Josh said: [what's missing] In a single word: feedback.
At a very high level of abstraction, most the AGI (and AI for that matter) schemes I've seen can be caricatured as follows: 1. Receive data from sensors. 2. Interpret into higher-level concepts. 3. Then a miracle occurs. 4. Interpret high-level actions from 3 into motor commands. 5. Send to motors. What's wrong with this? It implicitly assumes that data flows from 1 to 5 in waterfall fashion, and that feedback, if any, occurs either within 3 or as a loop thru the external world. In the hierarchical control system architecture that I am using for Texai, as inspired by the writings of James Albus, feedback can occur at each hierarchical level. Each node in the control hierarchy, even down to the device driver level, can be viewed as an agent. Pan, tilt and focus actuators for a vision sensor might be directly utilized by a node one level above the device driver to follow a moving object of interest. Likewise time-sensitive harm-protecting safeguard behavior should be implemented at the lowest possible level of a hierarchical control structure to minimize response time. If the robot puts its hand by mistake into a fire, the arm should withdraw before higher levels of behavior get involved. Regarding step (3) above, in the Texai architecture I will follow the proven example of driverless cars as exemplars of fielded hierarchical control systems. At the lowest level, a Rodney Brooks style finite state machine suffices to govern behavior and abstract concepts may not be needed because the real world is your model. The robot hand should pick up an object by simple pressure feedback (i.e. touch), not by calculating the exact position of the object and computing in advance the sequence of grasping actions. At higher levels in the hierarchical control system, (3) occurs as a result of symbolic processing of abstracted perceptions as received from subordinate levels. For example, the robot wants to get from the bedroom to the kitchen, so it deductively plans its route to take into account the sleeping dog that it expects to be in the way. It can perform symbolic plan repair as it executes its movement should sensors report anything amiss, or should an opportunity for improved performance arise (e.g. dog is not in the way). -Steve Stephen L. Reed Artificial Intelligence Researcher http://texai.org/blog http://texai.org 3008 Oak Crest Ave. Austin, Texas, USA 78704 512.791.7860 ----- Original Message ---- From: "J Storrs Hall, PhD" <[EMAIL PROTECTED]> To: agi@v2.listbox.com Sent: Monday, April 21, 2008 3:18:25 PM Subject: Re: [agi] WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? (Aplogies for inadvertent empty reply to this :-) On Saturday 19 April 2008 11:35:43 am, Ed Porter wrote: > WHAT ARE THE MISSING CONCEPTUAL PIECES IN AGI? In a single word: feedback. At a very high level of abstraction, most the AGI (and AI for that matter) schemes I've seen can be caricatured as follows: 1. Receive data from sensors. 2. Interpret into higher-level concepts. 3. Then a miracle occurs. 4. Interpret high-level actions from 3 into motor commands. 5. Send to motors. What's wrong with this? It implicitly assumes that data flows from 1 to 5 in waterfall fashion, and that feedback, if any, occurs either within 3 or as a loop thru the external world. Problem is, in brains, there are actually more nerve fibers transmitting data from higher numbers to lower, i.e. backwards, than forwards. I think that the interpretation of sensory input is a much more active process than we AGIers realize, and that doing things requires a lot more sensing. Here's a quip that feels like it has some relevance: "What's the difference between a physicist and an engineer? A physicist is someone who spends all his time building machinery, to help him write an equation. An engineer is someone who spends all his time writing equations, in order to build machinery." Josh ------------------------------------------- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?& Powered by Listbox: http://www.listbox.com ____________________________________________________________________________________ Be a better friend, newshound, and know-it-all with Yahoo! Mobile. Try it now. http://mobile.yahoo.com/;_ylt=Ahu06i62sR8HDtDypao8Wcj9tAcJ ------------------------------------------- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244&id_secret=101455710-f059c4 Powered by Listbox: http://www.listbox.com