Newsgroups: comp.robotics.research,comp.ai.genetic,comp.ai.alife,sci.cognitive
Path: cantaloupe.srv.cs.cmu.edu!nntp.club.cc.cmu.edu!miner.usbm.gov!news.er.usgs.gov!mcmcnews.cr.usgs.gov!news.cs.indiana.edu!news.nstn.ca!newsflash.concordia.ca!sunqbc.risq.net!hobbit.ireq.hydro.qc.ca!news
From: inmanh@cogs.susx.ac.uk (Inman Harvey)
Subject: Artificial Evolution of Adaptive Behaviour -- Thesis
X-Nntp-Posting-Host: riopelle.ireq.ca
Message-ID: <MBOYER.96Jan11161039@riopelle.robot.ireq.ca>
Lines: 61
Sender: news@ireq.hydro.qc.ca (Netnews Admin)
Organization: University of Sussex
Date: Thu, 11 Jan 1996 21:10:39 GMT
Approved: mboyer@robot.ireq.ca
Xref: glinda.oz.cs.cmu.edu comp.robotics.research:372 comp.ai.genetic:7662 comp.ai.alife:4885 sci.cognitive:11674

My Thesis on "The Artificial Evolution of Adaptive Behaviour" is
available by ftp (either as a whole or by individual chapters) at
http://www.cogs.susx.ac.uk/users/inmanh/inman_thesis.html

Abstract:

A methodology is presented for the design through artificial evolution
of adaptive complex systems, such as the control systems of autonomous
robots.

Genetic algorithms have largely been tailored towards optimisation
problems with a fixed and well-defined search-space; the SAGA (Species
Adaptation Genetic Algorithms) framework is introduced for the
different domain of long term artificial evolution, where the task
domain is ill-defined and can increase in complexity
indefinitely. Genotypes should be able to increase in length
indefinitely, and evolution will take place in a genetically converged
population. Significant changes from normal genetic algorithm practice
follow from this.

It is shown that changes in genotype length should be restricted to
gradual ones. Appropriate mutation rates are proposed to encourage
exploration of the high-dimensional fitness landscape without losing
gains already made.  Tournament selection, or similar ranking methods,
are advocated as a way of maintaining selection pressures at a known
rate. A crossover algorithm is introduced, which allows for
recombination of genotypes of different lengths without undue
confusion. The significance of a developmental process from genotype
to phenotype, of co-evolution and of neutral drift through genotype
space, are discussed.

As a class of control systems appropriate for evolution, programming
languages are dismissed in favour of realtime dynamical recurrent
connectionist networks; issues of time, representation and learning in
such networks are discussed. A whole complex system, comprised of such
a network together with sensory and motor systems, is characterised as
a dynamical system with internal state, coupled to a dynamical
environment.

Applications of these theoretical frameworks of artificial evolution
and of control systems are demonstrated in a series of experiments
with mobile robots engaged in navigational tasks using low-bandwidth
sensors. Initial experiments are in simulation; the validity of such
simulations and the significance of noise is discussed. Then
experiments move to a real-world domain, with the use of a specialised
piece of hardware which allows the automatic evaluation of populations
of mobile robots using real low-bandwidth vision to navigate in a test
environment. Evolution of capabilities is demonstrated in a sequence
of navigational tasks of increasing complexity.

Inman Harvey
Evolutionary and Adaptive Systems Group
COGS
University of Sussex

--
*****   Crossposted with comp.robotics.research (moderated)  *****
  Summary: Academic, government & industry research in robotics.
    Charter: ftp://ftp.ireq-robot.hydro.qc.ca/pub/crr/Charter
	       Submissions: crr@ireq-robot.hydro.qc.ca
 Meta-discussions/information: crr-request@ireq-robot.hydro.qc.ca
