Tony Lofthouse wrote: > It seems that your 'layered hierarchy' approach is very similar to Rod > Brooks subsumption architecture. This has been used to good effect in > generating natural behaviours in robotics but has not been very useful > in developing higher level cognition.
> Or maybe you are suggesting something else? Apparently I am re-inventing Brooks. =P >From that perspective, what I am doing is musing about how to discover the missing top-layer. Or, more precicely, how to recognise the charactoristics of that top-most layer among the varrious proposals as such charactoristics may be quite alien to what we immediately think of as intelligent behavior. Rod Brooks is one of my favorites. He has done some very good work. I think that many of his design ideas are necessary components of a complete artificially intelligent entity. -- I WANT A DEC ALPHA!!! =) 21364: THE UNDISPUTED GOD OF ALL CPUS. http://users.rcn.com/alangrimes/ ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]