61–70 of 90 posts
Earlier quoted context omitted.
That visual sensors only seem like they make no sense when they can get obstructed by weather
I don't get this perspective. Somehow humans drive with visual input
Earlier quoted context omitted.
That visual sensors only seem like they make no sense when they can get obstructed by weather
I don't get this perspective. Somehow humans drive with visual input
The advantage of machines is not that they have better brains than humans, but that they have better senses than humans, which is an advantage that goes out the window when you obstinately refuse to use better sensors than merely cameras "because that's what humans use".
Earlier quoted context omitted.
That analysis only works when p is non-vanishing, though. In point of fact the "car drives into something it didn't see" failure mode doesn't really exist, or if it does it's at a level much smaller than that of the human driver its intended to replace.
It works regardless of how big p is. Engine failures in aircraft are exceedingly rare but this statistical effect of needing p^2 events instead of p events has saved many lives. Having multiple pilots has the same rationale. While errors are correlated, getting an error past two pilots is roughly p - p^2 less likely than if you had a solo pilot. Self-driving, as a mission critical endeavor, needs to be leveraging the…
Uh... why? Shouldn't the goal be to be safer than people?
Basically that's just bad engineering: If your argument is not to deploy an existing system that is better than the current installed base because some other technique might be better still, you are harming your metric (safety) and not helping.
Earlier quoted context omitted.
No twist of fate, but self-sabotage in the form of being unwilling to use Lidar. Look how hard Waymo and Cruise are finding it to do robotaxis in a small geographical area and with Lidar. Tesla is trying to do robotaxis everywhere without using Lidar. They're solving a harder problem and are handicapping themselves while trying to do it. Here's why Lidar makes sense. You want independent information streams that are…
Counterpoint - Tesla is trying to avoid a local maximum where they are able to do robotaxi's in cars with $300,000 of equipment on roads that are precisely mapped down to the centimeter. Waymo and Cruise may have beat them to "first robotaxi" but I'm not convinced that they have anywhere near a scalable, sustainable model.
Unless there is a change in how autonomous driving software is trained, it seems Tesla is destined to dominate that market, right? Tesla has the most training data consisting of video input + corresponding driver behavior. And they have the most compute power. Which twist of fate could happen, so that Tesla falls behind in the future? I could imagine that there is an invention which lets AI learn about the world by j…
Data is just cars driving around. Mercedes Cars have cameras too. Compute power is just money, that is about the thinnest advantage you can have.
The truth is no one has the physical AI algorithm yet. Having cars equipped with cameras, big GPUs connected to can bus is the easy part.
Tesla has some advantage since they are spending the most on automation compared to other car makers.
However compared to Waymo, Tesla is quite behind. Waymo has done a million rider-only rides.
Tesla isn’t even certified to do driverless rides. The driver has to be at the wheel and all accidents are the driver’s fault.
Tesla also doesn’t take safety as seriously as Waymo. So Elon may be a net negative to the org.
If the competent Tesla engineers got similar car hardware to Waymo, perhaps they could have been competitive. LiDAR solves a whole bunch of vision problems and gives extra high quality signal for processing.
Mercedes? Pick an easier competition? As much as European cars have a favorable reputation among American consumers: They are awful! If you do benchmarking, you are going to find European cars have lots of appearance parts that are high quality, but the actual components are poor. A more realistic comparison would be to compare Tesla vs Ford or GM. These are 3 companies that have similar tech/culture standards. This…
Had you watched the video before commenting, you would know the point of the video is that Consumer Reports gave Mercedes self driving a much higher rating than Tesla. Video shows how awful the Mercedes software really is
Earlier quoted context omitted.
It works regardless of how big p is. Engine failures in aircraft are exceedingly rare but this statistical effect of needing p^2 events instead of p events has saved many lives. Having multiple pilots has the same rationale. While errors are correlated, getting an error past two pilots is roughly p - p^2 less likely than if you had a solo pilot. Self-driving, as a mission critical endeavor, needs to be leveraging the…
> Self-driving, as a mission critical endeavor, needs to be leveraging the same statistical phenomenon in order to reduce the exceedingly rare but highly impactful mistakes. Uh... why? Shouldn't the goal be to be safer than people? Basically that's just bad engineering: If your argument is not to deploy an existing system that is better than the current installed base because some other technique might be better stil…
If Tesla had one that's safer than humans, then yes they should be allowed to deploy it. My argument was that they're making it harder for themselves to exceed that safety threshold by insisting on vision only.
The user that created that video is known to have preference for Tesla (based on Twitter posts and their YouTube channel is all about Tesla), the video may be biased. The Consumer Reports comparison at the beginning of the video is Mercedes "Driver Assistance" vs Tesla "Autopilot". These are technologies for lane assistance, speed limit assistance, etc. "Advanced cruise control" is a better term for these. This video…
For anything less than SAE Level 4, the human MUST take over driving when requested. The question is, can we? Sign up for the beta test and find out, I guess!
Personally I would much prefer a new Mercedes E class wagon with Driver Assist (Distronic) to a Tesla with FSD.
Earlier quoted context omitted.
I don't get this perspective. Somehow humans drive with visual input
And a human with centimeter depth perception could drive far better. The goal of an autonomous car isn't to replicate human driving, it is to drive safely, accurately and in accordance to the laws.
I’ve seen the “human-like” behaviour of FSD 12.x praised a lot by channels like this, particularly where the car is breaking the rules in a way they consider “normal”. And it’s a fair argument that predictable behaviour improves safety.
However, behaviour that is common in the US - like making a turn into a side street while a pedestrian is beginning to cross - would be considered exceptionally aggressive and reckless here in Australia. It’s a cultural difference I’ve adapted to when moving back and forth.
At the end of the day though, when I walk across a street, I don’t want to have to worry if Tesla has fine tuned their model correctly to match our local expectations of yielding. I’d rather they just followed the law as closely as possible - because that’s the most predictable behaviour of all.