Slashdot Mirror

Retinal damage is not the only ocular risk.

https://velodynelidar.com/newsroom/guide-to-lidar-wavelengths/

1550 nm systems use a wavelength that is allowed to run more power compared to 905 nm. However, under certain conditions, the 1550 nm wavelength of light can still cause corneal damage and potential damage to the eye lens.

LIDAR is the way to go and both Google and Apple know this.

The problem is, puck-sized LIDAR systems, as seen in 8-packs on the Apple dev car, cost 8000 a piece and that is why Testa uses cheapo-cams and parking radar.

Not necessarily. Lidar can use multiple beams and multiple wavelengths to work around this.
http://velodynelidar.com/faq.h...
"Velodyne's LiDAR sensors work well in snow, sleet, and rain. The multiple beam approach of Velodyne's LiDAR sensors with laser beams with millions of laser beams at different angles enables to find "holes" in-between the snowflakes to "see" the environment. An inferior LiDAR with only one or a few laser beams would not work as well as one with 16, 32 or 64 laser beams."

If you look on the top of this vehicle, you will find a velodyne lidar, that sweeps the field of view at 15Hz with 64 beams. Here is there website: http://velodynelidar.com/lidar... .. From my understanding, there are 64 laser diodes mounted as a stripe, and 64 corresponding avalanche photodiodes , each group of 8 detectors is being fed to an 8-bit 3 gigasample per second ADC.

These units sell for $80K, and is one of the factors effecting wider adoption. I understand that there is a lot of demand among the auto and trucking industries if these can be made cheaper. This technology will become much cheaper as the cost of the ADC's drop. Right now, a 3GSPS adc costs about $600. A few years ago, this is what a 1GSPS part cost... process node shrinkage will make this kind of technology affordable, and open up a lot of other interesting ideas.

It's one thing to scan something that stationary, it's quite another thing to continuously keep track of a 360 degree field of view around the scanner. The self driving car from Google, I think, uses a custom detector from Velodyne that spins at 5-15Hz: http://velodynelidar.com/lidar/lidar.aspx

I know of at least one start-up company called Quanergy that plans on competing in this space to give cars/drivers better real-time situational awareness. Hopefully they'll be able to develop something that is cheap / good enough to be part of a futuristic car. Perhaps this will help in car accident reduction, and a saving of lives: http://www.youtube.com/watch?v=qwcSmo3dzVM

The Ford vehicle has four Velodyne HDL-32 LIDAR units. This is the generation after the one Google uses. They're smaller, but the field of view is wider vertically and the resolution is lower.

They spin and get full-circle images, so for research purposes they're usually mounted on top of the vehicle. But that has to change for production vehicles. A production system wiill need more sensors better integrated into the auto body.

Having worked on self-driving cars (2005 Grand Challenge), a few points:

The comment about minimizing "near-collision states" is significant. A near-collision state is one where a reasonable variance of the behavior of another vehicle could cause a collision. It's about predicting other-vehicle behavior. That's an important area to study. Aviation people put a lot of effort into minimizing near-misses, and it pays off.

Incidentally, Tesla's announcement that they're starting work on an "autopilot" is them playing catch-up. Audi, BMW, Cadillac, and Ford are already demoing automatic driving systems. It looks like Cadillac will be the first to ship hands-off highway driving, in 2015. All these early systems are highway driving only, although Cadillac includes stop-and-go driving in traffic jams. That's likely to be a very popular feature.

On the sensor side, more progress is needed, and it's coming. That rotating LIDAR contraption on top of Google's self-driving cars is from Velodyne. It's 64 LIDAR units on a spinning turntable. That's a research device, not a production one. There are better ways to do LIDAR, but the cost needs to come down. The approaches used in the Kinect and the XBox One will not work outdoors in bright sunlight. Outdoor LIDAR systems work fine, but they're pulsed, not continuous. For a nanosecond, at one frequency (color) they far outshine the sun. But the total energy per pulse is low, so they're eye-safe. Currently, such devices are very expensive, but that's not for any good reason. It's because some exotic ICs have to be made in tiny quantities.

Radars are getting better, too. A decade ago, in the Grand Challenge, we had to use Eaton VORAD radars, which operate at 24GHz. These could reliably range cars, trucks, and larger bicycles, but not people at long range, or signposts. (Such radars return range, azimuth, and range rate; this isn't a speed gun. I used to have one of these looking out my window at at an intersection, with a display plotting the traffic.) Today's automotive radars are running at 77GHz, with plans to move to 79GHz. There's an effort to standardize on 79GHz internationally. Tripling the frequency, plus applying more compute power to the processing, means that most objects a car might hit are detectable. These radars are getting cheap and small, so a car will have enough of them to provide full-circle data. Long range is needed mostly in front; on the side and in back, much lower power can be used.

A key issue is a high viewpoint. This isn't just about obstacle detection. You also need to profile the road. This was a big deal for the off-road DARPA Grand Challenge, but even on paved roads you need to be able to detect junk on the pavement and potholes. Google has their sensor on top of the roof. This will probably be unacceptable in a production car. I'd go for flash LIDARs at the top corners of the front windows. One possibility is a narrow strip just above the windshield, to contain all the sensors. This is one way to combine vehicle aesthetics and field of view.

Cameras are useful, but computer vision is still kind of dumb. Distance from stereo only works at short ranges, and range rate info from cameras is poor. Digital cameras are so cheap now, so it's tempting to think they can do the whole job. Not yet. Computer vision isn't good enough. Tesla is probably putting too much hope into camera processing. You need cameras to recognize signs, traffic lights, and such. Also, you need multiple sensors because not all objects are visible on all sensors. Radars can't see insulators. Cameras can't see objects with little contrast against the background. LIDARs can't see some materials, such as the charcoal fabric used on many office chairs. Sensor fusion is essential.

Enough for now. This looks quite do-able.

"The problem with Google's current approach is that the sensor system is too expensive" - Musk

He's referring to the expensive Velodyne rotating array of 64 LIDARs found on top of Google's cars. It's a useful device, but it's a research tool, not something that belongs on top of production vehicles.

Its called economies of scale. I'm sure the price/size/efficiency would drop when 100 million+ of them are ordered.

"The problem with Google's current approach is that the sensor system is too expensive" - Musk

He's referring to the expensive Velodyne rotating array of 64 LIDARs found on top of Google's cars. It's a useful device, but it's a research tool, not something that belongs on top of production vehicles.

What's needed is a compact solid-state 3D LIDAR for outdoor use. Advanced Scientific Concepts makes such things, but they're sold to DoD for about $100K each. Typical performance is 300 meter range, 128x128 pixels, 30 FPS. There's no fundamental reason the technology needs to be that expensive; it's just that the things are hand-made at a lab in Santa Barbara, CA. (I visited them a decade ago when we were doing a DARPA Grand Challenge vehicle. Back then, they had the technology working on an optical bench, but didn't have usable hardware yet.) This technology needs to be turned into a mass market product. The current generation Kinect, (which is a true LIDAR, not a trianguation sensor like the previous model) does roughly the same thing, but with a less sensitive sensor and a weaker laser. Eventually somebody will put enough money behind this to get it right.