[AI Lab] Pepper robot learning "ball in a cup"

แชร์
ฝัง
  • เผยแพร่เมื่อ 21 ธ.ค. 2024

ความคิดเห็น • 71

  • @四方山-g7b
    @四方山-g7b ปีที่แล้ว +21

    看完老高的直播又来回味一下~

  • @jillybeanAZ
    @jillybeanAZ 8 ปีที่แล้ว +68

    After 90 attempts, I was waiting for pepper to throw the ball and cup against the wall and smash it.

    • @Angie2343
      @Angie2343 8 ปีที่แล้ว

      Agreed.

    • @commandocanary5095
      @commandocanary5095 5 ปีที่แล้ว +1

      But he can't do that because he has no choice but to obey.

    • @augustalavista6814
      @augustalavista6814 3 วันที่ผ่านมา

      that'll be happening when he's on SNL

  • @kenadams4142
    @kenadams4142 8 ปีที่แล้ว +45

    Imagine with a little practice how good they'd be at capturing humans for their people zoo.

    • @Angie2343
      @Angie2343 8 ปีที่แล้ว +3

      Or dancing.

  • @PattymayoTv
    @PattymayoTv 8 ปีที่แล้ว +5

    With the quick reflexes of the robot it seems it would have been easier to teach it to locate the ball in motion and move the cup into position based on the balls trajectory instead of trying to create an optimal swing. So is the robot really learning?

    • @childofsol6986
      @childofsol6986 8 ปีที่แล้ว +16

      The point isn't to make a robot that can catch a ball in a cup. The point is to make a robot that can learn how to play ball in a cup by practicing

    • @slabua
      @slabua 8 ปีที่แล้ว

      So it actually shouldn't be needing to use the camera?

    • @Jpjd222
      @Jpjd222 8 ปีที่แล้ว

      AYYYYYYYYYY YOOOOOOOOO patty ima big fan of you, didn't think you would be here XD

  • @corellifer9799
    @corellifer9799 8 ปีที่แล้ว +11

    Poor Pepper 90 trial...but after he never fails...cute and scary

  • @jonnynelson5734
    @jonnynelson5734 8 ปีที่แล้ว +3

    Something so simple... and yet so scary. The Robots Cometh!

  • @pitcairnpostcardmag
    @pitcairnpostcardmag 8 ปีที่แล้ว +7

    For some reason I forget that Pepper is a robot and just a machine. This makes it seem very impressive after the 100 attempts.

  • @133faceman
    @133faceman 7 ปีที่แล้ว +5

    Its a bit slow at learning. Once it knows the way to move its going to always get the ball in the pot. What would be impressive is if it was moving around and doing this!

  • @MikeinMiss
    @MikeinMiss 8 ปีที่แล้ว +2

    Just a few questions. It seems the only thing modified for each trial is the starting position while the joint movements are the same each time, right? If you were using only cameras attached to the robot, then I assume the arm was moved along only one axis? I have trouble imagining how the algorithm knew whether its adjustments were making it closer to or further from achieving the goal. Also, recursive algorithms have been around for decades now, is this approach any different or just a unique implementation?

  • @sebk7185
    @sebk7185 8 ปีที่แล้ว +13

    Impressive. Even scary...

  • @jameschudy576
    @jameschudy576 8 ปีที่แล้ว +11

    I wish she could reset my ball and cup.

  • @Galaxia53
    @Galaxia53 8 ปีที่แล้ว +3

    This is amazing.

  • @vorupan
    @vorupan 8 ปีที่แล้ว +1

    While it is cool that in the end the optimal trajectory pretty much grants a succsess, it would be nice if this learning process could be abstracted and applied to different ball-/cup-/string-dimensions. Im guessing in this case the optimal trajectory is only true for the same test condtitions?

    • @pontusloviken94
      @pontusloviken94 8 ปีที่แล้ว +3

      Yes, but we have another intern that is now working on generalizing the solution to different starting conditions.

  • @profMara-pn1vi
    @profMara-pn1vi 7 ปีที่แล้ว

    magnifico, complimenti per i vostro lavoro

  • @PunikaProduction
    @PunikaProduction 8 ปีที่แล้ว +2

    Will he even learn to get the ball out of the cup himself? Or untangle the string? That would be awesome, but I am impressed nontheless

    • @asyagrechka1870
      @asyagrechka1870 8 ปีที่แล้ว +1

      getting the ball out of the cup would have been simple to do, but untangling the string would be a little harder :)

    • @aboutrobots
      @aboutrobots 8 ปีที่แล้ว +1

      Hello Asya,
      Are you publishing this method?
      Also, technically, does Pepper use its own camera to check how close the ball is to the cup? Or do you use external tracking?

    • @asyagrechka1870
      @asyagrechka1870 8 ปีที่แล้ว +4

      We used 2 external cameras, 1 at the top and 1 at the side. When the side camera detected that the ball was in a downward motion and very close to the cup, the top camera took a picture and from this picture we measured the distance from the ball to the cup.
      I have also been able to successfully optimize the ball-in-cup task with user feedback (score between 0-10) depending on how good the throw was.

    • @aboutrobots
      @aboutrobots 8 ปีที่แล้ว

      Thank you for your answer! I hope I have time to try with Nao soon
      I see, good to know for the cameras.
      User feedback is such a simple yet elegant idea! Perfect for Pepper.

  • @simonfriedo
    @simonfriedo 10 หลายเดือนก่อน

    is source code for your implementation public?

  • @SitiAisyah-es5ho
    @SitiAisyah-es5ho 8 ปีที่แล้ว +4

    impressive 😉

  • @mallamsiang
    @mallamsiang 8 ปีที่แล้ว

    what algoritm and parameter used ?

  • @O5680
    @O5680 8 ปีที่แล้ว +1

    Still better at it than I am!

  • @mascada5230
    @mascada5230 7 ปีที่แล้ว +1

    Most didn't realize what the f! this means: It learns! And it won't be bored nor tired from the process, like us humans... Imagine the possibilities (like skynet kkk)

  • @zyxockjm
    @zyxockjm 8 ปีที่แล้ว

    is that "bilboquet" taped to pepper's hand?

  • @ziggyinjapan
    @ziggyinjapan 8 ปีที่แล้ว

    wow, great work!

  • @randlee2934
    @randlee2934 8 ปีที่แล้ว

    that's awesome !can this robot be programmed by users to test other algorithm ,and make it smarter ?

  • @ModellbautechnikSalzkammergut
    @ModellbautechnikSalzkammergut 8 ปีที่แล้ว

    can it Do the housework

  • @matthewfelgate
    @matthewfelgate 7 ปีที่แล้ว

    I wonder if this could be used to learn to play Snooker.

  • @troymclure9354
    @troymclure9354 6 ปีที่แล้ว +1

    Those creepy soulless Chibi eyes bely it's sinister plan for singularity and the end of mankind itself.

  • @Florentin-2ds
    @Florentin-2ds 8 ปีที่แล้ว

    Bien joué coach.

  • @brkuldeep
    @brkuldeep 7 ปีที่แล้ว

    fantastic

  • @DaveStovicek
    @DaveStovicek 8 ปีที่แล้ว +2

    a curious game... the only winning move is not to play...

  • @WesleyAusten
    @WesleyAusten 8 ปีที่แล้ว +1

    すごいな…

  • @diddlididdli1376
    @diddlididdli1376 8 ปีที่แล้ว

    EVERYBODY RUN!!!!

  • @j.r.p.7039
    @j.r.p.7039 6 ปีที่แล้ว

    Haha, we have done that in 2008!!!

  • @pika2802
    @pika2802 8 ปีที่แล้ว

    It's Amazing!
    but I feel so sad

  • @Zoza15
    @Zoza15 8 ปีที่แล้ว +2

    Get outta here man!, really! :O

  • @하루30초
    @하루30초 3 ปีที่แล้ว

    와우 소름 돋는다 ㄷㄷㄷ

  • @ahuachapan2
    @ahuachapan2 8 ปีที่แล้ว +3

    I can do that. Stupid robots.

  • @misawajason
    @misawajason 8 ปีที่แล้ว

    lol, "learning"..........more like programmers in the background making adjustments. And the second half of the video is downright funny. Softbank is a joke

    • @MyLittleMagneton
      @MyLittleMagneton 8 ปีที่แล้ว +1

      lol wut?

    • @childofsol6986
      @childofsol6986 8 ปีที่แล้ว +10

      It's an evolutionary algorithm -the AI is making the adjustments, not the programmers. Why are you so hostile?

    • @Flusterbomb
      @Flusterbomb 8 ปีที่แล้ว

      Aggrieved AI?

    • @asyagrechka1870
      @asyagrechka1870 8 ปีที่แล้ว +1

      everything is learned automatically - except stabilizing the ball before each throw.

  • @mahes303
    @mahes303 8 ปีที่แล้ว +2

    This is amazing.