So Tesla doesn't do racing. Disappointing. It's a shame that they won't be represented at the Nikola Tesla EV Rally.
-
Want to remove ads? Register an account and login to see fewer ads, and become a Supporting Member to remove almost all ads.
A member asked him about the Coast to coast jacket. Apparently it was so nice that he was so miffed about not being able to get one online or in stores that he waited in line for a long time to ask Elon about it. As much as I want to support this guy but I don't think that would be the most pressing question I would ask Elon at this once a year event. I, actually, wanted to ask him about the possibility of (or lack of) dealership model to distribute more Model (E or Y or whatever) to appease the mass market, especially since the Model S has a wait time before delivery. I can imagine the Model X would have a delay too. I can only imagine how much delay the 3rd Generation car will have without a more widespread production and distribution strategy. But I didn't get picked on to ask a question. Oh well, maybe next year.
Yes, but the environment that a rocket works in is FAR less complex that a car on the freeway. Radar isn't high enough resolution to understand what is actually happening. You need vision for that. And computer vision understanding is still an unsolved AI problem.
Question, how is a car going to understand when a cop starts zip zagging across the freeway to do a full freeway hot stop?
When traffic cones are placed on the road to get everyone moved off a lane, how will the car see and understand the cones?
When an accident occurs and flares are set around a crash that just occurred, how will the car understand the scene and react accordingly?
When you are driving through a snow storm or a very heavy rain, how will the car deal with the crappy vision?
It isn't the boring, follow the guy in front you driving that is hard, it is all the exceptions.
I suspect the intent is to not to address the exceptions, but just to address the simple case. The human will be required to stay alert and take over when an exception occurs just like human override on cruise control.
He didn't say "in all circumstances". It'll be the boring, follow-the-guy-in-front that comes first, along with warnings when an exception occurs and then gradually adding exception handlers.
Another factor for the X 'delay'. Why rush, orders for it are still pilling in. They are battery constrained and had already sold out their entire production for Q2 per Elon during his ER guidance call...So, they have yet to test the limit of demand for the S that they are making 25%+ gross profit on. I would like to have an X tomorrow...but from TM's perspective, they can't make cars fast enough for demand and certainly have no chance of catching up with demand until the second half of the year...at best, so their attitude 'what's the rush?'
Computer vision and AI are two separate parts of this. With respect to the vision itself (physical sensor hardware and low level interpretation of the inputs) it's not unsolved, simply unsolved thus far at a low enough cost - see Google's LIDAR solution. The AI side of it is definitely a bigger challenge.
But what you're saying is exactly with what Elon has said previously, that the first 90% is relatively easy, then dealing with exceptions to get to 99% is exponentially harder, 99.9% exponentially harder than that, etc. That's precisely why they are making it analogous to aircraft auto-pilot (where a human is still required regardless) rather than full autonomy. Weather conditions is the biggest single challenge for current sensor technology, followed by higher level software reliably understanding unusual road conditions like you mentioned.
But, it's quite feasible in the next two years Tesla can implement an autopilot for freeways that works like an advanced cruise control you can use in ideal conditions, so long as they can sort out who's responsible when the inevitable guy falls asleep on the hour long freeway autopilot trip and doesn't wake up to take back control when required.
- - - Updated - - -
Nah it'll be trickier than that to get it reliable. For example, imagine you are the first car to come across some traffic anomaly... it wouldn't be reported yet so the AI would have to determine it on its own - a significant challenge given the scope of what may go wrong in road conditions.
I think they are pretty much planning on the mass market car to hit that 90% self driving mark right from the initial start of production or maybe even 99% so it wouldn't be that surprising if they could get to highway driving a year from now, the google program is easily in that 90-100% range right now. The end of 2016 isn't that far away for the mass market car anyway so if they plan to hit that mark it seems like they'll need to be pretty far along in development by mid 2015.
Trev Page
Member
That's pretty much what I think he was alluding to. Tesla however is pretty far ahead of the competition so doing so now wouldn't really affect them on the low end of the scale due to battery costs. Anyone else taking the patents to make their own car would be still take 2-3 years or more to develop and Tesla still has a leg up. Might be some merit in him doing that.
That's true and I can see that happening, but what's the percentage that it will be the first car at the scene of a wreck as an advanced car with this type of tech? Not very high until all cars are like this. And when are cones are the road? only during accidents or construction, so why not just code the car to understand that if it sees a cone object in the distance up ahead, to go ahead and move over to another lane when it can.
Yes I agree. Elon has been careful in the past to talk about an "auto pilot" function that requires a human in the drivers seat still paying attention to the surroundings as opposed to a system that can drive the car autonomously and the human in the drivers seat can do whatever they want.
And as another poster has pointed out up thread Elon is fully aware of the extreme difficulty in an automated system handling all the potential "corner cases" that might occur while driving. Of course humans aren't very good at dealing with those either.
My concern is that a "freeway autopilot" capability will almost certainly result in some drivers thinking that they don't have to watch the road as carefully and they will be tempted to do other things even more than they do now: answer text or email on their phone (despite that not being legally allowed), put on makeup, and who knows what else!
Not very high, but if it misinterprets and handles it wrong, you end up as a second accident there. Actually I imagine traffic cones are a relatively straightforward case related to obstacle avoidance... quite obvious and detectable as compared to, say, a 3-pronged trailer hitch
I read a piece in the MIT online blog saying this was the exact concern that Google has - their initial plan was a 'freeway pilot' but they quickly found that the 'driver' was so inattentive that the option of bailing out and handing back control was not really viable - hence the shift to the completely automatic, no steering wheel car they recently showed.
That is a much harder problem, but avoids the simpler case with the catastrophic end-game!
But you can't do that. The highway flares is something that can pop up anytime. If you are reading your book at the time, you won't see the flares. The car won't either unless it has true visual scene understanding.
T-bone that thing with a big truck..or a Tesla ..ouch
catastrophic might be a weak word for it
lazy humans shaped Google's new autonomous car:
http://www.technologyreview.com/news/527756/lazy-humans-shaped-googles-new-autonomous-car/
http://www.technologyreview.com/news/527756/lazy-humans-shaped-googles-new-autonomous-car/
Similar threads
- Locked
