Robot see, robot do: System learns after watching how-to videos
techxplore.com
Cornell University researchers have developed a new robotic framework powered by artificial intelligence—called RHyME (Retrieval for Hybrid Imitation under Mismatched Execution)—that allows robots to learn tasks by watching a single how-to video.
  • just_another_person@lemmy.worldEnglish
    1·
    1 month ago

    Maybe the acronym is different, but this has been done this exact same way for quite awhile unless I’m missing some key difference. Nvidia even has a toolkit for this already.

    Train > Simulation > Train > AR Simulation

    • Lugh@futurology.todayOPMEnglish
      1·
      1 month ago

      There’s a few different efforts like this. DeepMind have another one. I follow these types of developments as much as possible, because I think robotics is soon going to take off thanks to recent advances in AI.

  • HowAbt2morrow@futurology.todayEnglish
    13·
    1 month ago

    I hate to say and even more to see, but the two nerds in the pic are gonna take their knowledge and skills back to where they’re from thanks to little dick MAGA types.