Re: Re: [agi] SOTA
Hi Pei, If I want to start to try some low-budget programmable robot (say, in the price range of Robosapien V2 and LEGO Mindstorms NXT), which one will you recommend? I won't have high expectation in performance, but will be interested in testing ideas on the coordination of perception, reasoning, learning, and action. As you know, I am in favor of testing ideas on this sort of coordination in the context of a simulation world rather than physical robotics ... http://sourceforge.net/projects/agisim/ However, I also can see the value of experimenting with actual, real robots in the physical world. Toward the end of harmonizing these pursuits, I have considered creating an interface to the AGISim simulation world in the Pyro language http://www.pyrorobotics.org/?page=Pyro which is designed as an abstraction to allow AI algorithms to interact with robots without getting too deeply into the guts of the robotic sensors and actuators. So, Pei, my suggestion is that if you want NARS to interact with robots, perhaps you could do it using a Pyro interface. That way it would be easy to port your NARS-botic mind to various types of physical robots, and into the AGISim world as well (once we create a Pyro front end to AGISim) The Pyro page says " Robots: Currently, the robots supported include the Pioneer family (Pioneer, Pioneer2, PeopleBot robots), the Khepera family (Khepera, Khepera 2 and Hemisson robots), the AIBO, the IntelliBrain-Bot, and the Roomba. " I don't know how much these robots cost, nor do I know if there are other frameworks roughly equivalent to Pyro that I have not heard of. -- Ben - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: Re: [agi] SOTA
Hi Ben, As you know, though I think AGISim is interesting, I'd rather directly try the real thing. ;-) I know the Pyro project --- actually, I and two of the key members of Pyro were fellow students at graduate school, though I haven't contacted them in person in these years. I probably won't have the time for this project in the near future, but just want to prepare myself by exploring the possibilities and following the progress. I'll surely consider Pyro. Pei On 10/24/06, Ben Goertzel <[EMAIL PROTECTED]> wrote: Hi Pei, As you know, I am in favor of testing ideas on this sort of coordination in the context of a simulation world rather than physical robotics ... http://sourceforge.net/projects/agisim/ However, I also can see the value of experimenting with actual, real robots in the physical world. Toward the end of harmonizing these pursuits, I have considered creating an interface to the AGISim simulation world in the Pyro language http://www.pyrorobotics.org/?page=Pyro which is designed as an abstraction to allow AI algorithms to interact with robots without getting too deeply into the guts of the robotic sensors and actuators. So, Pei, my suggestion is that if you want NARS to interact with robots, perhaps you could do it using a Pyro interface. That way it would be easy to port your NARS-botic mind to various types of physical robots, and into the AGISim world as well (once we create a Pyro front end to AGISim) The Pyro page says " Robots: Currently, the robots supported include the Pioneer family (Pioneer, Pioneer2, PeopleBot robots), the Khepera family (Khepera, Khepera 2 and Hemisson robots), the AIBO, the IntelliBrain-Bot, and the Roomba. " I don't know how much these robots cost, nor do I know if there are other frameworks roughly equivalent to Pyro that I have not heard of. -- Ben - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED] - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: Re: Re: [agi] SOTA
Hi, On 10/24/06, Pei Wang <[EMAIL PROTECTED]> wrote: Hi Ben, As you know, though I think AGISim is interesting, I'd rather directly try the real thing. ;-) I felt that way too once, and so (in 1996) I did directly try the real thing. Building a mobile robot and experimenting with it was fun, but I quickly learned that one spends all one's time dealing with sensor and actuator issues and never really gets to deal with cognition in any interesting way. Admittedly, robotic tech has advanced a lot since then, but I think the basic point still holds. IMO, given the current state of mobile robot tech, to do robotics-based AI effectively requires at least one dedicated team member fully devoted to the robotics side Much robotics-based AI involves first experimenting in robot simulation software, anyway. AGISim right now is not a robot simulation software package, but it could be tailored into one, which would be interesting Maybe we'll start by making an AGISim Roomba, using the Pyro interface to Roomba ;-) -- Ben - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: Re: Re: [agi] SOTA
If your main interest is high level reasoning and cognition then at the moment there isn't very much going on in robotics which would fit well with that. When I started experimenting with PC controlled humanoids many years ago it soon became obvious that in order to stand any chance of doing high level reasoning using semantic networks and the like some pretty difficult perception problems needed to be tackled first. Six years later I'm still working on the perception problems, but there is an end in sight. I used to be of the opinion that doing robotics in simulation was a waste of time. The simulations were too perfect. To simplistic compared to the nitty gritty of real world environments. Algorithms developed and optimised for simulated environments would not translate well (or at all) into real robotics applications operating in non trivial environments. Ten years ago that was true, but now I think it's possible to build simulations with graphics and physics which are substantially more realistic, to the point where it might be possible to take algorithms developed within simulation, dump them onto a real robot and expect to see similar performance. You'd need to be careful to simulate sensor uncertainties, but it should be possible. Ironically, good quality simulations for robotics development will themselves assist in the cognitive process, becoming the robots inner theatre of the mind within which it may experiment with possible scenarios before committing to a course of action. On 24/10/06, Ben Goertzel <[EMAIL PROTECTED]> wrote: I felt that way too once, and so (in 1996) I did directly try the realthing. Building a mobile robot and experimenting with it was fun, butI quickly learned that one spends all one's time dealing with sensorand actuator issues and never really gets to deal with cognition in any interesting way. Admittedly, robotic tech has advanced a lotsince then, but I think the basic point still holds. IMO, given thecurrent state of mobile robot tech, to do robotics-based AIeffectively requires at least one dedicated team member fully devoted to the robotics sideMuch robotics-based AI involves first experimenting in robotsimulation software, anyway. AGISim right now is not a robotsimulation software package, but it could be tailored into one, which would be interesting Maybe we'll start by making an AGISimRoomba, using the Pyro interface to Roomba ;-)-- Ben-This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to:http://v2.listbox.com/member/[EMAIL PROTECTED] This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: Re: Re: Re: [agi] SOTA
I used to be of the opinion that doing robotics in simulation was a waste of time. The simulations were too perfect. To simplistic compared to the nitty gritty of real world environments. Algorithms developed and optimised for simulated environments would not translate well (or at all) into real robotics applications operating in non trivial environments. Ten years ago that was true, but now I think it's possible to build simulations with graphics and physics which are substantially more realistic, to the point where it might be possible to take algorithms developed within simulation, dump them onto a real robot and expect to see similar performance. You'd need to be careful to simulate sensor uncertainties, but it should be possible. Indeed ... I am interested in seeing AGISim go in this direction, though there is still more basic work to be done on AGISim first... Ironically, good quality simulations for robotics development will themselves assist in the cognitive process, becoming the robots inner theatre of the mind within which it may experiment with possible scenarios before committing to a course of action. Yeah, this is something we have discussed in an AGISim/Novamente context, though we have not done it yet. Basically, giving a Novamente system an "internal AGISim" theatre in which to experiment with various actions and scenarios, using simulated physics to shortcut the need for extensive cognition when appropriate... -- Ben - This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED]
Re: Re: Re: Re: [agi] SOTA
On 10/24/06, Ben Goertzel <[EMAIL PROTECTED]> wrote: Yeah, this is something we have discussed in an AGISim/Novamentecontext, though we have not done it yet. Basically, giving aNovamente system an "internal AGISim" theatre in which to experimentwith various actions and scenarios, using simulated physics to shortcut the need for extensive cognition when appropriate... Good. That's exactly the sort of thing that's needed, and that few if any other projects have attempted. (Simulated physics isn't just a shortcut for reasoning. "Making a bed by flicking the blankets - why does that work?") Not that Ben particularly needs my stamp of approval :) - but I think it's worth highlighting this because it's important. The interplay between perception and simulated physics is one of those features of the brain that's not just a historical accident. This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/[EMAIL PROTECTED]