• Maladius@lemmy.world
    link
    fedilink
    arrow-up
    12
    ·
    1 year ago

    What’s the hold up on my trash taking/dishes doing robot? Is object recognition still too slow? I heard there’d been strides with fuzzy logic there. Is power storage still a limiting factor?

    • howrar
      link
      fedilink
      arrow-up
      7
      ·
      edit-2
      1 year ago

      Object recognition is good enough for this kind of task now IMO. The problem is with controlling physical hardware, which is a problem typically handled by reinforcement learning. This is a difficult problem for current techniques mainly because of its sequential nature (i.e. what you need to do now depends on the state you’re in, which depends on what you did a second ago). Being sequential means you can’t easily take advantage of GPUs for parallelizing a huge amount of work like you can for image generation where you produce the entire thing at once.