Separate names with a comma.
Discussion in 'Autonomous Vehicles' started by Bladerskb, Apr 19, 2017.
Looks like It's Cruise, Google and then everyone else. No one is even close right now.
Pretty impressive. Interesting to see it deal with double parked cars.
Down right amazing! FSD *will* be here soon. I wonder what sensor suite was being used? Probably includes LIDAR. Impressive achievement.
Fortune article shows its prototype with left and right LIDARs on top of the roof.
Impressive. Dealt well with cyclists with death wish, and gave way to the raccoon at ~24 mins in...
And yet there are still people on here insisting Tesla leads - despite Waymo going driverless a long time ago and despite the fact that Tesla's HW2 has had to use more cameras than MobilEye to get still-not-on-par with MobilEye's HW1.
Many people who have personal experience of advanced driver assist technology will tell that the only system you can buy off the lot today that outperforms AP2 is AP1, even though MobilEye's EyeQ3 HW is installed in many other marques, and even though AP1 doesn't hit all the goals announced when it was launched.
Why is Telsa's implemention of EyeQ3 better than the others, do you think?
That's something that will never come to market or anyone will want on their roof. Next.
It's a prototype. They care nothing about aesthetics. Even so, if the car drives me around safely I could care less about antlers on the roof. I suspect even looking as silly as the prototype, it'd still sell like mad.
Tesla leads in a sense that its final hardware design is done and sold to the public while others are still having all those sensors poking out. Some still have big, gigantic computers in the trunk.
Tesla leads in a sense that AP2 improves very quickly since its first release to first 1,000 owners in 12/31/2016.
It is true that other prototypes are much better current Tesla AP2. Waymo has been a leader in autonomous technology but like others, they are not released for public use.
It took AP1 one year to have its autosteer released so I expect AP2 will surpass it in 1 year.
Waymo's high definition maps are done by sending its own employees to do the work. Tesla leads in this kind of data collection job because it doesn't depend on a small numbers of employees to do the mapping but its entire owners' fleet since October 2014.
This is one of the biggest Tesla myth. There is no such thing as a level 5 hardware capability. Level 5 or 4 capability is software issue. All Tesla has is a bunch of sensors and cameras. That's not level 5 capability.
Teslas High Presicon map are done through GPS logging and are useless for FSD. How is it hard for you people to understand.
Tesla is light years behind. Why do you people hate facts?
This quote can't be any truer.
"One of the most amazing things about Tesla is how Tesla fans manage to hold thoughts which are so patently false, against all types of evidence."
Seems to me that there is, of course. Of our five senses, only sight (and perhaps hearing, to some extent) matter for driving (taste, touch and smell do not seem relevant). So you and I already have the hardware, with only two 'cameras' (of which we can move the focus), to do the trick. The rest, as you mention, is software which we humans have, i.e. our brains (which can very well be listening to a podcast or a nice piece of music while still driving safely).
Why would AI not catch up with our level of driving, with 8 cameras and 12 or so sensors?
Lol, who is this guy? "you people..."
You came to a fan site for the most ardent brand supporters and post a screed about overt enthusiasm?
Wow. A car that understands that bicycles are actually allowed to be on the road. That will never sell in California. They need it to throw 1/2 full drink cups at the riders and a speaker to yell obscenities for it to be marketable.
What an illogical comparison. Another Tesla trait. I wonder why scientists don't come out proclaiming that their current super computer is AGI capable...
If you take the brain out of human you don't call the human self driving capable when you are missing the brain nor do you call humanoid robots AGI capable. It's nonsense. Where do you see Boston dynamics calling their robots AGI capable?
Hardware and software are not mutually exclusive when it's 99% software and 1% hardware.
Anyone can throw together 8 cameras and call it the day. Infact 2015 Mercedes was the first production car to get self driving permits. That's because they have more sensors than even ap2
They don't say Waymo leads because the only lead they have is on prototypes. There are probably hundreds of self driving prototypes out there from various companies (even from more than a decade ago), but largely irrelevant if the timeline for public release is indefinite. The closest thing Waymo have to public release are the slow moving neighborhood vehicles (they are still controlled trials though), but those are much more limited in practical use (only work in certain geographic areas, very slow).
Tesla is the only one with a system in widespread consumer hands (although software only L2 at the moment). Maybe someone else will take the lead (for example GM's supercruise), but so far Tesla is still in the front.
Lol. You remind me of an article of if self-driving cars would be too nice for the passenger's taste or if they will be programmed to be as aggressive as a typical driver might be.
It might be infuriating to some if the car is too nice to cyclists or in terms of yielding to other drivers.
Tesla has no fsd system. This is what we are talking about. Hype being used as a basis for truth. It's truly mingboggling.
What's the price of the system used in the test Bolts?
That's the problem we have right now in trying to judge where the various companies are. Fully autonomous is worth hundreds of thousands per vehicle. Almost autonomous is advanced driver assistance and is worth insurance savings and however many thousands extra that people would be willing to pay.
GM has been driving semi-autonomous cars for over 5 years. V2V systems have been on some GM cars for a year now. The autonomous testing? We do know they were running Leaf's with autonomy in early 2016 and switched to Bolts 10 months ago. When it started was most likely 2010.
Currently, GM is run by a brilliant and experienced automotive engineer with vision. She certainly has worn a lot of hats. She's been an automotive electrical engineer, a plant manager, VP global manufacturing eng'g, VP of global HR, executive VP of global product development, VP of global purchasing, etc. The fact she also has a masters in business from Stanford and has been working in the auto industry since she was 18 certainly makes her a cut above most (all?) automotive CEOs today. The auto industry at that level is devoid of women, so she must have been a hell of a lot more qualified than the male prospects to get the office.
Mary is betting heavily on electrification and autonomy as being the wave of the future. There is no other ICE automotive company investing as heavily as GM is now in these fields.
It's probably a very risky move, because the bigger auto companies aren't spending anywhere near the money or time on it that Mary is.