From: Stephen Reed (reed@cyc.com)
Date: Wed May 22 2002 - 10:37:19 MDT
On Tue, 21 May 2002, Ben Goertzel wrote:
> For intance, interfacing Cyc with James R. Albus's (NIST) work using
> intelligent hierarchically/heterarchically-structured control systems to
> guide experimental tanks would be extremely interesting. Look up Albus's
> work if you're not familiar with it, it is truly awesome. If you don't know
> him and are potentially interested in this connection, let me know; I know
> Albus, though we're not extremely close.
Thanks Ben for the pointer!
>From http://www.citeseer.com I read "A Reference Model Architecture for
Intelligent Systems Design" and "The Engineering of Mind" by James
S. Albus at NIST. From Google, I found the NIST web site where RCS is
available.
Some points:
1. Albus provides a reference architecture without dictating
implementation, yet demonstrates that RCS (Real-time Control System) is a
implementation that works well for NC, and robot/vehicle control.
2. RCS is an open source C++ library downloadable from NIST, so the
code and algorithms can be inspected.
3. The fundamental elements: Behavior Generation, Planning, Agent,
Sensory Perception, Value Judgment, World Modeling, Knowledge Database,
and Entities of Attention, are described well enough that I can envision
how to develop Cyc vocabulary to represent them, and to provide
programming code for Cyc to implement them. We already have planning, and
the World Model and Knowledge Database together appear to be covered by
the current Cyc KB.
4. I like the organizational hierarchy Albus describes for using the basic
fundamental elements at seven levels of generalization. At each level,
the timespan of interest is 10x the directly lower level. With regard to
robotics, at the lowest level the fundamental elements behave similar to
Brook's Subsumption Architecture (no or very little planning, just react),
and at the highest level the emphasis is strategic and long term
planning/scheduling.
5. Although Albus design comes out of the Robotic/Numerical Control field,
I agree that his architecture is generally applicable. The RCS library
seems tailored to numerical control so I would not be immediately
interested in an interface whose purpose was to make Cyc more
intelligent. Rather, I would enhance Cyc along the lines of the Albus
Reference Model Architecture, and at the lowest hierarchical levels,
explore and use the world of external knowledge sources.
6. The most encouraging aspect of what I read, is that Albus' architecture
has been proven on manufacturing cells and self-guided vehicles. If I
dream that someday Cyc will be the intellect of robots, then it must at
the minimum be able to perform as well as RCS, or be able to program an
RCS configuration.
Steve
--
===========================================================
Stephen L. Reed phone: 512.342.4036
Cycorp, Suite 100 fax: 512.342.4040
3721 Executive Center Drive email: reed@cyc.com
Austin, TX 78731 web: http://www.cyc.com
download OpenCyc at http://www.opencyc.org
===========================================================
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:39 MDT