers is small, so it won't have much depth resolution for distant objects. Note that while the video shows outdoor scenes, it doesn't show depth information for them.

Now the Advanced Scientific Concepts flash LIDAR is a real time of flight depth camera, a 128 x 128 pixel LIDAR. With a real time of flight device, depth resolution stays constant with distance, as with radar. This device tends to be equipped for a narrow field of view and long range, because it's sold to the military. But that's not inherent in the technology. A similar device, but with mechanical scanning, is the Velodyne laser scanner, which almost everybody in the 2006 Grand Challenge used.

I've met the people behind both systems. The ASC device is potentially mass-produceable at moderate cost, but the company is focused on DoD applications and hasn't pursued that. It requires custom IC fabrication, which is cheap when you make millions and extremely expensive when you make hundreds. The Velodyne thing is a better version of the impressive but fragile Team Dad laser scanner from the 2005 Grand Challenge. It's a spinning array of little LIDAR units. Both cost around $100,000, due to the tiny market.

http://www.nytimes.com/imagepages/2010/10/10/us/10google3.html

1) http://www.applanix.com/products.html
2) http://www.velodyne.com/lidar/lidar.aspx
4) http://www.topconpositioning.com/
7) http://www.netgear.com/

There's been much more progress in the last five years than most people realize, though. SLAM works now. Vision algorithms actually work. Low-cost inertial devices work. We're starting to see the payoff from the DARPA Grand Challenge, which gave robotics a serious and needed butt-kick.

In my humble opinion, the Darpa Grand Challenge, by offering a market to LIDAR makers, made vision-based SLAM a thing of the past and the under-budgeted : This beast has 64 laser telemeters on a rotating head. It gives a 100 000 3D points cloud of the environment 10 times per second. A working video slam seems to pale in comparison...

What you do, is build stuff and fuck the rest of them.

It's that simple.

In the GP's example of the DARPA grand challenge, I'm not sure it's quite that simple.

I mean, if you're competing in the DARPA urban challenge, you need several things.

A system combining a high precision GPS with high precision inertial measurement and an Omnistar subscription. Budget: $80,000
A Velodyne HD LIDAR - Budget $75,000
Five count SICK LMS-291 LIDARs - budget 5*$7000 = $35,000
38 motivated, intelligent engineers, programmers and administrators for 1 year. 38*$50,000 = $1,900,000

I'm sure in the computer programming world you can program the next big thing on your home computer with free tools. However, that does not generalise to everything. To develop some cutting edge technologies you also need money and competent people.

No, no open source code. But what the public does get out of this is advances in technology. Case in point: the *real* winners of this year's Urban Challenge are Velodyne. Their lidar sensor was invented by team DAD for the 2005 challenge. For the 2007 challenge, they decided that instead of losing the competition again, they would sell their lidar technology to the other teams. Over half of the 35 teams in the challenge bought one, and 5 of the 6 finishers (Virginia Tech being the exception).

This thing is a huge advance over previous technology for this application, and it directly owes its existence to this challenge. Thanks to DARPA, you can now buy a lidar that you can stick on top of a car and which gives you 360 degree range data in 3D at 10 Hz over Ethernet. Now that the company is jump-started, next year those specs will improve, costs will go down, and eventually something like this will be driving your car for you. That's the benefit everyone gets from this competition. Not to mention all the people whose imaginations have been captured by the competition; who have been working on the funding DARPA gave out, getting their PhDs, or even just working in their spare time, learning how to write the software to run these things. There's no doubt in my mind that DARPA has gotten far more mileage from their money in this contest than they would have dumping it in the accounts of some defense contractor.

So even though no open source was produced from the contest, the public will see a lot of benefit from the money DARPA has spent.

Reciever:

• Denon AVR-2800. Very good, clean sound. It does both DTS and DD decoding, and I can bi-wire my main speakers. ($1300)

• Panasonic A-120. It's a little older than most (1 1/2 years old...it's not even on the web site anymore), but it does the job nicely. It passes a DTS bitstream, which is all I was really looking for at the time.($500)

• Toshiba TW40X81 A good T.V. is something that you definately shouldn't scrimp on. I agonized for 8 months over this purchase, but it's the best thing I've ever bought Widescreen baby, YEAH! ($3600)

• All my speakers are by
• Sound Dynamics. RTS-11's for mains ($1000), RTS-7's for rears ($600), and an RTS-C2 for a center ($300). They kick ass, and compare favourably to similar sounding speakers in the price area too.

• A Sub is
• essential to quality movie-watching. It's not only about base you hear, it's about the rumbling you can feel. Mine is a Velodyne CT-100 with a 10" driver. ($750)

Looking back, I guess I spent quite a bit of money, but I don't regret a cent of it. I routinely enjoy watching DVD's at home more than going to the theater. I guess that's what it's all about, eh? :)