Columbia Engineering Researchers Create a Self-Aware Robot

cageymaru

Fully [H]
Joined
Apr 10, 2003
Messages
20,730
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.
 

Nukester

[H]ard|Gawd
Joined
Mar 21, 2016
Messages
1,428
That's not really self aware.. It was programmed to complete that task looking in specified sources. Self Aware would mean a consciousness
 

DejaWiz

Fully [H]
Joined
Apr 15, 2005
Messages
21,334
This is some next level shit!

T2-STILL-03.jpg
 
Last edited:

cageymaru

Fully [H]
Joined
Apr 10, 2003
Messages
20,730
That's not really self aware.. It was programmed to complete that task looking in specified sources. Self Aware would mean a consciousness
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."
 

MikeRotch

Limp Gawd
Joined
Aug 23, 2013
Messages
415
But after nearly 35 hours of training, the self-model was accurate within 4 cm.

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.
 

gamerk2

[H]ard|Gawd
Joined
Jul 9, 2012
Messages
1,876
That's not really self aware.. It was programmed to complete that task looking in specified sources. Self Aware would mean a consciousness

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.
 

MV75

[H]ard|Gawd
Joined
Nov 13, 2007
Messages
1,025
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.

That's a very npc response. You've already proven you have not the capacity to be proven to.
 

dgz

Supreme [H]ardness
Joined
Feb 15, 2010
Messages
5,838
That's a very npc response. You've already proven you have not the capacity to be proven to.

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.
 
Top