Posted on 03/22/2018 9:31:12 AM PDT by Former Proud Canadian
No exerpt.
Video of accident at link.
(Excerpt) Read more at apnews.com ...
For some reason the link didn’t work for me, but the Fox News one did:
http://www.foxnews.com/us/2018/03/22/dashcam-video-deadly-self-driving-uber-crash-released.html
I wonder what qualifications they looked for in passive drivers.
Thumbs-up to that!
Believe it or not, I'm a person that can actually tell you how to do that, but that's not really the point. If their system is not robust enough to do this task with a visual recognition system, than they either should do it with RADAR or LIDAR, or keep their piece of crap off the road.
The bottom line is that they should have and must be required to have a system that can detect objects in the road. If they insist on using cameras, but don't have sufficiently developed software to do it with cameras correctly, then they should not be allowed to put that contraption on public roads.
If they have RADAR and/or LIDAR, then a failure to detect an incoming signal should have caused the thing to come to a stop as a fail safe.
You have to approach the problem without the built-in knowledge we all have of objects. A computer system processing a light sensor array only sees various colors at each of the sensor locations. There is no inherent image. The actual objects need to be differentiated from artifacts like shadows, glare.
I know quite a lot about this topic, and have built my own hardware and software to do this sort of task. I know how image data looks to a computer, and I know what must be done to it to extract meaningful information from this sort of image data.
Systems need to not only differentiate actual objects from artifacts, they need to discount objects that it should not stop for. You don't want the car stopping because some leaves fall in front of the car, or a trash bag blows across its path.
What sort of RADAR echo or LIDAR echo would a leaf have? Again, if your video system won't handle the task, you should not be attempting to use your faulty video system to accomplish a task that must absolutely be accomplished.
The video's frame rate was 30 frames per second (33.3 milliseconds per frame).
From the time the woman's white sneakers were first barely detectable, (illuminated by the car's headlights) to the impact, there are 35 frames.
That's only 1.166 seconds. Even with vision equal to that of the camera, I seriously doubt that a human would have perceived a threat until much of the woman's legs were illuminated -- giving only a fraction of a second to respond.
The real kicker is that the car was in a well-iluminated area, and the woman was well outside that area. That would have compounded the difficulty of making the dark-to-light visual adjustment in time to perceive danger and to react effectively.
Here's a thorough article on the components of reaction time -- showing that the "standard" 1.5 second reaction time is, often, insufficient...
I recommend that you read it...
~~~~~~~~~~~~
In this instance, I suspect that I would not have outperformed the computer. YMMV...
An important design objective, or incidental feature? Of course the stupid thing should have spotted the woman.
Want to bet that they are using the Arduino development environment, the primary breeder of nasty software habits?
The human body is going to absorb those types of signals. The bike may have returned some signals, but maybe not enough to identify what was going on. I am guessing there was some sort of Infrared sensor on board the vehicle, but if the temperature of the roadbed was at 98.6 it wouldn't detect the human either..
For once, huh -{)
Kindly explain, then, how the military's anti-personnel radar works. I can assure you that it does all the way back into the 1960s.
An eternity to computers these days.
Not exactly a direct reply, but energy storage devices becoming available allow production of a relatively powerful garage-build EMP in the context of short to moderate range disruption of electronics.
Teledyn e2V markets such a device to disable engines without disabling brakes or steering. They claim a maximum 800 meter range. Someone will eventually build a less discriminant knock-off that can take out automated control systems.
After California testing issues in 2016, Uber sought other venues for live testing. Perhaps some green found it’s way into election coffers to grease approvals in other states.
" Our measurements establish the mm-wave system's ability to range humans up to 213 meters and distinguish between different human movements at 90 meters.
I'm thinking a human would not only have had their brights on, they would have also been watching the road. They might not have stopped in time, but at least they would have hit the brakes.
I've never heard of such a thing. Radar reflects off objects such as steel. If they are bouncing signals off off humans and getting a return, they are doing at a frequency I am not familiar with and neither are the Uber engineers.
Agreed...
But not to the FReeper who said he could have stopped/evaded in that time...
(FWIW, a big chunk of my career was in creating high speed semiconductors for computers...)
~~~~~~~~~~~~~
Total aside: to me, that "woman driver" looked much more like a fat, balding, dark-haired man -- with a scruffy, blondish, fake-looking wig perched on the back of his head... '-)
It’s perhaps an issue of the complexity of the operating environment and a lack of capability to formulate a working model through an electronics processing system.
Humans are not merely using just-in-time high level cognitive abilities to process a driving task. The senses-subconscious brain processes-spinal reflexes-instinctive behavior patterns-and intuition all play a part; such, that humans can often perform a familiar but skilled task, without continuous high level mental concentration.
That is so very true, especially with something like driving. I drive best when I'm well rested, but relaxed, and in away operating the vehicle without thinking about operating the vehicle. Sort of zen-driving. If one actually starts focussing on the pedals, shift lever, etc driving ability goes down. If you're in the zone, it's like you're part of the machine or the machine becomes part of you.
Metal bike frame and rims give a radar return. Stealth fabric which wouldn’t reflect laser light would still leave an anomalous blank area in a lidar’s sensing system, which should set a conditional alert flag in the system’s processing.
Birds and raindrops give a radar return.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.