I think AI driver give a good summary of some of issues with the Mark Rober showcase of LIDAR.

  • Some of the bias Mark Rober friendships with the LIDAR supplier.
  • Not using Tesla full self driving
  • Being so nervous that he accidentally disables autopilot, twice.
  • The one sided view in LIDAR, with not show examples of LIDAR have issues.
  • Give a way forward to do the tests with FSD
  • Mark Rober not giving the test his full attention, fun vs scientific process
  • 74 183.84@lemm.ee
    link
    fedilink
    English
    arrow-up
    10
    ·
    3 months ago

    Looks like you are trying really hard to defend Teslas ‘self driving’ bullshit. Tesla only using cameras for this is stupid. If you can’t see that then its a good thing you aren’t an engineer. Also, it was a youtube video for entertainment. Not a scientific study. You are trying too much here

  • Noel_Skum@sh.itjust.works
    link
    fedilink
    English
    arrow-up
    8
    ·
    3 months ago

    The single biggest issue must be that it was just funny / thought provoking content on YouTube - not a groundbreaking thesis being developed in real time.

    However, some apparent shortcomings of the Tezla are probably worth following-up… by far more qualified individuals in a far more formal and peer reviewable environment.

      • Noel_Skum@sh.itjust.works
        link
        fedilink
        English
        arrow-up
        3
        ·
        3 months ago

        Thank you.

        I saw it a few days ago. I know the guy from his glitterbomb videos but it was the Roadrunner vibe that really attracted me this time

        I’m no scientist but if you can map space mountain with lidar then… it’s probably better then a camera at identifying physical objects blocking your path. And his short experiment seems to support that.

  • Fizz@lemmy.nz
    link
    fedilink
    English
    arrow-up
    3
    ·
    3 months ago

    I don’t think it was very good response. All the points he brings up do not change any of the outcomes. Fsr would likely still fail all these tests.

    Ive watched a lot of AI driver and I think fsr is cool but its lack of lidar is a huge mistake and creates these dangerous situations whete Tesla isn’t smart enough to mimic the awareness of a real driver.

    • Eideen@lemmy.worldOP
      link
      fedilink
      English
      arrow-up
      1
      arrow-down
      1
      ·
      3 months ago

      lack of lidar is a huge mistake and creates these dangerous situations whete Tesla isn’t smart enough to mimic the awareness of a real driver.

      Can you give some examples?

        • Eideen@lemmy.worldOP
          link
          fedilink
          English
          arrow-up
          2
          arrow-down
          2
          ·
          3 months ago

          I didn’t see any humans been test in the Mark Rober video. How do you know I won’t fail the same test?

          • GreyEyedGhost@lemmy.ca
            link
            fedilink
            English
            arrow-up
            5
            ·
            3 months ago

            There was a story of where a deer was hit by a Tesla in FSD and didn’t even slow down. If it can happen to a deer it can happen to a person, and LIDAR would be a lot less likely to in either case.

            • LammaLemma@lemmy.ca
              link
              fedilink
              English
              arrow-up
              4
              ·
              3 months ago

              I think the previous post is asking for human drivers as tests. I think some people are just simping for Tethla. If Tesla started using LIDAR again- they’d cheer for it.

          • Fizz@lemmy.nz
            link
            fedilink
            English
            arrow-up
            1
            ·
            3 months ago

            You want to put a human in front of the Tesla and hope it stops? I don’t think killing 5 people is a W for Tesla.