All, There are a few threads discussing when AP 2.0 might hit, whether to wait on it, etc. Question: What is AP 2.0? Has Tesla said something that gives us some inkling of what is coming next? I feel like I remember Elon saying that autonomous driving is three years or so away (meaning in non-Tesla time it's probably a bit more). Is there something we are expecting to see in the meantime? Thanks. Tim
There are obvious capabilities within the current MobilEye hardware-powered system that Tesla could choose to implement. After having the chance to look at some variables present in the CAN-bus my guesses are (remeber this is speculation): - Pedestrian detection - Virtual lanes (I'm not sure what this feature is exactly but I've seen references to it) - Detection of construction areas - Red light and stop sign detection - Road type/class and road surface analysis - Junction mode (seen references to "Junction" allover the code) suggesting a tie-in with navigation/destination plotting, since the system would have to know a destination to be able to navigate a junction per the wishes of the driver) - Further improvements to the "moderate speed ahead of curve" function people are reporting is there (likely more rudimentary now than it will be) The biggest thing, IMO, would be integration of NAV/destination plotting with the AP.
I would guess AP2.0 hardware = SA1.0 hardware, and the software will catch up. SA = semi autonomous, level 3
I think "AP 2.0" refers to the sensor suite wired into the car. Software to fully utilize it comes over time. I assume the suite jumps from one camera to several, the jump being driven by the performance difference between the current Mobileye EyeQ3 processor and their next generation EyeQ4 processor, which can handle about eight cameras instead of one.
OP, as you can tell from the various responses, "AP 2.0" is just a term someone created and some enthusiasts are using to define some future state of AutoPilot hardware and/or software. There isn't any formal (at least agreed-to) definition, announcement or public specification, but there is plenty of speculation as you have found.
Tesla has never used the term "AP 2.0" as far as I know. It was made up here on TMC and is being used to denote a future enhancement of the sensor suite Tesla uses for autonomous driving. Obviously at some unknown point in the future Tesla will incorporate more and better sensors in the car. More cameras,more radar, maybe more ultrasonics, who knows what else. Until that time comes, speculation is rampant.
Tesla has new AP hardware developed. Internally it is referred to as the "next generation" platform. This is what is called AP 2.0 here. Some speculate that the Model X will have it at actual customer shipment. I believe this to be true.
The hardware in current MS is branded as Auto Pilot. According to MobilEye it is technically accurate to call it "best in class lane keeping assist" New hardware powered by multiple EyeQ3 chips (EyeQ4 will not be production ready until 2018) and additional cameras would allow the enabling, through software, a more semi-autonomous driving experience. Here's some snips from MobilEye's Q3 investor briefing that will also help (at least how I think about it): Mobile Eye’s Q3 Conference Call (11/3/2015). "So, currently, we are very happy with the introduction of Tesla with what we call Lane Keeping Assist, which is the best in class Lane Keeping Assist today. And we hear a lot of great feedbacks on this system. “ “What we presented is Lane Keeping Assist system rather than auto pilot system. Auto pilot system is going to be presented next year, where is going to be 360 degrees coverage around the vehicle and is going to be multiple cameras with additional sensors. What we have today is just a mono camera looking forward. So it’s a very limited input that we have on the road. But importance of this launch is, Tesla is willing to push the envelope faster and more aggressively than any other OEM, and definitely this is a very important in step forward to introduce the beginning of semi-autonomous application that will start being launched next year."
Very interesting. I don't follow Mobileye each quarter, but the EyeQ4 timing sounds like a slip compared with a presentation they made about a year ago.
Does anyone know if the current Tesla Model S hardware is sufficient to perform self parking in a perpendicular space (i.e., in a space in a regular parking lot) vs. parallel parking? I was surprised and a bit envious when I learned that my daughter's new Mercedes Benz E-class wagon can self-park in either curb spaces or in a parking lot, and it was not an extra-cost option for her (in the UK, not the US). So it would be "nice" if Tesla could do that in a future software enhancement, if the hardware is capable. My suspicion is that the rearward detection and visibility are not sufficient. Just a guess, though....
Based on the below URL "series production" to me equals "production ready" which may not be accurate. Moving Closer to Automated Driving, Mobileye Unveils EyeQ4® System-on-Chip with its First Design... -- JERUSALEM, March 4, 2015 /PRNewswire/ -- Availability Engineering samples of EyeQ4® are expected to be available by the fourth quarter of 2015. First test hardware with the full suite of applications including active safety suite of customer functions, environmental modeling (for each of the 8 cameras), path planning for hands-free driving and fusion with sensors, is expected to be available in the second quarter of 2016. Series production is supported for early 2018 start of production.
This is in-line with what the current hardware can do (based on the MobileEye specifications). Pedestrian detection, construction area detection, traffic signs, stop signs, etc. are all capable with the current hardware.
Based on the originally touted "self park in your garage" and "self pull up to your house" features, I would imagine the hardware is capable, within a certain degree of confidence. Parking in a garage is basically perpendicular parking any way you slice it. This is just speculation on my part.
