Re: [agi] An interesting project on embodied AGI

2008-04-29 Thread Mike Tintner
Bob: Particularly I'd be interested in having the robot learn a model of its own body kinematics - the beginnings of a sense of self - based on data mining its sensory data and also using experimental movements to confirm or refute hypotheses, which mught to a naive observer look like "play". Cor

Re: [agi] An interesting project on embodied AGI

2008-04-29 Thread Bob Mottram
2008/4/29 Ed Porter <[EMAIL PROTECTED]>: > But I agree the project is really quite ambitious in that it is trying to > create an embodied robot with a real AGI for a brain. > > It may well make major contributions to AGI. It sounds like a promising start, but it should also be noted that there

RE: [agi] An interesting project on embodied AGI

2008-04-28 Thread Ed Porter
> > (2) high quality picture of icub > > http://www.robotcub.org/index.php/robotcub/content/download/1131/3970/file/D SC_3994.jpg > > (2) PDF describing the robot in detail and near its end giving a brief > description of some of the software, including open source software they are > usi

RE: [agi] An interesting project on embodied AGI

2008-04-28 Thread Derek Zahn
Thanks, what an interesting project. Purely on the mechanical side, it shows how far away we are from truly flexible house-friendly robust mobile robotic devices. I'm a big fan of the robotic approach myself. I think it is quite likely that dealing with the messy flood of dirty data coming f

Re: [agi] An interesting project on embodied AGI

2008-04-28 Thread Bob Mottram
of icub > > http://www.robotcub.org/index.php/robotcub/content/download/1131/3970/file/DSC_3994.jpg > > (2) PDF describing the robot in detail and near its end giving a brief > description of some of the software, including open source software they are > using. > > http:/

RE: [agi] An interesting project on embodied AGI

2008-04-28 Thread Ed Porter
near its end giving a brief description of some of the software, including open source software they are using. http://www.robotcub.org/misc/review3/05_Metta_et_al.pdf -Original Message- From: J Storrs Hall, PhD [mailto:[EMAIL PROTECTED] Sent: Monday, April 28, 2008 2:27

Re: [agi] An interesting project on embodied AGI

2008-04-28 Thread Mike Tintner
Bob: I'm not totally convinced that having a high number of degrees of freedom is actually necessary for the development of intelligence. Of greater importance is the sensory capability, and the ways in which that data is processed. A birds beak is a far less elaborate tool than a human hand or

Re: [agi] An interesting project on embodied AGI

2008-04-28 Thread Bob Mottram
2008/4/28 J Storrs Hall, PhD <[EMAIL PROTECTED]>: > I drool over the physical robot -- it's built like a brick outhouse. It has 53 > degrees of freedom, binocular vision, touch, audition, and inertial sensors, > harmonic drives, top-grade aircraft aluminum members, the works. > > That doofy face

Re: [agi] An interesting project on embodied AGI

2008-04-28 Thread J Storrs Hall, PhD
I drool over the physical robot -- it's built like a brick outhouse. It has 53 degrees of freedom, binocular vision, touch, audition, and inertial sensors, harmonic drives, top-grade aircraft aluminum members, the works. That doofy face places it squarely in the deepest ravine of the uncanny val

[agi] An interesting project on embodied AGI

2008-04-28 Thread Ed Porter
For an article on an interesting project on embodied AGI read "Next Step In Robot Development Is Child's Play" at http://www.sciencedaily.com/releases/2008/04/080421162240.htm --- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://