BCS-SGAI 2010 Conference Workshop:
Bio-inspired and Bio-Plausible Cognitive Robotics
December 14, Peterhouse, Cambridge 10.30-12.30 and 13.15-14.45
There are also links in the table of contents to projects that overlap with CogAff, including, since 2004, collaborative projects in Cognitive Robotics (CoSy 2004-2008, CogX 2008-2012).
In addition to published and unpublished papers and technical reports, the web site also includes a collection of talks given over many years.
Apology
Despite warnings from academic staff the central university authorities decided in 2010 to reorganise campus web pages yet again, without taking action to ensure that references to old links are trapped and redirected.
As a result there are probably several broken links on this web site -- and on many other sites on this campus. Identifying and fixing them all will require massive effort for which resources are not available.
Many researchers propose a theory of THE right architecture for a system with some kind of intelligence (e.g. human intelligence).
Although this may be an appropriate way to address a specific technical problem, it is seriously misguided, if done as a contribution to our scientific or philosophical understanding, unless the specific architecture is related to a theory about THE SPACE of POSSIBLE architectures for various kinds of intelligent system.
Such a theory would need to include a survey of the possible types of components, the different ways they can be combined, the different functions that might be present, the different types of information that might be acquired and used, the different ways such information could be represented and processed, the different ways the architecture could come into existence (e.g. built fully formed, or self-assembling), and how various changes in the design affect changes in functionality.
Such a theory also needs to be related to a study of possible sets of requirements for architectures (and for their components). If we don't consider architectures in relation to what they are used for or needed for (in particular types of context) then we have no way of explaining why they should have the features they do have or of evaluating them. So we need to study
Proposing and studying just ONE architecture is like doing physics by finding out how things work around the leaning tower of Pisa, and ignoring all other physical environments; or like trying to do biology by studying just one species; or like trying to study chemistry by proposing one molecule for investigation. That's why, unlike other research groups that propose an architecture, argue for its engineering advantages or its evidential support, then build a tool to build models using that architecture, we have tried to build tools to explore alternative architectures so that we can search the space of designs instead simply promoting one design. See the SimAgent (sometimes written sim_agent) toolkit.
Recent developments elsewhere: Biologically Inspired Cognitive Architectures (BICA)
In the last few years the organisers of the BICA (Biologically Inspired Cognitive Architectures) workshops/conferences have begun to address this problem in a promising way.Here are some links:
Other links
- BICA 2008 Web site
- BICA 2009 Web site
with many useful links.
- CogArch Repository
Toward a Comparative Repository of Cognitive Architectures, Models, Tasks and Data
- Alexei V. Samsonovich's page.
(Including BICA links.)
- Ron Sun's Architectures Page
- umich.edu Cognitive Architectures page
By Bill Lemon, David Pynadath, Glenn Taylor and Bob Wray.
- Report on AIIB symposium, Spring 2010
- Requirements for a Fully Deliberative Architecture (Or component of an architecture)
Discussion note on some possible architectural sub-divisions.
- A First Draft Analysis of Some Meta-Requirements for Cognitive Systems in Robots
- Architecture-Based Motivation vs Reward-Based Motivation
- The Design-Based Approach to the Study of Mind (in humans, other animals, and machines)
Including the Study of Behaviour Involving Mental Processes.
The project was begun by Aaron Sloman and Glyn Humphreys (psychology) in 1991.
It is one of the oldest groupings in the School of Computer Science, though not as old as
- the medical image processing grouping,
- the natural language processing grouping
- the human-computer interaction grouping.
When the work began in 1991 it was a continuation of work begun in the 1960s at The University of Sussex, and continued in the School of Cognitive and Computing Sciences (COGS). (That, in turn, was a continuation of my 1962 Oxford DPhil Thesis attempting to defend Kant's philosophy of mathematics.)
Some of the earliest work was reported in this book (now out of print, but available online):
The Computer Revolution in Philosophy: Philosophy, science and models of mind (1978 -- with notes added since 2002).After AS moved to Birmingham, the work was partly funded by a grant to Sloman and Humphreys, from the UK Joint Council Initiative (JCI), which paid for equipment and a studentship.
Available as PDF and HTML. Also at ASSC repositoryChapter 7 on "Intuition and analogical reasoning", including reasoning with diagrams, and Chapter 8 "On Learning about Numbers" were specially closely related to the DPhil work on the nature of mathematical knowledge.
An additional studentship was funded by the Renaissance Trust (Gerry Martin).The first PhD thesis completed in the project was by Luc Beaudoin (funded by major scholarships from: Quebec's FCAR, The Association of Commonwealth Universities (UK), and the Natural Sciences and Engineering Research Council (NSERC) of Canada). It is listed here along with others. Among other things, it offered a new, unusually detailed analysis of aspects of motives that can change over time, and introduced the important distinction between deliberative mechanisms (which can represent, explore, hypothesise, plan and select possible situations, processes and future actions) and meta-management mechanisms which can can monitor, and to some extent control internal processes (including deliberative processes). The ideas are explained in more detail here. Similar work elsewhere uses labels such as "reflective", "metacognitive", "executive functions", and "self-regulation", though often with different emphases.
Later extensions arose from funding by DERA which enabled Brian Logan to work here for several years, followed by a project funded by The Leverhulme Trust on Evolvable virtual information processing architectures for human-like minds, originally set up with Brian Logan, which then paid for Matthias Scheutz to work here for 13 months (2000-2001), followed by Ron Chrisley (2001-2003).
A progress report on the CogAff project was written in 2003 (separate document).
From 2004 related work was funded by the EU, in two projects on cognitive robotics CoSy and CogX.
Much of this work is now done as part of the Intelligent Robotics research laboratory (led by Jeremy Wyatt) at Birmingham.
In 2004, Jackie Chappell, arrived in the School of Biosciences, and we began work on extending the biologists' ideas about "Altricial" and "Precocial" species to robots and investigating nature-nurture tradeoffs in animals.
Our theoretical research on animal cognition then expanded e.g. to include work on varieties of causation (Humean and Kantian) in animals and machines.
From 2008 this was further expanded to include studies of cognition in orangutans, in collaboration with Susannah Thorpe, also in Biosciences.CogAff is really a loose, informal, collection of sub-projects, most of them unfunded at any time,
including research on architectures, forms of representation and mechanisms occurring in humans,
other animals, and human-like machines.A more detailed list of topics covered can be found here.
Analysing such architectures, and the mental states and processes they can support, allows us to investigate, for instance, whether consciousness or the ability to have emotional states is an accident of animal evolution or a direct evolutionary consequence of biological requirements or a side-effect of things meeting other requirements and constraints.
One of the main outcomes of this research was development of the CogAff schema introduced above and (explained briefly in this poster) for characterising a wide range of types of possible architecture in natural and artificial systems (in contrast with most researchers on cognitive architectures who promote a particular architecture).
A special case (or subclass) of CogAff is the H-CogAff (Human-Cogaff) architectures, which is still currently too difficult to implement, though various subsets have been implemented by researchers here and elsewhere.
Requirements for architectural theories: The CogAff (generative Schema)
- Natural architectures evolved to fit many different biological niches. We need, but don't yet have, an agreed conceptual framework for describing both architectures and requirements/niches.
- We can move towards an agreed ontology for architectural designs by making some high level distinctions, e.g. between
1.a sensory/perceptual processes constantly changing to represent the environment (including internal states)
2.a motor/action/effector processes constantly changing the environment and perhaps some internal states
3.a central, more slowly changing, processesor between
1.b Evolutionarily very old reactive processes, constantly driven by what is sensed internally and externally
2.b Newer deliberative processes able to represent what does not exist but might, e.g. future actions, unseen situations, past causes.
3.b Specialised meta-management/reflective processes capable of describing information-processes states and processes in oneself (and therefore also others).
The CogAff schema shown above summarises this space of possible types of architectural components.
The first three divisions above (1.a--3.a) correspond to the vertical divisions in the schema.
The second three divisions above (1.b--3.b) correspond to the horizontal divisions in the schema: evolutionarily oldest functions in the bottom layer.NB A Schema for architectures is not an architecture.
It is more like a grammar. Instances of the schema are like sentences in the grammar. However the CogAff schema is a grammar whose 'sentences' are not strings but quite complex networks of concurrently active mechanisms with different functions.A special subset of the CogAff schema: Architectures with Alarms
Many organisms seem to have, and many robots and other intelligent machines will need an "alarm" mechanism, which receives input from many of the internal and external sensors and is capable of recognising patterns that require very rapid global reorganisation of ongoing processes, for example switching into states like fleeing, attacking, freezing, or attending closely to what may or may not be a sign of serious danger or some opportunity.
This kind of mechanism seems to be very old in animal evolution and can be observed in a woodlouse, for example, when it reacts to being touched by rolling itself up in a ball, or a fly which reacts to the rapid approach of a fly-swat by stopping whatever it is doing (e.g. feeding) and switching to an escape action.
So a very crude depiction of an insect-like information processing architecture could be something like this:
An insect-like special case of the CogAff schema is purely reactive -- none of the deliberative or meta-management functions are provided.
(Though there could be proto-deliberative mechanisms of kinds described here.)In such a (relatively) simple architecture, alarm mechanisms can trigger simple emotions (e.g. in the woodlouse that rapidly curls up in a ball if touched while walking).
Another special subset of the CogAff schema: Omega Architectures
Architectures of this general type where the flow of information and control can be thought of as roughly like the Greek capital letter Omega Ω (not necessarily presented in this sort of diagram) are often re-invented.
The assumption is that perception consists of detection of low level physical signals that are processed at increasing levels of abstraction until the processing generates new goals or preferences, at which point some selection mechanism (e.g. contention scheduling) chooses the best motive or action and the then signals propagate downwards to the motor subsystems which then produce behaviour.
This "peephole" view of perception and action contrasts with the "multi-window" view of both perception and action as involving concurrent processing at different levels of abstraction partly under the control of the environment and partly under the control of various layers of central information processing, operating in parallel.
A later section of this web site gives an overview of a much more complex special case (or subset of cases) of the CogAff schema: H-CogAff.
A poster summarising some of the main theoretical ideas is here (PDF 3-pages).
A flash version has mysteriously appeared on Docstoc here.
(Can anyone tell me how that happened?)
Some dimensions in which architectures can vary were presented at a Symposium on Designing a Mind in 2000 available here.
(However, that paper does not clearly distinguish the CogAff schema from the H-CogAff special case, presented briefly below.
It has other flaws that need to be remedied, in part by extending the analysis of ways in which architectures can differ,
in part inspired by the diversity produced by biological evolution, and in part by inspiring deeper analyses of that diversity as
proposed at the AIIB symposium in 2010.)
The name "CogAff" is used both for the project and as a label for a generic schema proposed several years ago for a wide variety of architectures, natural and artificial. (We don't claim it is general enough to cover all cases: some of the distinctions are not fine-grained enough. But it illustrates a style of research on architectures that is unfortunately rare.)This Schema, as explained above, classifies requirements for the major components of an architecture into nine broad categories on a 3x3 grid which can be connected together in different ways (depending on how various kinds of information - factual information, queries, control information, etc, flow between subsystems).
This is just a first crude sub-division, requiring more detailed analysis and further decomposition of cases. However it does cover many different types of architecture, natural and artificial, depicted rather abstractly above.
Architectures vary according to what mechanisms they have in the boxes, and how they are connected. Also more complex architectures may have important subdivisions and possibly may require functions that don't fit neatly into any of the boxes.
The generic CogAff schema includes an important sub-class of architectures that include mechanisms capable of producing what might be called "emotional" or "alarm" reactions, as show in the "insect-like" special case, above.
A much more complex special case is the H-CogAff architecture, which we suggest
provides a very high level "birds-eye view" of the architecture of a typical
(adult) human mind, depicted crudely here (as a first approximation):
It includes concurrently active sub-architectures that evolved at different times
in our evolutionary history, in addition to sub-architectures that grow themselves
during individual development (as discussed in this paper by Chappell and Sloman.)A paper summarising the ideas behind the CogAff schema and the H-CogAff architecture
is this 2003 progress report on the Cogaff project.A paper published in 1996 (published with commentaries) explained how emotional phenomena like long-lasting grief could be accommodated within this framework
I.P. Wright, A. Sloman, L.P. Beaudoin,
Towards a Design-Based Analysis of Emotional Episodes,
Philosophy Psychiatry and Psychology, 3, 2, pp. 101--126, 1996,
http://www.cs.bham.ac.uk/research/projects/cogaff/96-99.html#2Further details are provided in other papers, including for example this polemical piece:
Some Requirements for Human-like Robots: Why the recent over-emphasis on embodiment has held up progress (2008).
Now published in
Creating Brain-like Intelligence,
Eds. B. Sendhoff, E. Koerner, O. Sporns and H. Ritter and K. Doya,
Springer-Verlag, 2009 Berlin,
http://rapidshare.com/files/209786694/Creating_Brain-Like_Intelligence.zipAn incomplete survey of types of architecture that include a "deliberative layer" can be
found in Requirements for a Fully Deliberative Architecture.Some systems described as "deliberative" include only what we call "proto-deliberative" mechanisms.
Most of the hypothesised architectures are still too difficult to implement
though some of the simpler ones have been implemented using the SimAgent toolkit,
and demonstrated here.More complex examples were developed within the EU-funded CoSy robot project (2004-2008),
and are being extended in its sequel the CogX robot project (2004-2012).Tutorial presentations of how ideas like "qualia" and some of the vexing problems of consciousness ("the explanatory gap") can be understood in this framework are presented here.
In 1998 Gerd Ruebenstrunk presented some of our ideas for German readers in his diploma thesis in psychology on "Emotional Computers" (Bielefeld University, 1998). His 2004 presentation on emotions, at a workshop on "Affective Systems" (in English) is here.
NEWS: AUDIO BROADCAST ONLINE:
Audio discussion
broadcast on Deutschlandradio
on 'Emotional Computers' online
(mostly in German), chaired by
Maximilian Schönherr.
The audio link is on the right, under 'AUDIO ON DEMAND'. Click on
'Emotionale Agenten'.
Audio interview on grand challenge (December 2004)
NEWS: RESEARCH GRAND CHALLENGE:
In 2002, the UK Computing Research Committee (UKCRC) initiated a
discussion of research grand challenges. One of these is Grand Challenge
5:
'Architecture of Brain and Mind' For more information see
http://www.cs.bham.ac.uk/research/cogaff/gc/
OUR SOFTWARE TOOLS ARE AVAILABLE FREE OF CHARGE/OPEN SOURCE
at
http://www.cs.bham.ac.uk/research/poplog/freepoplog.html
Including
There are now far more papers in the Cogaff directory than were originally envisaged when this scheme started. When I find time I shall try to organise grouping by topic, though that will not be easy because of the complex overlaps of topic.
Browsers for the Postscript and PDF formats used here are freely available. See http://www.cs.bham.ac.uk/~axs/browsers.html
and search here:
tertiary emotions
meta-management
diagrams
vision architecture
artificial intelligence toolkit
information-processing
Kantian Humean causation
meta-requirements eucognition
free-will
what is AI?
"what is information?"
Grand challenge
research roadmap
education programming AI
qualia
Marvin Minsky
-----------------------------------matter energy information
"possible minds"
"design space" "niche space"
evolution altricial precocial
biology
emotions "cluster concepts"
emotions intelligence
emotions architectures
virtual machines
Turing irrelevance
CoSy Playmate
CoSy robot
functions of vision
consciousness
creativity machines
John McCarthy
-----------------------------------
Some documents are in html, latex or plain ascii text. Most of the postscript files are duplicated in PDF format.
PDF versions of files available only postscript can be provided on request. Email A.Sloman@cs.bham.ac.uk requesting conversion of a paper you cannot read.
Browsers for these formats are freely available. See http://www.cs.bham.ac.uk/~axs/browsers.html
NOTE (16 Jun 1998):
Files which were previously in form xxx.Z are now in the form xxx.gz
The toolkit runs in Poplog, which used to be an expensive commercial
product, but is also now available free of charge with full system
sources, at
http://www.cs.bham.ac.uk/research/poplog/freepoplog.html
OR
ftp://ftp.cs.bham.ac.uk/pub/dist/poplog/freepoplog.html
Information about the symposium, including abstracts and full papers can be found here http://www.cs.bham.ac.uk/research/projects/cogaff/dam00
A book of papers related to the workshop was edited by Darryl
Davis and published in 2004
Visions of Mind: Architectures for Cognition and
Affect.
IGI Publishing
Please read that file information BEFORE writing to individuals asking
for advice or information.
Please note: I do not deal with student admissions.
This file is maintained by Aaron Sloman, and designed to be lynx-friendly, and viewable with any browser.
Email A.Sloman@cs.bham.ac.uk
