Columbia Engineering Researchers Create a Self-Aware Robot

Discussion in 'HardForum Tech News' started by cageymaru, Jan 31, 2019.

  1. cageymaru

    cageymaru [H]ard as it Gets

    Messages:
    19,724
    Joined:
    Apr 10, 2003
    Columbia Engineering researchers have used deep learning, a machine learning (ML) technique, to teach a robot to become self-aware. A four-degree-of-freedom articulated robotic arm moved randomly and collected data from one thousand trajectories, each comprising of one hundred points. The robotic arm was not presented with prior knowledge of physics, geometry, or motor dynamics. Deep learning allowed the robot to initially create an inaccurate self-model that did not know what it was or how its joints were connected. But after nearly 35 hours of training, the self-model was accurate within 4 cm.

    This allowed the robot to perform "pick and place" tasks in a closed loop where it recalibrated itself based on its self-model as it moved. The objects in this task were placed onto the ground at specific locations each time. This allowed the robot to grasp objects and place them into a receptacle with a 100% success rate. When presented with the same task but in an open loop system; where it had to rely solely upon its internal self-model without external feedback, the robot performed the task with a 44% success rate. "'That's like trying to pick up a glass of water with your eyes closed, a process difficult even for humans,' observed the study's lead author Kwiatkowski, a PhD student in the computer science department who works in Lipson's lab." The robot is now capable of detecting and compensating for broken parts. It will re-imagine and retrain itself when damaged. The robot arm can also write text messages to researchers.

    To date, robots have operated by having a human explicitly model the robot. "But if we want robots to become independent, to adapt quickly to scenarios unforeseen by their creators, then it's essential that they learn to simulate themselves," says Hod Lipson, professor of mechanical engineering, and director of the Creative Machines lab, where the research was done. Lipson, who is also a member of the Data Science Institute, notes that self-imaging is key to enabling robots to move away from the confinements of so-called "narrow-AI" towards more general abilities. "This is perhaps what a newborn child does in its crib, as it learns what it is," he says. "We conjecture that this advantage may have also been the evolutionary origin of self-awareness in humans. While our robot's ability to imagine itself is still crude compared to humans, we believe that this ability is on the path to machine self-awareness." Lipson and Kwiatkowski are aware of the ethical implications. "Self-awareness will lead to more resilient and adaptive systems, but also implies some loss of control," they warn. "It's a powerful technology, but it should be handled with care." The researchers are now exploring whether robots can model not just their own bodies, but also their own minds, i.e. whether robots can think about thinking.
     
    DejaWiz likes this.
  2. deton8

    deton8 Limp Gawd

    Messages:
    395
    Joined:
    Sep 27, 2007
    Great, now the Terminators don't even need entire bodies. The arm is going to be running around by itself...
     
  3. Nukester

    Nukester [H]ard|Gawd

    Messages:
    1,429
    Joined:
    Mar 21, 2016
    That's not really self aware.. It was programmed to complete that task looking in specified sources. Self Aware would mean a consciousness
     
  4. DejaWiz

    DejaWiz Oracle of Unfortunate Truths

    Messages:
    18,748
    Joined:
    Apr 15, 2005
    This is some next level shit!

    T2-STILL-03.jpg
     
    Last edited: Jan 31, 2019
    The Mad Atheist likes this.
  5. Jailer

    Jailer Limp Gawd

    Messages:
    234
    Joined:
    Sep 4, 2002
    Robots are going to kill us all.
     
  6. cageymaru

    cageymaru [H]ard as it Gets

    Messages:
    19,724
    Joined:
    Apr 10, 2003
    Initially it completed the pick and place by looking in specific places. The second run where it only scored a 44% rating, it did the same task "blind." They are now teaching it to learn to "think about thinking."
     
  7. The Mad Atheist

    The Mad Atheist Gawd

    Messages:
    915
    Joined:
    Mar 9, 2018
    Now give it a full body, lets see what it can do!?
     
    xmadror likes this.
  8. PeaKr

    PeaKr Gawd

    Messages:
    716
    Joined:
    Sep 6, 2004
    Death-to-Bots.gif
     
    dgz likes this.
  9. MikeRotch

    MikeRotch Limp Gawd

    Messages:
    399
    Joined:
    Aug 23, 2013
    And after nearly 3 more days of training, the self-model was able learn how to navigate YouTube, watch videos of the Logan brothers, Tide Pod challenges, and "In My Feelings" challenge. And 1 more hour after that the self-model learned how to launch itself off the roof of the building and committed suicide.
     
  10. gamerk2

    gamerk2 [H]ard|Gawd

    Messages:
    1,565
    Joined:
    Jul 9, 2012
    Prove to me your self-aware; at the end of the day you are just responding to pre-programmed commands dictated by neurons firing on and off, no different from this machine.
     
  11. MV75

    MV75 [H]ard|Gawd

    Messages:
    1,025
    Joined:
    Nov 13, 2007
    That's a very npc response. You've already proven you have not the capacity to be proven to.
     
    Nukester likes this.
  12. dgz

    dgz [H]ardness Supreme

    Messages:
    5,169
    Joined:
    Feb 15, 2010
    Oh, so someone has managed to define "consciousness" beyond spewing many words but not saying all that much? That's why we don't have AI. We don't know what to build. We don't really know it is.
     
  13. Nanogrip

    Nanogrip Limp Gawd

    Messages:
    434
    Joined:
    Dec 4, 2016
     

    Attached Files:

  14. RipperMac

    RipperMac Limp Gawd

    Messages:
    353
    Joined:
    Jul 20, 2002
    Why? We are so fu*k*d!!:vulcan:
     
  15. Monkey God

    Monkey God Mangina Full of Sand

    Messages:
    6,722
    Joined:
    May 7, 2007
    This isn't self-awareness. For fucks sake.