Slashdot Log In
Self-Introspecting Robot Learns to Walk
Posted by
CowboyNeal
on Sat Sep 01, 2007 10:20 AM
from the dreaming-of-electric-sheep dept.
from the dreaming-of-electric-sheep dept.
StCredZero writes "There's something about these things that seems eerily alive! The Starfish Robot reminds me of the Grid Bugs from Tron. But it's very real, and apparently capable of self introspection. In fact, instead of being explicitly coded, it teaches itself how to walk, and it can even learn how to compensate for damage."
Related Stories
This discussion has been archived.
No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
Full
Abbreviated
Hidden
Loading... please wait.
I'm not one to complain about newsworthiness (Score:3, Informative)
Re: (Score:2)
I believe that we will eventually create true self-replicating machines. It may even be one of the next important steps in the progression of computer technology (Boolean Logic, Relay, Tube, Transistor, IC, Microprocessor, Self-modifying code...)
Where it gets controversial is that I think that we could see it in the next 50 years or so. (That is, a self-replicating organism that can m
Self-reflection, literally! (Score:4, Interesting)
I hope this becomes a more general library that can be used to help self-reflection of this sort become a more separate part of physical designs. Even if the implications of the physical model aren't dynamic, a standard way of quickly seeing how your model 'sees' itself would help debugging and development in many future projects.
The only problem if it becomes more prevalent would be same one that quantum mechanics holds - people think that 'observer effects' has to involve consciousness, in the same way they'd think that a program's self-reflection would mean that it 'thinks' the same way they do. Neither is true - they're all mechanical terms wrapped in common language. Anything that can record an effect on the world (a falling rock's scratches in another stone would work) is a quantum observer - consciousness has nothing to do with the 'collapsing wave function'. The same here - a bit of self-reflection on the part of a program doesn't mean it's eerie self-corrections are capable of the complexities of our mind. If anything, such mechanical results would imply that our own minds act simpler in some ways than we may think, and that consciousness doesn't necessarily have to be as inscrutable and special as we might want.
Ryan Fenton
Re: (Score:3, Interesting)
Philosophers like Daniel Dennett agree with this notion. Consciousness may simply be a more complex continually-running predictive model like that used by this robot.
Re:Self-reflection, literally! (Score:5, Insightful)
Oddly enough, you could not conceive of anything without consciousness. Understanding is a mental, not physical process. You could however conceive of consciousness without the physical world. Indeed every culture has been doing so for all of recorded history in the form of spirit worlds, afterlife, etc.
Occam's razor can be much abused depending on how you frame your observation. "I think therefore I am." is much more straight forward than "I am incredibly complex and elaborate, therefore I think." Let's set Occam's Razor aside for this discussion, it doesn't seem to be the right tool for the job here.
If you allow yourself to view the conscious world as more fundamental than the physical world, then the observed consistency/connectedness of all physical phenomena would require some sort of governing over-consciousness that is responsible for the physical world. That of course would be a form of creationism, much reviled here on
Parent
Re: (Score:3, Interesting)
Understanding is a mental, not physical process.
You are assuming that they are independent, when in fact there is lots of evidence that mental processes depend on physical processes. There are drugs to alter your consciousness, physical damage to your brain can cause mental damage, and there are experiments where people's thoughts have been maninpulated by direct electrical stimulation (these people were undergoing brain surgery).
That of course would be a form of creationism, much reviled here on /.
Because it doesn't explain anything or offer any evidence.
Creepy (Score:5, Funny)
Re: (Score:3, Interesting)
Poor thing... (Score:2)
Argh, I said that and had a sudden mental image of hordes of animal rights activists protesting the mistreatment of robots.
Re: (Score:2)
Re: (Score:2)
Re: (Score:3, Interesting)
break all its legs off, post it on youtube (Score:2)
This robot moves in a fluid way, almost like a living creature would, many people will immediately anthropomorphize it.
--
What I find interesting is applications in todays world. How about equipping cars with abilities to sense its physical parts and build a total model of itself in real time. This could be used for immediate diagnosis of problems with the car itself and with its interaction with the surrounding environment. Many p
Don't like the look of this one bit. (Score:2, Insightful)
Hope it doesn't figure out how to circumvent the remote-control kill switch.
Hope it doesn't build a bigger version of itself...
Two questions... (Score:5, Funny)
2. Can it contemplate it?
dreaded beast (Score:3, Funny)
Skipping the blogodreck, here's the real info (Score:5, Informative)
First, get past the blogodreck to the actual work. [cornell.edu] (Slashdot editors missed a blog troll again.) Also, this work is several years old. The papers are from 2004 to 2006.
The original article says that the robot has "tilt and angle sensors in all its joints", but that's wrong. It only has one central tilt sensor. That's significant, because if it did have tilt sensors at each joint, system identification would be easier. The algorithm is doing better than one might expect.
This thing is doing what controls people call "automatic system identification". You have some set of sensor inputs and some set of control outputs, and the control system has to figure out how they relate. It does this by adjusting the outputs and watching what happens. There are various statistical techniques for doing this. Calling this "introspection" isn't really correct.
After system identification, the model is inverted, or solved for the inputs in terms of the outputs. The inverted model can then be used as a controller. Given desired outputs, the inputs needed to achieve them can be computed.
The novel result here is that a reasonably decent system identification for a nonlinear system is being performed with a small number of physical tries. That's an improvement over previous methods, which tended to "learn" very slowly. I'd looked at approaches like this for legged locomotion in the past, but the available system identification algorithms weren't good enough. This looks promising.
Good robotics work, crap Slashdot article.
Link to the Research Group at Cornell (Score:3, Informative)
So would a beowulf cluster of these.... (Score:4, Funny)
The next step... (Score:4, Funny)
Compensate for damaga (Score:3, Interesting)
Re: (Score:2)
Re:Damage (Score:4, Funny)
Parent
Re: (Score:3, Interesting)
Re: (Score:2)