|
|
cosyBibAdd.bib
@TECHREPORT{Hawes/etal:2006a,
AUTHOR = {Nick Hawes and Jeremy Wyatt and Aaron Sloman},
TITLE = {An Architecture Schema for Embodied Cognitive Systems},
INSTITUTION = {University of Birmingham, School of Computer Science},
YEAR = {2006},
NUMBER = {CSR-06-12},
MONTH = {November},
ABSTRACT = {The study of architectures to support intelligent behaviour is certainly
the broadest, and arguably one of the most ill-defined enterprises
in AI and Cognitive Science. In the CoSy project one of our goals
is to develop and understand cognitive architectures suitable for
the control of robots. This is not the same as developing an architecture
for robot control, nor is it the same as developing a purely cognitive
architecture unconnected to real sensors or actuators. We argue that
work on architectures traditionally falls into two camps. First there
are cognitive architectures which attempt to provide unified theories
of cognition such as SOAR [Laird et al., 1987] and ACT-R [Anderson
et al., 2004]. Their value is typically measured in terms of an ability
to reproduce some of the characteristics of human like information
processing. ACT-R for example is used extensively for creating models
of cognition that are then evaluated against data from humans. In
other words, they are evaluated as psychological theories. On the
other hand, roboticists have been engaged with issues of how to enable
robots to act reliably and robustly in a rapidly changing world when
faced with limited computational power, uncertain sensing, and uncertain
action. Architectures for robot control such as 3T [Bonasso et al.,
1997] are therefore largely concerned issues of real- time control,
uncertainty, sensory fusion (or the lack of it), and error recovery.
They are evaluated in terms of the performance of the resulting robotic
systems on a variety of tasks.
In CoSy we have interests in both cognitive science and engineering
science, and consequently our work is related to both of the aforementioned
camps whilst also looking at closely related issues. Our work is
neither concerned with trying to model humans or any other specific
type of animal, nor with trying to compete on practical design tasks.
Rather it is concerned with trying to understand the possibilities
and trade-offs involved in different designs in relation to different
sets of requirements. In this paper we will describe an architecture
schema which inherits some of the ambitions of classic cognitive
architectures, and those of robot control architectures, whilst allowing
us to explore these additional issues. It is important to note now
that we don't present an empirical evaluation of an implementation
of a scenario-specific instantiations of the architecture schema
in this paper, we do describe two possible instantiations based on
the CoSy demonstrator scenarios. It is also worth stating at this
stage that our intention is not to perform extensive evaluation of
the architecture schema against human behaviour. Instead we intend
to evaluate it by profiling behaviour of scenario-specific tiations
of it under varying conditions, such as internal failures and varying
types of change in the world.},
DATE-ADDED = {2009-01-05 11:49:03 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
EMAIL = {N.A.Hawes@cs.bham.ac.uk, J.L.Wyatt@cs.bham.ac.uk, A.Sloman@cs.bham.ac.uk},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/CSR-06-12.pdf}
}
@TECHREPORT{Hawes/etal:2007b,
AUTHOR = {Nick Hawes and Michael Zillich and Jeremy Wyatt},
TITLE = {BALT \& CAST: Middleware for Cognitive Robotics},
INSTITUTION = {University of Birmingham, School of Computer Science},
YEAR = {2007},
NUMBER = {CSR-07-1},
MONTH = {April},
ABSTRACT = { In this paper we present a toolkit for implementing architectures
for intelligent robotic systems. This toolkit is based on a previously
developed architecture schema (a set of architecture design rules).
The purpose of both the schema and toolkit is to facilitate research
into information-processing architectures for state-of-the-art intelligent
robots, whilst providing engineering solutions for the development
of such systems. A robotic system implemented using the toolkit is
presented to demonstrate its key features. },
DATE-ADDED = {2009-01-05 11:37:59 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
EMAIL = {N.A.Hawes@cs.bham.ac.uk, M.Zillich@cs.bham.ac.uk, J.L.Wyatt@cs.bham.ac.uk},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/CSR-07-1.pdf}
}
@MASTERSTHESIS{LisonThesis2008,
AUTHOR = {Pierre Lison},
TITLE = {Robust Processing of Situated Spoken Dialogue},
SCHOOL = {Universit\"at des Saarlandes},
YEAR = {2008},
MONTH = {December},
ABSTRACT = {Spoken dialogue is often considered as one of the most natural means
of interaction between a human and a machine. It is, however, notoriously
hard to process using NLP technology. As many corpus studies have
shown, natural spoken dialogue is replete with disfluent, partial,
elided or ungrammatical utterances, all of which are very hard to
accommodate in a dialogue system. Furthermore, automatic speech recognition
[ASR] is known to be a highly error-prone task, especially when dealing
with complex, open-ended discourse domains. The combination of these
two problems -- ill-formed and/or misrecognised speech inputs --
raises a major challenge to the development of robust dialogue systems.
This thesis presents an integrated approach for addressing these issues
in the context of domain-specific dialogues for human-robot interaction
[HRI]. Several new techniques and algorithms have been developed
to this end. They can be divided into two main lines of work.
The first line of work pertains to speech recognition. We describe
a new model for context-sensitive speech recognition, which is specifically
suited to HRI. The underlying hypothesis is that, in situated human-robot
interaction, ASR performance can be significantly improved by exploiting
contextual knowledge about the physical environment (objects perceived
in the visual scene) and the dialogue history (previously referred-to
objects within the current dialogue). The language model is dynamically
updated as the environment changes, and is used to establish expectations
about uttered words which are most likely to be heard given the context.
The second line of work deals with the robust parsing of spoken inputs.
We present a new approach for this task, based on a incremental parser
for Combinatory Categorial Grammar [CCG]. The parser takes word lattices
as input and is able to handle ill-formed and misrecognised utterances
by selectively relaxing and extending its set of grammatical rules.
This operation is done via the introduction of non-standard CCG rules
into the grammar. The choice of the most relevant interpretation
is then realised via a discriminative model augmented with contextual
information. The model includes a broad range of linguistic and contextual
features, and can be trained with a simple perceptron algorithm.
All the algorithms presented in this thesis are fully implemented,
and integrated as part of a distributed cognitive architecture for
autonomous robots. We performed an extensive evaluation of our approach
using a set of Wizard of Oz experiments. The obtained results demonstrate
very significant improvements in accuracy and robustness compared
to the baseline.},
URL = {http://www.cognitivesystems.org/publications/main.thesis.plison2008.pdf}
}
@TECHREPORT{luo06kth,
AUTHOR = {Luo, J. and Pronobis, A. and Caputo, B. and Jensfelt, P.},
TITLE = {The {KTH-IDOL2} Database},
INSTITUTION = {Kungliga Tekniska Hoegskolan, CVAP/CAS},
YEAR = {2006},
NUMBER = {CVAP304},
MONTH = {October},
URL = {http://www.cognitivesystems.org/publications/luo06kth_idol2.pdf}
}
@TECHREPORT{pronobis06idiap,
AUTHOR = {Pronobis, A. and Caputo, B.},
TITLE = {The More You Learn, the Less You Store: Memory-Controlled Incremental
{SVM}},
INSTITUTION = {IDIAP},
YEAR = {2006},
TYPE = {IDIAP-RR},
NUMBER = {51},
ABSTRACT = {The capability to learn from experience is a key property for a visual
recognition algorithm working in realistic settings. This paper presents
an SVM-based algorithm, capable of learning model representations
incrementally while keeping under control memory requirements. We
combine an incremental extension of SVMs with a method reducing the
number of support vectors needed to build the decision function without
any loss in performance, introducing a parameter which permits a
user-set trade-off between performance and memory. The resulting
algorithm is guaranteed to achieve the same recognition results as
the original incremental method while reducing the memory growth.
Moreover, experiments in two domains of material and place recognition
show the possibility of a consistent reduction of memory requirements
with only a moderate loss in performance. For example, results show
that when the user accepts a reduction in recognition rate of 5%,
this yields a memory reduction of up to 50%.},
URL = {http://www.cognitivesystems.org/publications/pronobis06idiap.pdf}
}
@TECHREPORT{pronobis05kth,
AUTHOR = {Pronobis, A. and Caputo, B.},
TITLE = {The {KTH-INDECS} Database},
INSTITUTION = {Kungliga Tekniska Hoegskolan, CVAP},
YEAR = {2005},
NUMBER = {CVAP297},
MONTH = {September},
URL = {http://www.cognitivesystems.org/publications/pronobis05kth_indecs.pdf}
}
@TECHREPORT{Sloman:2006a,
AUTHOR = {A. Sloman},
TITLE = {{How to Put the Pieces of AI Together Again}},
INSTITUTION = {University of Birmingham, School of Computer Science},
YEAR = {2006},
NUMBER = {COSY-TR-0608},
NOTE = {Poster summary for AAAI'06 Members Poster Session, Boston July 2006.
2-Page abstract at http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#tr0608
Poster at http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#pr0603},
ABSTRACT = {Since the 1970s AI as a science has progressively fragmented into
many activities that are very narrowly focused. It is not clear that
work done within these fragments can be combined in the design of
a human-like integrated system -- long held as one of the goals of
AI as science. A strategy is proposed for reintegrating AI based
around a backward-chaining analysis to produce a roadmap with partially
ordered milestones, based on detailed scenarios, that everyone can
agree are worth achieving, even when they disagree about means. This
is a summary of ideas being developed within the CoSy project about
how to plan long term research using a partially ordered network
of scenarios and a grid of requirements for competences. },
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
EDITOR = {Ion Muslea and Dieter Fox},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/aaai06-member.pdf}
}
@MISC{slomanpr0801,
AUTHOR = {Aaron Sloman},
TITLE = {{A Multi-picture Challenge for Theories of Vision}},
YEAR = {2008},
ABSTRACT = {Demonstration that humans can be presented with a collection of unpredictable
photographs of natural, moderately complex scenes (e.g. about 10),
at the rate of one a second, and can then answer somewhere between
30\% and 70\% of a set of unexpected questions about what was seen
in the pictures. This demonstrates some constraints on possible mechanisms
capable of supporting vision in humans and perhaps some other animals.
The processing needs to go up several levels of abstraction (e.g.
perhaps nine or ten levels) within a second. This almost certainly
makes use of a great deal of prior knowledge about kinds of things
that can be seen in our world, though most of that knowledge is dormant
most of the time. Somehow the image data can wake up relevant subsets
at various levels of abstraction, which can then collaborate in converging
on an interpretation. If the image is removed after a short time
not all the potential processing will have been completed, but a
surprising amount has been achieved. There seems to be a lot of individual
variation, though so far only informal tests have been done.},
INSTITUTION = {School of Computer Science, The University of Birmingham},
NUMBER = {COSY-PR-0801},
TYPE = {Research Note},
URL = {http://www.cognitivesystems.org/publications/multipic-challenge.pdf}
}
@TECHREPORT{Sloman:2007,
AUTHOR = {A. Sloman},
TITLE = {{Two Notions Contrasted: `Logical Geography' and `Logical Topography'
(Variations on a theme by Gilbert Ryle: The logical topography of
`Logical Geography'.)}},
INSTITUTION = {School of Computer Science, University of Birmingham},
YEAR = {2007},
NUMBER = {COSY-DP-0703},
ADDRESS = {Birmingham, UK},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#dp0703},
ABSTRACT = {In his 1949 book The Concept of Mind (CM) and in other writings the
philosopher Gilbert Ryle suggested that a good way for philosophers
to resolve some philosophical disputes (often by discovering that
both sides were based on conceptual confusions) is to study the 'logical
geography' of the concepts involved. I used to think I knew what
that meant. But now I think I was using a different concept of from
Ryle's -- referring to a different type of analysis that is fundamentally
related to the scientific project of providing explanations of how
the world works. This paper provides some background then describes
the difference I have in mind, showing how a theory about how some
class of objects works generates a set of possible types of states,
events and processes that can be referred to as a "Logical Topography".
There are different ways of carving up that space into different
categories or identifying different relationships that can occur
within it. Those different ways define different "Logical geographies".
This paper shows how work in AI and robotics can extend the work
of Ryle and other philosophers by exposing logical topographies that
support different possible logical geographies, only one of which
may correspond to how our ordinary concepts work. This helps to resolve
some century-old puzzles about the nature of conceptual analysis
and to show how the relationships between philosophy and science
can be deeper than many philosophers realise.
(This paper extends one of the points made in Appendix IV of my Oxford
DPhil thesis (1962))},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/#dp0703}
}
@MISC{Sloman:2007c,
AUTHOR = {Aaron Sloman},
TITLE = {{A First Draft Analysis of some Meta-Requirements for Cognitive Systems
in Robots}},
YEAR = {2007},
NOTE = {Contribution to euCognition wiki, also available as, http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#dp0701},
ABSTRACT = {This is a contribution to discussions regarding the construction of
a research roadmap for future cognitive systems, including intelligent
robots, in the context of the euCognition network, and the UKCRC
Grand Challenge 5: Architecture of Brain and Mind. I have argued
that in the context of trying either (a) to produce working systems
to elucidate scientific questions about intelligent systems, or (b)
to advance long term engineering objectives through advancing science,
the task of coming up with a set of requirements that is sufficiently
detailed to provide a basis for developing milestones and evaluation
criteria is itself a hard research problem. One aspect of the problem
is to provide an analysis of words and phrases that are commonly
used to specify objectives, but whose meanings are very abstract
and unclear, in particular words like ``robust''. ``flexible'', ``creative''
and ''autonomous''. This document argues that the words all share
a feature that could be described as expressing a ''meta-requirement''.
What that means is that none of them is directly associated with
a set of features which, if found in an object or process or system,
would justify the application of the label, or which can be used
to derive design features. In other words the words express concepts
that do not specify criteria for their instances though they do express
criteria for deriving criteria. To derive criteria from the concepts
more information is required, from which the criteria can be derived,
in a systematic way that differs for each of the meta-criteria. Analyses
of the words based on this idea are proposed. This is an exercise
in analysis of logical topography. Subsequent work will need to provided
detailed examples of the use of the various meta-criteria.},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
NUMBER = {COSY-DP-0701}
}
@MISC{Sloman:2007d,
AUTHOR = {Aaron Sloman},
TITLE = {{Requirements for Digital Companions: It's harder than you think}},
MONTH = {October},
YEAR = {2007},
NOTE = {Position Paper for Workshop on Artificial Companions in Society:
Perspectives on the Present and Future Organised by the Companions
project. Oxford Internet Institute (25th--26th October, 2007) http://www.cs.bham.ac.uk/research/projects/cogaff/07.html\#711},
ABSTRACT = {Presenting some of the requirements for a truly helpful, as opposed
to merely engaging (or annoying) artificial companion, with arguments
as to why meeting those requirements is way beyond the current state
of the art in AI. },
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
INSTITUTION = {University of Birmingham},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/sloman-oii-2007.pdf}
}
@TECHREPORT{Sloman:2007e,
AUTHOR = {Aaron Sloman},
TITLE = {{Predicting Affordance Changes (Alternatives ways to deal with uncertainty)}},
INSTITUTION = {School of Computer Science, University of Birmingham},
YEAR = {2007},
NUMBER = {COSY-DP-0702},
MONTH = {Nov},
NOTE = {Unpublished discussion paper http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#dp0702
(HTML)},
ABSTRACT = {Discussion of some of the relationships between (a) predicting physical,
topological and geometrical consequences of motions and (b) predicting
the changes in affordances that result from such motions, including
both (b.1.) changes in {\em action affordances} (changes in what
the agent can do in the environment) and (b.2.) changes in {\em epistemic
affordances}, i.e. changes in the information available to the agent
or changes in the ease of planning or deciding. It is suggested that
in some circumstances the predictions can be based on processes operating
on selected fragments of a 2-D representation of a 3-D scene (or
a 2.5-D representation when occlusion is involved) and reasoning
by manipulating the representation. Moreover, where uncertainty is
a problem for prediction it is often due to the existence of a ``phase
boundary'' between configurations where the prediction definitely
gives one result and configurations where the prediction definitely
gives another result. One way of reducing uncertainty is move an
object (or even the viewing position) away from such a phase boundary.
This sometimes allows simple, deterministic, geometric reasoning
to be used, instead of much more complex and unreliable reasoning
with probability distributions and expected utilities.},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab}
}
@MISC{Sloman:2007f,
AUTHOR = {Aaron Sloman},
TITLE = {{Why symbol-grounding is both impossible and unnecessary, and why
theory-tethering is more powerful anyway.}},
YEAR = {2007},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cogaff/talks/\#models},
ABSTRACT = {Introduction to key ideas of semantic models, implicit definitions
and symbol tethering through theory tethering, providing a criticism
concept empiricism, including its recently revived version, ``symbol
grounding theor''. The idea of an axiom system having some models
is explained, showing how the structure of a theory can give some
semantic content to undefined symbols in that theory, making it unnecessary
for all meanings to be derived bottom up from (grounded in) sensory
experience, or sensory-motor contingencies. Although symbols need
not be grounded, since they are mostly defined by the theory in which
they are used, the theory does need to be ``tethered'', if it is
to be capable of being used for predicting and explaining things
that happen, or making plans for acting in the real world. These
ideas were quite well developed by 20th Century philosophers of science,
and I now both attempt to generalise those ideas to be applicable
to theories expressed using non-logical representations (e.g. maps,
diagrams, working models, etc.) and begin to show how they can be
used in explaining how a baby or a robot, can develop new concepts
that have some semantic content but are not definable in terms of
previously understood concepts. There is still much work to be done,
but what needs to be done to explain how intelligent robots might
work, and how humans and other intelligent animals learn about the
environment, is very different from most of what is going on in robotics
and in child and animal psychology. The addition of new explanatory
hypotheses is abduction. Normally abduction uses pre-existing symbols.
The simultaneous introduction of new symbols and new axioms (ontology-extending
abduction) generates a very difficult problem of controlling search.},
ADDRESS = {Birmingham, UK},
DATE-ADDED = {2009-01-06 09:02:20 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
INSTITUTION = {School of Computer Science, University of Birmingham},
KEYWORDS = {cosy; irlab},
NUMBER = {COSY-DP-0605},
TYPE = {Research Note},
URL = {http://www.cognitivesystems.org/publications/models.pdf}
}
@MISC{Sloman:2007g,
AUTHOR = {Aaron Sloman},
TITLE = {{What evolved first and develops first in children: Languages for
communicating? or Languages for thinking? (Generalised Languages:
GLs)}},
YEAR = {2007},
NOTE = {Presentation given to Birmingham Psychology department. http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#pr0702},
ABSTRACT = {Investigating the evolution of cognition requires an understanding
of how to design working cognitive systems since there is very little
direct evidence (no fossilised behaviours or thoughts). That claim
is illustrated in relation to theories about the evolution of language.
Almost everyone seems to have got things badly wrong by assuming
that language must have started as primitive communication between
individuals that gradually got more complex, and then later somehow
got absorbed into cognitive systems. An alternative theory is presented
here, namely that generalised languages (GLs) supporting (a) structural
variability, (b) compositional semantics (generalised to include
both diagrammatic syntaxes and contextual influences on semantics
at every level) and (c) manipulability for reasoning, evolved {\em
first} for various kinds of 'thinking', i.e. internal information
processing. This is incosistent with many theories of the evolution
of language. It is also inconsistent with Dennett's account of the
evolution of consciousness in {\em Content and Consciousness} (1969).},
ADDRESS = {Birmingham, UK},
DATE-ADDED = {2009-01-06 08:59:53 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
INSTITUTION = {School of Computer Science, University of Birmingham},
KEYWORDS = {cosy; irlab},
NUMBER = {COSY-PR-0702},
URL = {http://www.cognitivesystems.org/publications/glang-evo-ai1.pdf}
}
@TECHREPORT{Sloman:2006c,
AUTHOR = {Aaron Sloman},
TITLE = {{Requirements for a Fully Deliberative Architecture (Or component
of an architecture)}},
INSTITUTION = {School of Computer Science, University of Birmingham},
YEAR = {2006},
TYPE = {Research Note},
NUMBER = {COSY-DP-0604},
ADDRESS = {Birmingham, UK},
MONTH = {May},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#dp0604},
ABSTRACT = { For some decades, researchers in AI and Cognitive Science have talked
about animals or machines as having 'deliberative' capabilities.
In my own work, I have, for 10 years or more, been contrasting 'reactive',
'deliberative' and 'meta-management' (sometimes referred to as 'reflective')
capabilities (categories within which many further subdivisions are
possible). The key feature of a deliberative system is the ability
to represent and reason about, and to compare and evaluate, possible
situations that do not exist, or are not known to exist, either because
they are future possibilities, or because they are remote or hypothetical
possibilities. That ability is analysed in more detail in the paper.
In particular we see a need for a fully deliberative system to be
able to construct representations of possible states of affairs of
varying structure and varying complexity, using at least one formalism
with compositional semantics, in mechanisms that allow two or more
such structures to be constructed, analysed and compared, where the
result of comparing them may be another complex structure describing
the pros and cons. Additional related requirements are described.
Much of this is a presentation of old ideas: going back to work by
Minsky, Evans, Winston, and many others during the 1960s and early
1970s.
Although I have taken all that for granted for many years, gradually
I have come to realise that the ideas are not all widely understood
and the word 'deliberative' is used in different ways, partly because
people have not analysed the variety of cases in a deep way that
is widely shared.
I try to contrast 'fully deliberative' systems with much simpler
kinds of 'proto-deliberative' systems, while allowing for many simpler
cases in between (including intermediate states through which evolutionary
trajectories have passed, and some through which developing individuals
may pass). It is important that in a complex architecture with many
components there are different kinds of subsets, and in my work I
have characterised three (partly overlapping) main subsets, which
differ in their evolutionary history, in their spread amongst other
animals besides humans, and in their functionality (though they may
overlap in the kinds of mechanisms they use).},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/fully-deliberative.html}
}
@TECHREPORT{Sloman:2006d,
AUTHOR = {Aaron Sloman},
TITLE = {{Sensorimotor vs objective contingencies}},
INSTITUTION = {School of Computer Science, University of Birmingham},
YEAR = {2006},
TYPE = {Research Note},
NUMBER = {COSY-DP-0603},
ADDRESS = {Birmingham, UK},
MONTH = {May},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#dp0603},
ABSTRACT = { I have been trying, with limited success, to get people to understand
the importance (for theories of mental processes including learning,
perception, reasoning and communication), of a distinction between
learning about sensorimotor contingencies (concerned with relations
between states, events and processes within an animal or machine)
and learning about objective condition-consequence contingencies
(concerned with relations between states, events and processes in
the environment).
The distinction is important for theories of infant development,
for the design of robots that act in and learn about their environment,
and for philosophical and other theories of embodied cognition.
The document is a discussion note listing some possible reasons why
the different sorts of people fail to appreciate the distinction
(e.g. they are concept empiricists, or they already use the phrase
'sensorimotor' so broadly as to cover both categories, not realising
the importance of the subdivision they are not attending to). Various
examples are presented that illustrate the distinction and its importance.
This elaborates on some of the points made in the discussion document
on 'Orthogonal Recombinable Competences'},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/sensorimotor.html}
}
@MISC{sloman-cosypr0507,
AUTHOR = {Aaron Sloman},
TITLE = {{Perception of structure: Anyone Interested?}},
YEAR = {2005},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#pr0507},
ABSTRACT = {Illustration of some of the requirements for a vision system capable
of being used in a robot that manipulates 3-D objects. The pictures
displayed here are very easy for humans to understand not merely
insofar as they recognise the objects depicted, in spite of poor
quality and poor resolution, but also because humans easily see various
ways in which the objects can and cannot be grasped, and can plan
a sequence of moves to transform one of the configurations presented
into another.},
ADDRESS = {Birmingham, UK},
INSTITUTION = {School of Computer Science, University of Birmingham},
NUMBER = {COSY-PR-0507},
TYPE = {Research Note},
URL = {http://www.cognitivesystems.org/publications/challenge.pdf}
}
@TECHREPORT{Sloman:2005,
AUTHOR = {Aaron Sloman},
TITLE = {{Spatial prepositions as higher order functions: And implications
of Grice's theory for evolution of language.}},
INSTITUTION = {School of Computer Science, University of Birmingham},
YEAR = {2005},
TYPE = {Research Note},
NUMBER = {COSY-DP-0605},
ADDRESS = {Birmingham, UK},
ABSTRACT = {This discussion note suggests that some forms of expression that are
apparently vague, inviting interpretations of their meaning in terms
of probability distributions, would be better construed as having
a different form of semantics, namely specifying an 'higher order'
function from contexts to truth-conditions. So statements made using
them have a two level semantics. The first level specifies the function,
which has to be applied to arguments extracted from the context,
which may be linguistic or non linguistic, including the purpose
of the communication. Then when that function is applied to the arguments
the result is a specification of truth-conditions. This can be extended
to how questions and imperatives using those expressions also need
to be interpreted. I first proposed this sort of interpretation for
'better' in 1969 in How to derive 'Better' from 'is', {\em American
Phil. Quarterly} Vol 6, pp43--52, but I think the phenomenon is much
more common than has been realised. I try to show how the use of
such things can be predicted on the basis of Grice's theory of communication,
and draw some conclusions regarding the evolution of language, and
the relations between linguistic and non-linguistic mental functions.
From this viewpoint, communication is collaborative problem-solving,
not the transmission and decoding of some signal, and the ability
to use a language is just a special case of a more general ability
to solve problems by combining different kinds of competence. This
is related to the amazing invention of a sign language by Nicaraguan
deaf children and to arguments for the evolution of inner structured
languages prior to the evolution of language for communication. This
is a discussion paper and everything is still tentative.},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/spatial-prepositions.html}
}
@TECHREPORT{Sloman/etal:2006c,
AUTHOR = {Aaron Sloman and Jackie Chappell and the CoSy PlayMate team},
TITLE = {{Orthogonal Recombinable Competences Acquired by Altricial Species
(Blankets, string, and plywood)}},
INSTITUTION = {School of Computer Science, University of Birmingham},
YEAR = {2006},
TYPE = {Research Note},
NUMBER = {COSY-DP-0601},
ADDRESS = {Birmingham, UK},
MONTH = {January},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers\#dp0601},
ABSTRACT = { This is part of an attempt to explain why our ability to perceive
and produce processes involving 3-D objects of varying shape was
so important for the evolution of the human mind, at the same time
as pointing out what is wrong with most of the stuff that gets written
about the importance of embodiment.
I suspect this reinvents some of Piaget's ideas. It is consistent
with some of the main themes of McCarthy's 'The Well-Designed Child'.
I have recently (April 2006) discovered many connections with the
book The Infant's World by Philippe Rochat (2001).
The main idea is that children acquire types of information that
are orthogonal insofar as they relate to aspects of things or situations
in the environment that can vary (nearly) independently, e.g. kinds
of stuff things are made of, kinds of local surface features, kinds
of relations between things, kinds of whole objects (composed of
stuff with specific surfaces and parts with multiple relations),
kinds of processes, etc.
The competences are also recombinable insofar as they can be used
in perceiving or producing novel structures and processes. The requirement
for re-use in novel combinations seems to impose strong requirements
on the forms of representation used. The recombination is predictive:
you can imagine many details of the process of trying to put on a
shirt made of paper, or lead, or the process of sitting on a chair
made of butter, even if you have never encountered such a thing.
The competences can involve different levels of abstraction.
E.g. grasping something with your teeth and with finger and thumb
are extremely different as regards sensory input and motor signals.
But an animal that can represent what is common to both has a powerful
re-usable abstraction that can also be applied to grasping done by
another person (e.g. a child who may need help) or grasping done
by machines.
I conclude that the so-called 'mirror neurones' should have been
called 'abstraction neurones', and that might have prevented much
confusion (e.g. about imitation).
Powerful innate mechanisms are needed for acquiring such competences
through play and exploration. Very few species can do it. As far
as I can tell there is nothing in AI that accounts for this, and
no known neural mechanisms. (Data-mining techniques can be viewed
as deriving separate 'competences' from large amounts of data, but
as far as I know those techniques and the forms of representation
chosen are not designed to support creative recombination, like solving
a problem by inventing something new involving previously known kinds
of motion, of shape, and of physical stuff)
I'd be interested to know if there's anything implemented by anyone
in AI that models such learning. I have not yet found AI literature
identifying the problem, though it's possible that I've read something
in the past which I had forgotten.
It's also likely that someone has used a different label for this
notion of orthogonal competences, which is why I failed to find previous
work on this. },
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/orthogonal-competences.html}
}
@TECHREPORT{Sloman/etal:2005b,
AUTHOR = {Aaron Sloman and Cosy-partners},
TITLE = {{CoSy deliverable DR.2.1 Requirements study for representations}},
INSTITUTION = {The University of Birmingham, UK},
YEAR = {2005},
NUMBER = {COSY-TR-0507},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#tr0507},
ABSTRACT = {We report on some of the hard unsolved problems we have identified
on the basis of detailed analysis of some of the processes that will
have to occur when the PlayMate and Explorer robots perform their
tasks. The analysis used our scenario-driven research methodology.
We introduce some preliminary characterisations of the key problems
and some preliminary ideas for dealing with them, inspired in part
by studies of cognition in humans and other animals. We confirm the
conjecture in the CoSy proposal that various kinds of representations
are required for different sorts of sub-mechanisms (including for
instance representations concerned with planning complex sequences
of actions and representations used in producing and controlling
fast and fluent movements). The different representations are in
part related to different ontologies, since different sub-mechanisms
acquire, manipulate and use information about different subject-matter.
A substantial part of this report is therefore concerned with first
draft, incomplete, ontologies that we expect our robots will need,
some parts of which the robots will have to develop for themselves,
especially ontologies concerned with objects and processes that have
quite complex structures involving multi-strand relationships. A
particularly important requirement for a robot with 3-D manipulation
capabilities is the ability to perceive and understand what we have
labelled 'multi-strand' relationships (where multiple parts of complex
objects are related, e.g. edges, corners and faces of two cubes),
which cause {\em multi-strand processes} to occur when objects are
moved, with several different relationships changing in parallel.
Perceiving such processes seems to require something like a simulation
process to occur. Moreover, this needs to happen at different levels
of abstraction concurrently (some continuous, with high or low resolution,
and some discrete capturing 'qualitative' structural changes), for
the same reason as many researchers have claimed that perception
of static scenes involves multiple-levels of abstraction. So we conclude
that our robot is likely to require an architecture and mechanisms
that support several concurrent simulations at different levels of
abstraction, in registration with one another and (where appropriate)
with the sensory data. It seems that a mechanism like this can also
implement some of what is often referred to as spatial or visual
reasoning, and could be relevant to perception and understanding
of affordances. We consider in particular requirements for a pre-linguistic
robot that is capable of perceiving, acting in and to some extent
reasoning about the world before being able to talk about it, and
raise questions about how that might relate to learning that adds
linguistic competence. We note that in animals there is wide variation
between species that start with most of the ontology and representational
competence they will ever need and those that somehow learn or develop
what they need and suggest that further study of those cases may
yield clues regarding options for robots of different kinds. Most
of this work has not yet been published. This is work-in-progress
and much of it remains to be expanded, clarified and polished.},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab}
}
@TECHREPORT{Sridharan/etal:2007,
AUTHOR = {Mohan Sridharan and Nick Hawes and Jeremy Wyatt and Richard Dearden
and Aaron Sloman},
TITLE = {Planning Information Processing and Sensing Actions},
INSTITUTION = {University of Birmingham, School of Computer Science},
YEAR = {2007},
NUMBER = {COSY-TR-0706},
MONTH = {November},
ABSTRACT = { The goal of the CoSy project is to create cognitive robots to serve
as a testbed of theories on how humans work, and to identify problems
and techniques relevant to producing general-purpose human-like domestic
robots. Given the constraints on the resources available at the robot's
disposal and the complexity of the tasks that the robot has to execute
during cognitive interactions with other agents or humans, it is
essential that the robot perform just those tasks that are necessary
for it to achieve its goal. In this paper we describe our attempts
at creating such a system that enables a mobile robot to plan its
information processing and sensing actions. We build on an existing
planning framework, which is based on Continual Planning. Continual
planning combines planning, plan execution and plan monitoring. Unlike
classical planning approaches, here it is not necessary to model
all contingencies in advance -- the agent acts as soon as it has
a feasible plan, in an attempt to gather more information that would
help resolve the uncertainty on the rest of the plan. We describe
how the system addresses challenges such as state representation,
conflict resolution and uncertainty. A few experimental results are
provided to highlight both the advantages and disadvantages of the
current approach, and to motivate directions of further research.
All algorithms are implemented and tested in the playmate scenario.},
DATE-ADDED = {2009-01-05 11:34:05 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/jacobssonetal07binding.pdf}
}
@TECHREPORT{ullah07cold,
AUTHOR = {Ullah, M. M. and Pronobis, A. and Caputo, B. and Luo, J. and Jensfelt,
P.},
TITLE = {The {COLD} Database},
INSTITUTION = {Kungliga Tekniska Hoegskolan, CVAP/CAS},
YEAR = {2007},
NUMBER = {TRITA-CSC-CV 2007:1},
MONTH = {October},
URL = {http://www.cognitivesystems.org/publications/ullah07cold.pdf}
}
@COMMENT{{jabref-meta: selector_publisher:}}
@COMMENT{{jabref-meta: selector_author:}}
@COMMENT{{jabref-meta: selector_journal:}}
@COMMENT{{jabref-meta: selector_keywords:}}
This file has been generated by
bibtex2html 1.79
Print this page
|
