No post body was provided.
Cruise is opening driverless cars to the public in San Francisco
421–430 of 652 posts
Re: Cruise is opening driverless cars to the public in San Francisco
#422Earlier quoted context omitted.
Vision-based driving. Humans don't have lidar sensors.
Humans don’t regress per-pixel depth or use convolutions and region proposals to draw bounding boxes around objects. They don’t function on models with fixed weights trained by backprop either. The idea that “vision only” somehow more closely resembles how humans drive quickly falls apart if you inspect the internals of these systems.
The similarity is in the problem to be solved, not the details of the compute pipeline. Depth must be inferred somehow, rather than measured by actively interacting with the surface, as it is in LiDAR.
Re: Cruise is opening driverless cars to the public in San Francisco
#423Earlier quoted context omitted.
The software could require a trip to the dealer for a visual inspection of the tires at set intervals. Hopefully free of charge for something so simple. A quick hookup to the computer and the interval is reset.
Tesla vehicles can detect and notify the driver of tires with low tread remaining. It's detected by a delta in rotation speed between other tires and the tire needing replacement. Seems like a software implementation is straightforward. https://driveteslacanada.ca/software-updates/your-tesla-can-...
That doesn't help with end of service life, it helps with uneven wear.
If all the tires wear evenly this detection won't help.
Re: Cruise is opening driverless cars to the public in San Francisco
#424Earlier quoted context omitted.
Tesla vehicles can detect and notify the driver of tires with low tread remaining. It's detected by a delta in rotation speed between other tires and the tire needing replacement. Seems like a software implementation is straightforward. https://driveteslacanada.ca/software-updates/your-tesla-can-...
That doesn't help with end of service life, it helps with uneven wear. If all the tires wear evenly this detection won't help.
Was editing my comment while you were commenting (removed service life, as software won’t detect dry rot or other defects undetectable from wheel speed measurements). Assuming tires wear evenly, you could still detect the change in rotation speed over time due to tread wear.
Re: Cruise is opening driverless cars to the public in San Francisco
#425I'm not interested in cars I can't own. This idea that we'll turn cars into some kind of service and convert roads into places filled with company-owned vehicles is completely foreign. At that point it'd be cheaper to have self-driving buses and subways. I can only think this viewpoint comes from people who have only ever lived in cities where car ownership is inconvenient given the lack of personal garages. At the m…
In suburban US, automated taxis are way more accurate and for folks like my parents who don't drive. Taking an uber to supermarket and back? Easy. Taking a bus? Much more difficult (primarily because we don't have a good bus or tram culture here). Same with e.g. visiting friends/family.
Limited capability folks benefit a lot from easy to access taxi service. It won't replace folks who want to own a car or need to (e.g. commuting when public transit isn't good enough).
Re: Cruise is opening driverless cars to the public in San Francisco
#426Earlier quoted context omitted.
Cruise CEO here. Our strategy has been to solve the challenges needed to operate driverless robotaxis on a well-equipped vehicle, then aggressively drive the cost down. Many OEMs are doing this in reverse order. They're trying to squeeze orders of magnitude of performance gains out of really low-cost hardware. Today it's unclear what strategy will win. In a few years our next generation of low-cost compute and sensin…
I'm no where near as experienced as you and your team, but that is what I was thinking as I read this. Tesla rather quickly went from the expensive sensors to the camera based setup they have now and it'll be interesting to watch how all this unfolds, safely from my 2006 vehicle with nearly no computers.
There's absolutely nothing stopping Tesla from adding back lidar/other sensors if the technology becomes cheaper or it turns out visual-only isn't accurate enough; Elon has other advantages that no other company is anywhere near competing with though too, and he clearly understands this, he understands his position well - and it's strong. He's also a very agile entrepreneur/engineer and not afraid to pull the trigger on whatever ideas come to his attention as being the best decision. He's also already succeeded in Tesla's mission - which was to get other vehicle manufacturers to transition to EV, so anything else after that is really just icing on the cake; Tesla stock holders however still believe strongly in him - and I'd argue rightfully so.
For now by using the cheapest technology he's arguably selling more EVs and/or making more profit per vehicle. If the market's competition requires a course change, then I don't see why he wouldn't take it - I don't think he'd fall pray to sunk cost fallacy; the reason for decisions may not be obvious to the public either, as we likely don't know details of his nuanced master plan.
Re: Cruise is opening driverless cars to the public in San Francisco
#427Earlier quoted context omitted.
Agreed - I think the "but can it drive in a whiteout blizzard" question is best redirected to: "can a human?" I suspect there are operating conditions the AVs won't solve acceptably - some of those conditions IMO are also conditions where we should not accept a human to solve acceptably. In general I feel we have a lackadaisical culture around driving that encourages/excuses unsafe behavior, and is overoptimistic abo…
I grew up in a part of Ontario where total whiteouts can happen fairly frequently on both major highways leading in and out of my small town. It is in fact possible to drive dozens of km in near or total whiteout conditions simply by the hazard lights of the car ahead of you. You very frequently will see lines of cars km long, all going I don't think vision-based FSV will ever reliably handle winter conditions like t…
Humans certainly don't reliably handle these conditions. ;)
It does seem like "something else" is needed for these kinds of low-visibility scenarios -- frankly, when nobody should be on the road.
Re: Cruise is opening driverless cars to the public in San Francisco
#428Earlier quoted context omitted.
Cars are large, depreciating assets that spend the vast majority of their product lifecycle doing nothing. Conversely, metropolitan areas have to dedicate up to half their available space to empty blacktop storing these unused assets that sit around doing nothing. The sooner we solve on-demand transportation at scale without requiring a human driver the sooner we can move away from this colossal degree of waste.
By this logic you should promote trailer parks.
Trailer parks are peanuts against really dense buildings like apartments/condos with dedicated park/fitness facilities. Stuff I saw in HK is amazing.
Re: Cruise is opening driverless cars to the public in San Francisco
#429Earlier quoted context omitted.
Cruise CEO here. Our strategy has been to solve the challenges needed to operate driverless robotaxis on a well-equipped vehicle, then aggressively drive the cost down. Many OEMs are doing this in reverse order. They're trying to squeeze orders of magnitude of performance gains out of really low-cost hardware. Today it's unclear what strategy will win. In a few years our next generation of low-cost compute and sensin…
It's good to hear a CEO say "we don't know the answer, but we're making a bet" rather than the typical Elizabeth Holmes style "We are absolutely correct and first they ignore you, then they laugh at you, then they fight you, then you get convicted of three counts of wire fraud and go to prison".
Good one!
Re: Cruise is opening driverless cars to the public in San Francisco
#430Earlier quoted context omitted.
Vision-based driving. Humans don't have lidar sensors.
Humans aren't just a stereoscopic camera - we can sense depth by knowing what things should look like, or by moving our head, or refocusing, or… Did you know we can see light polarization? https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4528539/
You’re describing vision, and not LiDAR. We are in agreement.