|
|
cosyBib2006.bib
@INPROCEEDINGS{Bertolli06a,
AUTHOR = {Federico Bertolli and Patric Jensfelt and Henrik I. Christensen},
TITLE = {SLAM using Visual Scan-Matching with Distinguishable {3D} Points},
BOOKTITLE = {Proceedings of the International Conference on Intelligent Robots
and Systems (IROS'06)},
YEAR = {2006},
ABSTRACT = {Scan-matching based on data from a laser scanner is frequently used
for mapping and localization. This paper presents an scan-matching
approach based instead on visual information from a stereo system.
The Scale Invariant Feature Transform (SIFT) is used together with
epipolar constraints to get high matching precision between the stereo
images. Calculating the 3D position of the corresponding points in
the world results in a visual scan where each point has a descriptor
attached to it. These descriptors can be used when matching scans
acquired from different positions. Just like in the work with laser
based scan matching a map can be defined as a set of reference scans
and their corresponding acquisition point. In essence this reduces
each visual scan that can consist of hundreds of points to a single
entity for which only the corresponding robot pose has to be estimated
in the map. This reduces the overall complexity of the map. The SIFT
descriptor attached to each of the points in the reference allows
for robust matching and detection of loop closing situations. The
paper presents real-world experimental results from an indoor office
environment.},
URL = {http://www.cognitivesystems.org/publications/fedepaper.pdf}
}
@INPROCEEDINGS{06cvpr,
AUTHOR = {S. Fidler and G. Berginc and A. Leonardis},
TITLE = {Hierarchical Statistical Learning of Generic Parts of Object Structure},
BOOKTITLE = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition},
YEAR = {2006},
PAGES = {182--189},
ADDRESS = {New York, USA},
MONTH = {June},
ABSTRACT = {With the growing interest in object categorization various methods
have emerged that perform well in this challenging task, yet are
inherently limited to only a moderate number of object classes. In
pursuit of a more general categorization system this paper proposes
a way to overcome the computational complexity encompassing the enormous
number of different object categories by exploiting the statistical
properties of the highly structured visual world. Our approach proposes
a hierarchical acquisition of generic parts of object structure,
varying from simple to more complex ones, which stem from the favorable
statistics of natural images. The parts recovered in the individual
layers of the hierarchy can be used in a top-down manner resulting
in a robust statistical engine that could be efficiently used within
many of the current categorization systems. The proposed approach
has been applied to large image datasets yielding important statistical
insights into the generic parts of object structure.},
URL = {http://www.cognitivesystems.org/publications/fidlercvpr06.pdf}
}
@ARTICLE{fidlerPAMI06,
AUTHOR = {Sanja Fidler and Danijel Sko\v{c}aj and Ale\v{s} Leonardis},
TITLE = {Combining Reconstructive and Discriminative Subspace Methods for
Robust Classification and Regression by Subsampling},
JOURNAL = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
YEAR = {2006},
VOLUME = {28},
PAGES = {337-350},
NUMBER = {3},
MONTH = {March},
ABSTRACT = {Linear subspace methods that provide sufficient reconstruction of
the data such as PCA offer an efficient way of dealing with missing
pixels, outliers, and occlusions that often appear in the visual
data. Discriminative methods, such as LDA and CCA, which on the other
hand, are better suited for classification and regression tasks,
are highly sensitive to corrupted data. We present a theoretical
framework for achieving best of both types of methods: an approach
that combines the discrimination power of discriminative methods
with the reconstruction property of reconstructive methods which
enables one to work on subsets of pixels in images, to efficiently
detect and reject the outliers. The proposed approach is therefore
capable of robust classification/regression with a high-breakdown
point. The theoretical results are demonstrated on several computer
vision tasks showing that the proposed approach significantly outperforms
the standard discriminative methods in the case of missing pixels
and images containing occlusions and outliers.},
URL = {http://www.cognitivesystems.org/publications/fidlerPAMI06.pdf}
}
@INPROCEEDINGS{Fritz06a,
AUTHOR = {Mario Fritz and Bernt Schiele},
TITLE = {Towards Unsupervised Discovery of Visual Categories},
BOOKTITLE = {Proceedings of 28th Annual Symposium of the German Association for
Pattern Recognition DAGM06},
YEAR = {2006},
ADDRESS = {Berlin, Germany},
MONTH = SEP,
ABSTRACT = {Recently, many approaches have been proposed for visual ob- ject category
detection. They vary greatly in terms of how much supervision is
needed. High performance ob ject detection methods tend to be trained
in a supervised manner from relatively clean data. In order to deal
with a large number of ob ject classes and large amounts of training
data, there is a clear desire to use as little supervision as possible.
This paper proposes a new approach for unsupervised learning of visual
categories based on a scheme to detect reoccurring structure in sets
of images. The approach finds the locations as well as the scales
of such reoccurring structures in an unsupervised manner. In the
experiments those reoccurring structures correspond to ob ject categories
which can be used to directly learn ob- ject category models. Experimental
results show the effectiveness of the new approach and compare the
performance to previous fully-supervised methods.}
}
@INPROCEEDINGS{Hawes/etal:2006b,
AUTHOR = {Nick Hawes and Aaron Sloman and Jeremy Wyatt},
TITLE = {Requirements \& Designs: Asking Scientific Questions About Architectures},
BOOKTITLE = {Proceedings of AISB'06: Adaptation in Artificial and Biological Systems},
YEAR = {2006},
EDITOR = {Tim Kovacs and James A. R. Marshall},
PAGES = {52-55},
ADDRESS = {Bristol},
MONTH = {April},
PUBLISHER = {The Society for the Study of Artificial Intelligence and the Simulation
of Behaviour},
ABSTRACT = {This paper discusses our views on the future of the field of cognitive
architectures, and how the scien- tific questions that define it
should be addressed. We also report on a set of requirements, and
a related architecture design, that we are currently investigating
as part of the CoSy project.},
DATE-ADDED = {2009-01-05 11:51:05 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/hawesetal06gc5.pdf}
}
@INPROCEEDINGS{Hawes/etal:2006,
AUTHOR = {Nick Hawes and Jeremy Wyatt},
TITLE = {Towards Context-Sensitive Visual Attention},
BOOKTITLE = {Proceedings of the Second International Cognitive Vision Workshop
(ICVW06)},
YEAR = {2006},
EDITOR = {Markus Vincze and Lucas Paletta},
ADDRESS = {Graz, Austria},
MONTH = {May},
ABSTRACT = {In this paper we present a discussion of information processing context
and how we believe a visual attention system should be influenced
by contextual information. We support this argument with a proof-of-concept
design and implementation of a context-sensitive extension to the
Itti & Koch model of visual attention as part of an architecture
for a cognitive system. Our model demonstrates improved performance
in terms of both fixations and processing time on visual search tasks
compared to the non-extended model.},
DATE-ADDED = {2009-01-05 11:50:09 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/haweswyatt06.pdf}
}
@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}
}
@INBOOK{hong08a,
PAGES = {27-46},
TITLE = {Learning Causality and Intentional Actions},
PUBLISHER = {Springer},
YEAR = {2008},
AUTHOR = {S. Hongeng and J. Wyatt},
SERIES = {LNAI: Towards Affordance-Based Robot Control},
ABSTRACT = {Previous research has shown that human actions can be detected by
motion patterns. However, labeling motion patterns is not sufficient
in a cognitive system that requires reasoning about the agent's intentions,
and how the environmental context affects the way an action is performed.
In this paper, we develop a graphical model that captures how the
movements that realize the action vary depending on the situ- ations,
and present statistical learning algorithms. Using ob ject manip-
ulation tasks, we illustrate how a system infers the agent's goals
from visual observation and compare results with findings in psychological
experiments.},
URL = {http://www.cognitivesystems.org/publications/lnai07.pdf}
}
@INPROCEEDINGS{hong06,
AUTHOR = {Somboon Hongeng and Jeremy Wyatt},
TITLE = {Learning Causality and Intention in Human Actions},
BOOKTITLE = {Proceedings of the 6th IEEE-RAS International Conference of Humanoid
Robots (Humanoids'06)},
YEAR = {2006},
MONTH = {December},
PUBLISHER = {IEEE},
ABSTRACT = {Previous research has shown that human actions can be detected by
motion patterns. However, labeling motion patterns is not sufficient
in a cognitive system that requires reasoning about the agent's intentions,
and how the environmental context affects the way an action is performed.
In this paper, we develop a graphical model that captures how the
movements that realize the action vary depending on the situations,
and present statistical learning algorithms. Using object manipulation
tasks, we illustrate how a system infers the agent's goals from visual
observation and compare results with findings in psychological experiments.},
DATE-ADDED = {2009-01-05 11:39:46 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/hongeng_humanoids06.pdf}
}
@INPROCEEDINGS{Kruijff/etal:2006-PIT,
AUTHOR = {Geert-Jan M. Kruijff and John D. Kelleher and Nick Hawes},
TITLE = {Information Fusion For Visual Reference Resolution In Dynamic Situated
Dialogue},
BOOKTITLE = {Perception and Interactive Technologies: International Tutorial and
Research Workshop, PIT 2006},
YEAR = {2006},
EDITOR = {Elisabeth Andre and Laila Dybkjaer and Wolfgang Minker and Heiko
Neumann and Michael Weber},
VOLUME = {4021},
SERIES = {Lecture Notes in Computer Science},
PAGES = {117 -- 128},
ADDRESS = {Kloster Irsee, Germany},
MONTH = {June},
PUBLISHER = {Springer Berlin / Heidelberg},
ABSTRACT = {Human-Robot Interaction (HRI) invariably involves dialogue about objects
in the environment in which the agents are situated. The paper focuses
on the issue of resolving discourse references to such visual objects.
The paper addresses the problem using strategies for intra-modal
fusion (identifying that different occurrences concern the same object),
and inter-modal fusion, (relating object references across different
modalities). Core to these strategies are sensorimotoric coordination,
and ontology-based mediation between content in differentmodalities.
The approach has been fully implemented, and is illustrated with
several working examples.},
DATE-ADDED = {2009-01-05 11:49:48 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
EE = {http://dx.doi.org/10.1007/11768029_12},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/kruijffetal06pit.pdf}
}
@INCOLLECTION{Leibe06b,
AUTHOR = {B. Leibe and A. Leonardis and B. Schiele},
TITLE = {An Implicit Shape Model for Combined Object Categorization and Segmentation},
BOOKTITLE = {Towards Category-Level Object Recognition},
PUBLISHER = {Springer},
YEAR = {2006},
EDITOR = {M. Hebert and J. Ponce and C. Schmid and A. Zisserman},
SERIES = {LNCS},
NOTE = {to appear},
ABSTRACT = {We present a method for object categorization in real-world scenes.
Following a common consensus in the field, we do not assume that
a figure-ground segmentation is available prior to recognition. However,
in contrast to most standard approaches for object class recognition,
our approach automatically segments the object as a result of the
categorization. This combination of recognition and segmentation
into one process is made possible by our use of an Implicit Shape
Model, which integrates both capabilities into a common probabilistic
framework. This model can be thought of as a non-parametric approach
which can easily handle configurations of large numbers of object
parts. In addition to the recognition and segmentation result, it
also generates a per-pixel confidence measure specifying the area
that supports a hypothesis and how much it can be trusted. We use
this confidence to derive a natural extension of the approach to
handle multiple objects in a scene and resolve ambiguities between
overlapping hypotheses with an MDL-based criterion. In addition,
we present an extensive evaluation of our method on a standard dataset
for car detection and compare its performance to existing methods
from the literature. Our results show that the proposed method outperforms
previously published methods while needing one order of magnitude
less training examples. Finally, we present results for articulated
objects, which show that the proposed method can categorize and segment
unfamiliar objects in different articulations and with widely varying
texture patterns, even under significant partial occlusion.}
}
@INPROCEEDINGS{Leibe06c,
AUTHOR = {B. Leibe and K. Mikolajczyk and B. Schiele},
TITLE = {Efficient Clustering and Matching for Object Class Recognition},
BOOKTITLE = {British Machine Vision Conference (BMVC'06)},
YEAR = {2006},
ABSTRACT = {In this paper we address the problem of building object class representations
based on local features and fast matching in a large database. We
propose an efficient algorithm for hierarchical agglomerative clustering.
We examine different agglomerative and partitional clustering strategies
and compare the quality of obtained clusters. Our combination of
partitional-agglomerative clustering gives significant improvement
in terms of efficiency while maintaining the same quality of clusters.
We also propose a method for building data structures for fast matching
in high dimensional feature spaces. These improvements allow to deal
with large sets of training data typically used in recognition of
multiple object classes.},
OPTADDRESS = {Edinburgh, UK},
OPTMONTH = {Sept.}
}
@INPROCEEDINGS{Leibe06d,
AUTHOR = {B. Leibe and K. Mikolajczyk and B. Schiele},
TITLE = {Segmentation Based Multi-Cue Integration for Object Detection},
BOOKTITLE = {British Machine Vision Conference (BMVC'06)},
YEAR = {2006},
ABSTRACT = {This paper proposes a novel method for integrating multiple local
cues, i.e. local region detectors as well as descriptors, in the
context of object detection. Rather than to fuse the outputs of several
distinct classifiers in a fixed setup, our approach implements a
highly flexible combination scheme, where the contributions of all
individual cues are flexibly recombined depending on their explanatory
power for each new test image. The key idea behind our approach is
to integrate the cues over an estimated top-down segmentation, which
allows to quantify how much each of them contributed to the object
hypothesis. By combining those contributions on a per-pixel level,
our approach ensures that each cue only contributes to object regions
for which it is confident and that potential correlations between
cues are effectively factored out. Experimental results on several
benchmark data sets show that the proposed multi-cue combination
scheme significantly increases detection performance compared to
any of its constituent cues alone. Moreover, it provides an interesting
evaluation tool to analyze the complementarity of local feature detectors
and descriptors.},
OPTADDRESS = {Edinburgh, UK},
OPTMONTH = {Sept.}
}
@INPROCEEDINGS{mozos2006iros,
AUTHOR = {Mart\'{i}nez Mozos, O. and Burgard, W.},
TITLE = {Supervised Learning of Topological Maps using Semantic Information
Extracted from Range Data},
BOOKTITLE = {Proc.~of the IEEE/RSJ International Conference on Intelligent Robots
and Systems (IROS)},
YEAR = {2006},
PAGES = {2772-2777},
ADDRESS = {Beijing, China},
ABSTRACT = { This paper presents an approach to create topological maps from geometric
maps obtained with a mobile robot in an indoor-environment using
range data. Our approach uses AdaBoost, a supervised learning algorithm,
to classify each point of the geometric map into semantic classes.
We then apply a segmentation procedure based on probabilistic relaxation
labeling on the resulting classications to eliminate errors. The
topological graph is then extracted from the individual di erent
regions and their connections. In this way, we obtain a topological
map in the form of a graph, in which each node indicates a region
in the environment with its corresponding semantic class (e.g., corridor,
or room) and the edges indicate the connections between them. Experimental
results obtained with data from di erent real-world environments
demonstrate the effectiveness of our approach.},
URL = {http://www.cognitivesystems.org/publications/mozos2006iros.pdf}
}
@INPROCEEDINGS{mozos/etal:2006,
AUTHOR = {Mart\'{i}nez Mozos, O. and Rottmann, A. and Triebel, R. and Jensfelt,
P. and Burgard, W.},
TITLE = {Semantic Labeling of Places using Information Extracted from Laser
and Vision Sensor Data},
BOOKTITLE = {In Proc.~of the IEEE/RSJ IROS 2006 Workshop: From Sensors to Human
Spatial Concepts},
YEAR = {2006},
ADDRESS = {Beijing, China},
ABSTRACT = {Indoor environments can typically be divided into places with different
functionalities like corridors, kitchens, offices, or seminar rooms.
The ability to learn such semantic categories from sensor data enables
a mobile robot to extend the representation of the environment facilitating
the interaction with humans. As an example, natural language terms
like ``corridor" or ``room" can be used to communicate the position
of the robot in a map in a more intuitive way. In this work, we first
propose an approach based on supervised learning to classify the
pose of a mobile robot into semantic classes. Our method uses AdaBoost
to boost simple features extracted from range data and vision into
a strong classifier. We present two main applications of this approach.
Firstly, we show how our approach can be utilized by a moving robot
for an online classification of the poses traversed along its path
using a hidden Markov model. Secondly, we introduce an approach to
learn topological maps from geometric maps by applying our semantic
classification procedure in combination with a probabilistic relaxation
procedure. We finally show how to apply associative Markov networks
(AMNs) together with AdaBoost for classifying complete geometric
maps. Experimental results obtained in simulation and with real robots
demonstrate the effectiveness of our approach in various indoor environments.},
URL = {http://www.cognitivesystems.org/publications/mozos2006iros_w.pdf}
}
@INPROCEEDINGS{Mikolajczyk06c,
AUTHOR = {K. Mikolajczyk and B. Leibe and B. Schiele},
TITLE = {Multiple object class detection with a generative mode},
BOOKTITLE = {Proceedings of International Conference on Computer Vision and Pattern
Recognition 2006},
YEAR = {2006},
ADDRESS = {New York, USA},
MONTH = JUN,
ABSTRACT = {In this paper we propose an approach capable of simultaneous recognition
and localization of multiple object classes using a generative model.
We propose a novel hierarchical representation which allows to represent
individual images as well as various objects classes in a single
similarity invariant model. The recognition method is based on a
codebook representation where appearance clusters built from edge
based features are shared among several object classes. A probabilistic
model based on Bayesian rules allows for reliable detection of various
objects in the same image. The approach is very efficient due to
applied fast clustering and matching method capable of dealing with
millions of high dimensional features. The system shows an excellent
performance on several object categories in wide range of scales,
in-plane rotations, background clutter, and occlusion. The performance
is comparable with state of the art approaches dedicated to single
object classes.}
}
@ARTICLE{Philipona06,
AUTHOR = {David L Philipona and J Kevin O'Regan},
TITLE = {Color naming, unique hues, and hue cancellation predicted from singularities
in reflection properties.},
JOURNAL = {Vis Neurosci},
YEAR = {2006},
VOLUME = {23},
PAGES = {331-9},
NUMBER = {3-4},
ABSTRACT = {Psychophysical studies suggest that different colors have different
perceptual status: red and blue for example are thought of as elementary
sensations whereas yellowish green is not. The dominant account for
such perceptual asymmetries attributes them to specificities of the
neuronal representation of colors. Alternative accounts involve cultural
or linguistic arguments. What these accounts have in common is the
idea that there are no asymmetries in the physics of light and surfaces
that could underlie the perceptual structure of colors, and this
is why neuronal or cultural processes must be invoked as the essential
underlying mechanisms that structure color perception. Here, we suggest
a biological approach for surface reflection properties that takes
into account only the information about light that is accessible
to an organism given the photopigments it possesses, and we show
that now asymmetries appear in the behavior of surfaces with respect
to light. These asymmetries provide a classification of surface properties
that turns out to be identical to the one observed in linguistic
color categorization across numerous cultures, as pinned down by
cross cultural studies. Further, we show that data from psychophysical
studies about unique hues and hue cancellation are consistent with
the viewpoint that stimuli reported by observers as special are those
associated with this singularity-based categorization of surfaces
under a standard illuminant. The approach predicts that unique blue
and unique yellow should be aligned in chromatic space while unique
red and unique green should not, a fact usually conjectured to result
from nonlinearities in chromatic pathways.},
URL = {http://www.cognitivesystems.org/publications/PhiliponaVisNeurosci.pdf}
}
@ARTICLE{Philipona06,
AUTHOR = {David L Philipona and J Kevin O'Regan},
TITLE = {Color naming, unique hues, and hue cancellation predicted from singularities
in reflection properties.},
JOURNAL = {Vis Neurosci},
YEAR = {2006},
VOLUME = {23},
PAGES = {331-9},
NUMBER = {3-4},
ABSTRACT = {Psychophysical studies suggest that different colors have different
perceptual status: red and blue for example are thought of as elementary
sensations whereas yellowish green is not. The dominant account for
such perceptual asymmetries attributes them to specificities of the
neuronal representation of colors. Alternative accounts involve cultural
or linguistic arguments. What these accounts have in common is the
idea that there are no asymmetries in the physics of light and surfaces
that could underlie the perceptual structure of colors, and this
is why neuronal or cultural processes must be invoked as the essential
underlying mechanisms that structure color perception. Here, we suggest
a biological approach for surface reflection properties that takes
into account only the information about light that is accessible
to an organism given the photopigments it possesses, and we show
that now asymmetries appear in the behavior of surfaces with respect
to light. These asymmetries provide a classification of surface properties
that turns out to be identical to the one observed in linguistic
color categorization across numerous cultures, as pinned down by
cross cultural studies. Further, we show that data from psychophysical
studies about unique hues and hue cancellation are consistent with
the viewpoint that stimuli reported by observers as special are those
associated with this singularity-based categorization of surfaces
under a standard illuminant. The approach predicts that unique blue
and unique yellow should be aligned in chromatic space while unique
red and unique green should not, a fact usually conjectured to result
from nonlinearities in chromatic pathways.},
URL = {http://www.cognitivesystems.org/publications/PhiliponaVisNeurosci.pdf}
}
@INPROCEEDINGS{plagemann06euros,
AUTHOR = {Plagemann, C. and Stachniss, C. and Burgard, W.},
TITLE = {Efficient Failure Detection for Mobile Robots using Mixed-Abstraction
Particle Filters},
BOOKTITLE = {European Robotics Symposium 2006},
YEAR = {2006},
EDITOR = {H.I. Christiensen},
VOLUME = {22},
SERIES = {STAR Springer tracts in advanced robotics},
PAGES = {93--107},
PUBLISHER = {Springer-Verlag Berlin Heidelberg, Germany},
ABSTRACT = {In this paper, we consider the problem of online failure detection
and isolation for mobile robots. The goal is to enable a mobile robot
to determine whether the system is running free of faults or to identify
the cause for faulty behavior. In general, failures cannot be detected
by solely monitoring the process model for the error free mode because
if certain model assumptions are violated the observation likelihood
might not indicate a defect. Existing approaches therefore use comparably
complex system models to cover all possible system behaviors. In
this paper, we propose the mixed-abstraction particle filter as an
efficient way of dealing with potential failures of mobile robots.
It uses a hierarchy of process models to actively validate the model
assumptions and distribute the computational resources between the
models adaptively. We present an implementation of our algorithm
and discuss results obtained from simulated and real-robot experiments.},
ISBN = {3-540-32688-X},
URL = {http://www.cognitivesystems.org/publications/plagemann06euros.pdf}
}
@INPROCEEDINGS{pronobis06iros,
AUTHOR = {Pronobis, A. and Caputo, B. and Jensfelt, P. and Christensen, H.
I.},
TITLE = {A Discriminative Approach to Robust Visual Place Recognition},
BOOKTITLE = {Proceedings of the IEEE/RSJ International Conference on Intelligent
Robots and Systems (IROS'06)},
YEAR = {2006},
ADDRESS = {Beijing, China},
MONTH = {October},
ABSTRACT = {An important competence for a mobile robot system is the ability to
localize and perform context interpretation. This is required to
perform basic navigation and to facilitate local specific services.
Usually localization is performed based on a purely geometric model.
Through use of vision and place recognition a number of opportunities
open up in terms of flexibility and association of semantics to the
model. To achieve this the present paper presents an appearance based
method for place recognition. The method is based on a large margin
classifier in combination with a rich global image descriptor. The
method is robust to variations in illumination and minor scene changes.
The method is evaluated across several different cameras, changes
in time-of-day and weather conditions. The results clearly demonstrate
the value of the approach.},
URL = {http://www.cognitivesystems.org/publications/pronobis06iros.pdf}
}
@INPROCEEDINGS{seemann06cvpr,
AUTHOR = {E. Seemann and B. Leibe and B. Schiele},
TITLE = {Multi-Aspect Detection of Articulated Objects},
BOOKTITLE = {Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
2005},
YEAR = {2006},
ADDRESS = {New York, USA},
MONTH = JUN,
ABSTRACT = {A wide range of methods have been proposed to detect and recognize
objects. However, effective and efficient multiviewpoint detection
of objects is still in its infancy, since most current approaches
can only handle single viewpoints or aspects. This paper proposes
a general approach for multi-aspect detection of objects. As the
running example for detection we use pedestrians, which add another
difficulty to the problem, namely human body articulations. Global
appearance changes caused by different articulations and viewpoints
of pedestrians are handled in a unified manner by a generalization
of the Implicit Shape Model [5]. An important property of this new
approach is to share local appearance across different articulations
and viewpoints, therefore requiring relatively few training samples.
The effectiveness of the approach is shown and compared to previous
approaches on two datasets containing pedestrians with different
articulations and from multiple viewpoints.}
}
@INPROCEEDINGS{Seemann06,
AUTHOR = {Edgar Seemann and Bernt Schiele},
TITLE = {Cross-Articulation Learning for Robust Detection of Pedestrians},
BOOKTITLE = {Proceedings of 28th Annual Symposium of the German Association for
Pattern Recognition DAGM06},
YEAR = {2006},
ADDRESS = {Berlin, Germany},
MONTH = SEP,
ABSTRACT = {Recognizing categories of articulated ob jects in real-world scenarios
is a challenging problem for today?s vision algorithms. Due to the
large appearance changes and intra-class variability of these ob
jects, it is hard to define a model, which is both general and discriminative
enough to capture the properties of the category. In this work, we
pro- pose an approach, which aims for a suitable trade-off for this
problem. On the one hand, the approach is made more discriminant
by explic- itly distinguishing typical ob ject shapes. On the other
hand, the method generalizes well and requires relatively few training
samples by cross- articulation learning. The effectiveness of the
approach is shown and compared to previous approaches on two datasets
containing pedestri- ans with different articulations.}
}
@INPROCEEDINGS{skocajCVWW06,
AUTHOR = {D. Sko\v{c}aj and M. Uray and A. Leonardis and H. Bischof},
TITLE = {Why to Combine Reconstructive and Discriminative Information for
Incremental Subspace Learning},
BOOKTITLE = {CVWW 2006 : proceedings of the 11th Computer Vision Winter Workshop},
YEAR = {2006},
PAGES = {52-57},
ADDRESS = {Tel\v{c}, Czech Republic},
MONTH = {February 6-8},
ABSTRACT = {In the paper we propose a novel method for incremental visual learning
by combining reconstructive and discriminative subspace methods.
This is achieved by embedding LDA learning and classification into
the incremental PCA framework. The combined subspace consists of
a truncated PCA subspace and a few additional basis vectors that
encompass the discriminative information, which would be lost by
the discarded principal vectors. As such it contains both sufficient
reconstructive information to enable incremental learning, and the
previously extracted discriminative information to enable efficient
classification as well. We demonstrate that we are able to efficiently
update the current model with new instances of the already learned
classes as well as to introduce new classes.},
URL = {http://www.cognitivesystems.org/publications/skocajCVWW06.pdf}
}
@INPROCEEDINGS{Sloman:2006,
AUTHOR = {A. Sloman},
TITLE = {{Introduction to Symposium GC5: Architecture of Brain and Mind Integrating
high level cognitive processes with brain mechanisms and functions
in a working robot}},
BOOKTITLE = {{Proceedings of the AISB '06 Adaptation in Artificial and Biological
Systems}},
YEAR = {2006},
ADDRESS = {Bristol},
MONTH = {April},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#tr0602},
ABSTRACT = {This symposium is inspired by UKCRC Research Grand Challenge 5: GC5:
Architecture of Brain and Mind. The aim of GC5 is to provoke unified
discussion of long term research goals in AI, Cognitive Science,
and related disciplines, especially goals concerned with giving computers
a useful and general subset of human capabilities, implemented in
a biologically inspired fashion. The symposium can also be seen as
part of a series of related events attempting to promote a high-level
long-term vision of achievable scientific goals of AI/Cognitive Science,
including The DAM (Designing an Mind) Symposium at AISB'00 (Davis,
2005), the Tutorial on Philosophical Foundations of AI at IJCAI'01
(Sloman and Scheutz, 2001), the St. Thomas symposium in 2002 (Minsky
et al., 2004), and the IJCAI'05 Tutorial on Learning and Representation
in Animals and Robots (Sloman and Schiele, 2005). It presents themes
central to the EC-funded Cognitive Systems initiative including the
CoSy project which is part of that initiative, whose members have
helped to organise this symposium, and the euCognition project which
is funding this meeting. A common feature is the focus on scientific
goals rather than useful applications though implementation of working
systems is central to the proposed methodology. This introduction
to the symposium provides some background and highlights some of
the major problems to be overcome. },
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/sloman-aisb06-gc5-intro.pdf}
}
@INPROCEEDINGS{Sloman:2006b,
AUTHOR = {Aaron Sloman},
TITLE = {{Polyflaps as a domain for perceiving, acting and learning in a 3-D
world}},
BOOKTITLE = {{Position Papers for 2006 AAAI Fellows Symposium}},
YEAR = {2006},
ADDRESS = {Menlo Park, CA},
PUBLISHER = {AAAI},
NOTE = {http://www.aaai.org/Fellows/fellows.php and http://www.cognitivesystems.org/publications/Fellows16.pdf},
ABSTRACT = {Test domains for AI can have a deep impact on research. The polyflap
domain is proposed for testing complex AI theories about architectures,
mechanisms and forms of representation involved in features of human
and animal intelligence that evolved to enable perception, action,
and learning in diverse environments containing things that we can
perceive and manipulate, and many complex processes involving objects
that differ in shape, materials, causal properties, and relations
to one another. We need a test environment that is rich enough to
provide some of that variety of structures, processes and affordances,
yet simple enough to be within reach of robotics research in the
not too distant future.},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/Fellows16.pdf}
}
@INPROCEEDINGS{Sloman/etal:2006,
AUTHOR = {Aaron Sloman and Jackie Chappell and The CoSy Team},
TITLE = {{How an animal or robot with 3-D manipulation skills experiences
the world}},
BOOKTITLE = {{The tenth annual meeting of the Association for the Scientific Study
of Consciousness, Oxford}},
YEAR = {2006},
ADDRESS = {Internet},
MONTH = {June},
PUBLISHER = {ASSC},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#pr0602,
Poster for ASSC10, Oxford June 2006. Also at ASSC10 Eprints Archive:
http://eprints.assc.caltech.edu/112/},
ABSTRACT = {This presentation elaborates on
'The substratum of this experience is the mastery of a technique'
(Wittgenstein)
I try to show, with illustrative videos, that many 'techniques' are
implicitly involved in ordinary experiences -- and that the complexities
grow as a child develops, extending its ontology and therefore the
variety of affordances it can experience and use. I point out that
there are two interpretations of sensorimotor contingencies, one
intrasomatic (relating only the contents of sensory and motor signals
at various levels of abstraction) the other extrasomatic (amodal,
objective), referring to an environment that exists independently
of whether and how it is experienced or acted on, and that the latter
provides computational advantages in some cases, supporting a Kantian
rather than a Humean view of knowledge and concepts. This also suggests
a re-interpretation of mirror neurons as 'abstraction neurons'.
What we are conscious of in the environment depends on the ontology
we have available. A child whose ontology does not include the notion
of boundary, or the notion of alignment of boundaries may not be
able to replace a cut-out wooden picture in its recess, even if he
knows which recess it should go in. Careful observation of children
at various stages shows transitions that involve extensions of the
available ontology, which must go along with development of suitable
forms of representation and mechanisms for manipulating them, and
an architecture that combines them all. Thus the substratum of the
more sophisticated child's experience is mastery of many 'techniques',
not just one as implied by Wittgenstein (who probably did not intend
that). It is suggested that there are considerable differences between
precocial species whose competences and architecture are mostly genetically
determined and altricial species that develop most of their own competences
e.g. through playful exploration, driven by meta-level bootstrapping
mechanisms.
Only when I started working in detail on requirements for a human-like
robot able to manipulate 3-D objects using vision and an arm with
gripper did I notice what should have been obvious long before, namely
that structured objects have 'multi-strand' relationships not expressible
simply as R(x, y), because the relation between x and y involves
many relations between parts of x and parts of y.
For a more detailed presentation of the resulting theory see COSY-PR-0505:
A (Possibly) New Theory of Vision (PDF)
Hence, motion of such structured objects involves 'multi-strand'
(concurrent) processes. That is, many relationships change in parallel
-- e.g. faces, edges, corners of one block may all be changing their
relationships to faces edges and corners of another (and things get
more complex when objects are flexible, e.g. your hand peeling a
banana or a sweater being put on a child).
Thus seeing what you are doing in such cases can have a kind of complexity
that appears not to have been noticed previously because of too much
focus on simpler visual tasks like recognition and tracking.
I'll show why we need to postulate mechanisms in which concurrent
processes at different levels of abstraction, in partial registration
with the optic array (NOT the retina, since saccades, etc., occur
frequently) are represented.
Nothing in AI comes close to modelling this, and it seems likely
that it will be hard to explain in terms of known neural mechanisms.
If the opportunity arises I'll try to explain some of the implications
for human development, understanding of causation, and computational
modelling, and spell out requirements to be addressed in future interdisciplinary
research, explaining deep connections with Gibson's notion of affordance,
and its generalisation to 'vicarious affordance'.
The evolution of grasping devices that move independently of eyes
(i.e. hands instead of mouth or beak) had profound implications --
undermining claims about sensory-motor contingencies -- also suggesting
that mirror neurons should have been called 'abstraction neurons'.
Some of the ideas are also sketched here: COSY-DP-0601 'Orthogonal
Competences Acquired by Altricial Species'
A critique of common assumptions about 'sensorimotor contingencies'
is presented, including making a distinction between somatic (internal)
and exosomatic (external) ontologies. Too many people expect too
much to come from the somatic (intrasomatic) variety -- including
knowledge of sensorimotor contingencies, a notion criticised in http://www.cs.bham.ac.uk/research/projects/cosy/papers/#dp0603
Requirements for 'fully deliberative' systems are analysed in http://www.cs.bham.ac.uk/research/projects/cosy/papers/#dp0604
},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/assc10-poster.pdf}
}
@INPROCEEDINGS{Sloman/etal:2006b,
AUTHOR = {Aaron Sloman and Birmingham CoSy Project Team and Jackie Chappell},
TITLE = {{Poster: Acquiring Orthogonal Recombinable Competences}},
YEAR = {2006},
EDITOR = {Harold Bekkering},
ADDRESS = {Radboud University Nijmegen, NL},
MONTH = {April},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#pr0601,
Conference url: http://www.socsci.ru.nl/CogSys2},
ABSTRACT = {A child or baby robot that has to manipulate 3-D objects in its environment
would face a combinatorial explosion if all possible situations have
to be learnt about separately. This could take evolutionary time-scales.
It is conjectured that humans and some other altricial species instead
use innate mechanisms for decomposing situations into components
that can be explicitly learnt about, and stored in such a way that
the competence can be re-used in combination with other learnt competences,
in perceiving novel situations and performing novel actions.
That includes learning about kinds of surface fragments (e.g. varieties
of curvature and surface discontinuities), kinds of surface properties
(e.g. texture, hardness, etc.), kinds of material (rigid, flexible
in different ways), kinds of objects composed of materials and shapes,
kinds of relationships, kinds of changes in relationships, kinds
of causal connections between changes.
These need to be represented in a manner that is independent of precise
sense-data when they are perceived, or sensorimotor contingencies,
so that knowledge about them can be used in planning future actions,
thinking about the past, and comparing actions using different hands,
or hands or mouth in different positions. This implies a use of 'objective'
representations (e.g. of 3-D structure) which can then also be used
in perceiving 'vicarious' affordances (for others).
An implication is that mirror neurons should have been called 'abstraction
neurons'. There are many other implications, for robotics, psychology
and neuroscience. },
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/cogsys2-poster.pdf}
}
@INPROCEEDINGS{Sloman/etal:2006d,
AUTHOR = {Aaron Sloman and Jeremy Wyatt and Nick Hawes and Jackie Chappell
and Geert-Jan M. Kruijff},
TITLE = {Long Term Requirements for Cognitive Robotics},
BOOKTITLE = {Proceedings CogRob2006, The Fifth International Cognitive Robotics
Workshop. The AAAI-06 Workshop on Cognitive Robotics},
YEAR = {2006},
ADDRESS = {Boston, Massachusetts, USA},
MONTH = {July},
ABSTRACT = {This paper discusses some of the long term objectives of cognitive
robotics and some of the requirements for meeting those objectives
that are still a very long way off. These include requirements for
visual perception, for architectures, for kinds of learning, and
for innate competences needed to drive learning and development in
a variety of different environments. The work arises mainly out of
research on requirements for forms of representation and architectures
within the PlayMate scenario, which is a scenario concerned with
a robot that perceives, interacts with and talks about 3-D objects
on a tabletop, one of the scenarios in the EC-funded CoSy Robotics
project.},
DATE-ADDED = {2009-01-05 11:49:29 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cs.bham.ac.uk/~nah/bibtex/papers/slomanetal06cogrob.pdf}
}
@INPROCEEDINGS{stachniss2006icra,
AUTHOR = {Stachniss, C. and Mart\'{i}nez Mozos, O. and Burgard, W.},
TITLE = {Speeding-Up Multi-Robot Exploration by Considering Semantic Place
Information},
BOOKTITLE = {Proc.~of the IEEE Int.~Conf.~on Robotics \& Automation (ICRA)},
YEAR = {2006},
ADDRESS = {Orlando, FL, USA},
ABSTRACT = {In this paper, we consider the problem of exploring an unknown environment
with a team of mobile robots. One of the key issues in multi-robot
exploration is how to assign target locations to the individual robots.
To better distribute the robots over the environment and to avoid
redundant work, we take into account the type of place a potential
target is located in (e.g., a corridor or a room). To determine the
type of a place, we apply a classifier learned with AdaBoost which
additionally considers spatial dependencies between nearby locations.
Our approach to incorporate the type of places in the coordination
of the robots has been implemented and tested in different environments.
The experiments demonstrate that our system effectively distributes
the robots over the environment and allows them to accomplish their
mission faster compared to approaches that ignore the semantic place
labels.},
URL = {http://www.cognitivesystems.org/publications/stachniss2006icra.pdf}
}
This file has been generated by
bibtex2html 1.79
Print this page
|
