|
|
cosyBib2008.bib
@INPROCEEDINGS{brenner08aamas,
AUTHOR = {Michael Brenner},
TITLE = {Continual Collaborative Planning for Mixed-Initiative Action and
Interaction},
BOOKTITLE = {Proceedings of the 7th International Conference on Autonomous Agents
and Multiagent Systems (AAMAS 2008)},
YEAR = {2008},
URL = {http://www.cognitivesystems.org/publications/brenner-aamas08.pdf}
}
@INPROCEEDINGS{Brenner/Kruijff:2008,
AUTHOR = {Michael Brenner and Ivana Kruijff-Korbayova},
TITLE = {A Continual Multiagent Planning Approach to Situated Dialogue},
BOOKTITLE = {Proceedings of the 12th Workshop on the Semantics and Pragmatics
of Dialogue (LonDial 2008)},
YEAR = {2008},
URL = {http://www.cognitivesystems.org/publications/brenner-kruijff-londial2008.pdf}
}
@ARTICLE{brenner08jaamas,
AUTHOR = {Michael Brenner and Bernhard Nebel},
TITLE = {Continual Planning and Acting in Dynamic Multiagent Environments},
JOURNAL = {Journal of Autonomous Agents and Multiagent Systems},
YEAR = {2008},
URL = {http://www.cognitivesystems.org/publications/brenner-nebel06.pdf}
}
@INPROCEEDINGS{brenner08kr,
AUTHOR = {Patrick Eyerich and Michael Brenner and Bernhard Nebel},
TITLE = {On the Complexity of Planning Operator Subsumption},
BOOKTITLE = {Proceedings of the Eleventh International Conference on Principles
of Knowledge Representation and Reasoning (KR 2008)},
YEAR = {2008},
URL = {http://www.cognitivesystems.org/publications/eyerich-etal-kr2008.pdf}
}
@INPROCEEDINGS{fidler08cvpr,
AUTHOR = {S. Fidler and B. Boben and A. Leonardis},
TITLE = {Similarity-based cross-layered hierarchical representation for object
categorization},
BOOKTITLE = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition},
YEAR = {2008},
ADDRESS = {Alaska, USA},
MONTH = {June},
ABSTRACT = {This paper proposes a new concept in hierarchical representations
that exploits features of different granularity and specificity coming
from all layers of the hierarchy. The concept is realized within
a cross-layered compositional representation learned from the visual
data. We show how similarity connections among discrete labels within
and across hierarchical layers can be established in order to produce
a set of layer-independent shape-terminals, i.e. shapinals. We thus
break the traditional notion of hierarchies and show how the category-specific
layers can make use of all the necessary features stemming from all
hierarchical layers. This, on the one hand, brings higher generalization
into the representation, yet on the other hand, it also encodes the
notion of scales directly into the hierarchy, thus enabling a multi-scale
representation of object categories. By focusing on shape information
only, the approach is tested on the Caltech 101 dataset demonstrating
good performance in comparison with other state-of-the-art methods.},
URL = {http://www.cognitivesystems.org/publications/fidler08cvpr.pdf}
}
@INPROCEEDINGS{Frintrop08a,
AUTHOR = {Simone Frintrop and Patric Jensfelt},
TITLE = {Active Gaze Control for Attentional Visual {SLAM}},
BOOKTITLE = {Proceedings of the International Conference on Robotics and Automation
(ICRA'08)},
YEAR = {2008},
ABSTRACT = {In this paper, we introduce an approach to active camera control for
visual SLAM. Features, detected by a biologically motivated attention
system, are tracked over several frames to determine stable landmarks.
Matching of features to database entries enables global loop closing.
The focus of this paper is the active camera control module, which
supports the system with three behaviours: i) A tracking behaviour
tracks promising landmarks and prevents them from leaving the field
of view. ii) A redetection behaviour directs the camera actively
to regions where landmarks are expected and thus supports loop closing.
iii) Finally, an exploration behaviour investigates regions without
landmarks and enables a more uniform distribution of landmarks. Several
real-world experiments show that the active camera control outperforms
the passive system considerably. },
URL = {http://www.cognitivesystems.org/publications/frintropJensfelt_ICRA2008.pdf}
}
@INPROCEEDINGS{Frintrop08b,
AUTHOR = {Simone Frintrop and Patric Jensfelt},
TITLE = {Attentional Landmarks and Active Gaze Control for Visual {SLAM}},
BOOKTITLE = {IEEE Transactions on Robotics, special Issue on Visual {SLAM}},
YEAR = {2008},
VOLUME = {24},
MONTH = OCT,
ABSTRACT = {This paper is centered around landmark detection, tracking and matching
for visual SLAM (Simultaneous Localization And Mapping) using a monocular
vision system with active gaze control. We present a system specialized
in creating and maintaining a sparse set of landmarks based on a
biologically motivated feature selection strategy. A visual attention
system detects salient features which are highly discriminative,
ideal candidates for visual landmarks which are easy to redetect.
Features are tracked over several frames to determine stable landmarks
and to estimate their 3D position in the environment. Matching of
current landmarks to database entries enables loop closing. Active
gaze control allows us to overcome some of the limitations of using
a monocular vision system with a relatively small field of view.
It supports (i) the tracking of landmarks which enable a better position
estimation, (ii) the exploration of regions without landmarks to
obtain a better distribution of landmarks in the environment, and
(iii) the active redetection of landmarks to enable loop closing
in situations in which a fixed camera fails to close the loop. Several
real-world experiments show that accurate position estimation is
obtained with the presented system and that active camera control
outperforms the passive approach. },
URL = {http://www.cognitivesystems.org/publications/frintropJensfeltTRO2008.pdf}
}
@INPROCEEDINGS{fritz08cvpr,
AUTHOR = {Mario Fritz and Bernt Schiele},
TITLE = {Decomposition, Discovery and Detection of Visual Categories Using
Topic Models},
BOOKTITLE = {Proceedings of CVPR},
YEAR = {2008},
MONTH = JUN,
ABSTRACT = {We present a novel method for the discovery and detection of visual
object categories based on decompositions using topic models. The
approach is capable of learning a compact and low dimensional representation
for multiple visual categories from multiple view points without
labeling of the training instances. The learnt object components
range from local structures over line segments to global silhouette-like
descriptions. This representation can be used to discover object
categories in a totally unsupervised fashion. Furthermore we employ
the representation as the basis for building a supervised multi-category
detection system making efficient use of training examples and outperforming
pure features-based representations. The proposed speed-ups make
the system scale to large databases. Experiments on three databases
show that the approach improves the state-of-the-art in unsupervised
learning as well as supervised detection. In particular we improve
the state-of-the-art on the challenging PASCAL'06 multi-class detection
tasks for several categories.},
URL = {http://www.cognitivesystems.org/publications/cvpr08_mario.pdf}
}
@INPROCEEDINGS{Hawes/etal:2008a,
AUTHOR = {Nick Hawes and Jeremy Wyatt},
TITLE = {Benchmarking The Influence of Information-Processing Architectures
on Intelligent Systems},
BOOKTITLE = {Proceedings of the Robotics: Science \& Systems 2008 Workshop: Experimental
Methodology and Benchmarking in Robotics Research},
YEAR = {2008},
MONTH = {June},
ABSTRACT = {The design of the information-processing architecture used to develop
an intelligent robot plays a significant role in the behaviour of
the final system. In this paper we discuss the possibilities for
benchmarking the influence of architecture designs on intelligent
robots. We separate this problem into two sub-problems: benchmarking
the architecture design and benchmarking the implementation of the
design. For each of these sub-problems we list some design- and run-time
properties that could be investigated. To further demonstrate these
ideas we present some early efforts to benchmark the run-time properties
of a previously developed architecture schema. },
DATE-ADDED = {2009-01-04 20:30:15 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
LOCATION = {Zurich, Switzerland},
URL = {http://www.cognitivesystems.org/publications/haweswyatt08benchmarking.pdf}
}
@INPROCEEDINGS{Hawes/etal:2008,
AUTHOR = {Nick Hawes and Jeremy Wyatt and Aaron Sloman},
TITLE = {Exploring Design Space For An Integrated Intelligent System},
BOOKTITLE = {Research and Development in Intelligent Systems XXV: Proceedings
of AI-2008, The Twenty-eighth SGAI International Conference on Innovative
Techniques and Applications of Artificial Intelligence},
YEAR = {2008},
EDITOR = {Max Bramer and Frans Coenen and Miltos Petridis},
ADDRESS = {Cambridge, England},
MONTH = {December},
PUBLISHER = {Springer},
ABSTRACT = {Understanding the trade-offs available in the design space of intelligent
systems is a major unaddressed element in the study of Artificial
Intelligence. In this paper we approach this problem in two ways.
First, we discuss the development of our integrated robotic system
in terms of its trajectory through design space. Second, we demonstrate
the practical implications of architectural design decisions by using
this system as an experimental platform for comparing behaviourally
similar yet architecturally different systems. The results of this
show that our system occupies a "sweet spot" in design space in terms
of the cost of moving information between processing components.},
DATE-ADDED = {2009-01-04 20:37:48 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cast; cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/hawesetal08ai.pdf}
}
@ARTICLE{Hawes/etal:2009,
AUTHOR = {Nick Hawes and Jeremy Wyatt and Aaron Sloman},
TITLE = {Exploring Design Space For An Integrated Intelligent System},
JOURNAL = {Knowledge-Based Systems},
YEAR = {2009},
ABSTRACT = {Understanding the trade-offs available in the design space of intelligent
systems is a major unaddressed element in the study of Artificial
Intelligence. In this paper we approach this problem in two ways.
First, we discuss the development of our integrated robotic system
in terms of its trajectory through design space. Second, we demonstrate
the practical implications of architectural design decisions by using
this system as an experimental platform for comparing behaviourally
similar yet architecturally different systems. The results of this
show that our system occupies a "sweet spot" in design space in terms
of the cost of moving information between processing components.},
DATE-ADDED = {2009-01-05 12:57:16 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cast; cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/hawesetal08kbs.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{Jacobsson/etal:2008a,
AUTHOR = {Jacobsson, H. and Hawes, N.A. and Kruijff, G.J.M. and Wyatt, J.},
TITLE = {Crossmodal Content Binding in Information-Processing Architectures},
BOOKTITLE = {Proceedings of the 3rd ACM/IEEE International Conference on Human-Robot
Interaction (HRI)},
YEAR = {2008},
ADDRESS = {Amsterdam, The Netherlands},
MONTH = {March},
ABSTRACT = {Operating in a physical context, an intelligent robot faces two fundamental
problems. First, it needs to combine information from its different
sensors to form a representation of the environment that is more
complete than any representation a single sensor could provide. Second,
it needs to combine high-level representations (such as those for
planning and dialogue) with sensory information, to ensure that the
interpretations of these symbolic representations are grounded in
the situated context. Previous approaches to this problem have used
techniques such as (low-level) information fusion, ontological reasoning,
and (high-level) concept learning. This paper presents a framework
in which these, and related approaches, can be used to form a shared
representation of the current state of the robot in relation to its
environment and other agents. Preliminary results from an implemented
system are presented to illustrate how the framework supports behaviours
commonly required of an intelligent robot.},
URL = {http://www.cognitivesystems.org/publications/hri_binding.pdf}
}
@ARTICLE{Kristan2009,
AUTHOR = {Kristan, M. and Per\v{s}, J. and Kova\v{c}i\v{c}, S. and Leonardis,
A.},
TITLE = {A Local-motion-based probabilistic model for visual tracking},
JOURNAL = {Pattern Recognition},
YEAR = {2008},
NOTE = {accepted for publication},
ABSTRACT = {Color-based tracking is prone to failure in situations where visually
similar targets are moving in a close proximity or occlude each other.
To deal with the ambiguities in the visual information, we propose
an additional color-independent visual model based on the target's
local motion. This model is calculated from the optical flow induced
by the target in consecutive images. By modifying a color-based particle
filter to account for the target's local motion, the combined color/local-motion-based
tracker is constructed. We compare the combined tracker to a purely
color-based tracker on a challenging dataset from hand tracking,
surveillance and sports. The experiments show that the proposed local-motion
model largely resolves situations when the target is occluded by,
or moves in front of, a visually similar object.},
URL = {http://www.cognitivesystems.org/publications/MatejKristanPR09.pdf}
}
@INPROCEEDINGS{kristanCVWW08,
AUTHOR = {M. Kristan and D. Sko\v{c}aj and A. Leonardis},
TITLE = {Incremental learning with {G}aussian mixture models},
BOOKTITLE = {Computer Vision Winter Workshop CVWW 2008},
YEAR = {2008},
PAGES = {25-32},
ADDRESS = {Moravske toplice, Slovenia},
MONTH = {February},
ABSTRACT = {In this paper we propose a new incremental estimation of Gaussian
mixture models which can be used for applications of online learning.
Our approach allows for adding new samples incrementally as well
as removing parts of the mixture by the process of unlearning. Low
complexity of the mixtures is maintained through a novel compression
algorithm. In contrast to the existing approaches, our approach does
not require fine-tuning parameters for a specific application, we
do not assume specific forms of the target distributions and temporal
constraints are not assumed on the observed data. The strength of
the proposed approach is demonstrated with an example of online estimation
of a complex distribution, an example of unlearning, and with an
interactive learning of basic visual concepts.},
URL = {http://www.cognitivesystems.org/publications/kristanCVWW08.pdf}
}
@ARTICLE{KristanIMAVIS2008,
AUTHOR = {Kristan, M. and Sko\v{c}aj, D. and Leonardis, A.},
TITLE = {Online Kernel Density Estimation For Interactive Learning},
JOURNAL = {Image and Vision Computing},
YEAR = {2008},
ABSTRACT = {In this paper we propose a Gaussian-kernel-based online kernel density
estimation which can be used for applications of online probability
density estimation and online learning. Our approach generates a
Gaussian mixture model of the observed data and allows online adaptation
from positive examples as well as from the negative examples. The
adaptation from the negative examples is realized by a novel concept
of unlearning in mixture models. Low complexity of the mixtures is
maintained through a novel compression algorithm. In contrast to
the existing approaches, our approach does not require fine-tuning
parameters for a specific application, we do not assume specific
forms of the target distributions and temporal constraints are not
assumed on the observed data. The strength of the proposed approach
is demonstrated with examples of online estimation of complex distributions,
an example of unlearning, and with an interactive learning of basic
visual concepts.},
COMMENT = {submitted for publication}
}
@INPROCEEDINGS{Kruijff/etal:2008,
AUTHOR = {G.J.M. Kruijff and M. Brenner and N.A. Hawes},
TITLE = {Continual Planning for Cross-Modal Situated Clarification in Human-Robot
Interaction},
BOOKTITLE = {Proceedings of the 17th International Symposium on Robot and Human
Interactive Communication (RO-MAN 2008)},
YEAR = {2008},
ADDRESS = {Munich, Germany},
MONTH = {August},
ABSTRACT = {Robots do not fully understand the world they are situated in. This
includes what humans talk to them about. A fundamental problem is
thus how a robot can clarify such a lack of understanding. This paper
addresses the issue of how a robot can create a plan for resolving
a need for clarification. It characterises situated clarification
as an information need which may arise in any sensory-motoric modality
required to interpret the situated context of the robot, or any deliberative
modality referring to that context. It then focuses on how, once
a clarification need has been identified, the robot can create a
plan in which one or more modalities are used to resolve it. Modalities
are involved on the basis of the types of information they can provide.
These information types are identified in the ontologies the modalities
use to interconnect their content with content of other modalities
(via information fusion). We take a continual approach to planning
and execution monitoring. This provides the ability to re-plan depending
on modality availability and success in resolving (part of) a clarification
need. We illustrate the implementation on several examples.},
URL = {http://www.cognitivesystems.org/publications/main.sitclar.roman2008.pdf}
}
@BOOK{Kruijff/etal:2008-ICRA,
TITLE = {Proceedings of the ICRA 2008 Workshop: Social Interaction with Intelligent
Indoor Robots (SI3R)},
PUBLISHER = {ICRA},
YEAR = {2008},
AUTHOR = {G.J.M. Kruijff and H. Zender and M. Hanheide and B. Wrede},
ADDRESS = {Pasadena, CA, USA},
MONTH = {May},
ABSTRACT = {Robots are moving from the factories into our homes. Today, we have
the Roomba. Tomorrow, in 2010, industry aims to give us the first
commercial humanoids. Bringing robots as assistants into homes, offices,
and shopping malls presents serious challenges to human-robot interaction.
Robots will need to assist untrained users. Robots will need to interact
with people in environments that are designed for, and populated
by, humans. This workshop focuses on how robotic systems can be designed
such as to meet these challenges. Make robots adapt to the environment.
Make robots socially acceptable. Make robots fit into the environment,
without the environment needing to be made to fit them.},
URL = {http://www.dfki.de/cosy/www/events/si3r-icra08/}
}
@INPROCEEDINGS{Galvez08a,
AUTHOR = {Dorian G\'alvez L\'opez and Kristoffer Sj\"{o} and Chandana Paul
and Patric Jensfelt},
TITLE = {Hybrid Laser and Vision Based Object Search and Localization},
BOOKTITLE = {Proceedings of the International Conference on Robotics and Automation
(ICRA'08)},
YEAR = {2008},
ABSTRACT = {We describe a method for an autonomous robot to efficiently locate
one or more distinct objects in a realistic environment using monocular
vision. We demonstra te how to efficiently subdivide acquired images
into interest regions for the robot to zoom in on, using receptive
field cooccurrence histograms. Objects are recognized through SIFT
feature matching and the positions of the objects are es timated.
Assuming a 2D map of the robot's surroundings and a set of navigation
nodes betw een which it is free to move, we show how to compute an
efficient sensing plan that allows the robot's camera to cover the
environment, while obeying restrictions on the different objects'
maximum and minimum viewing distances. The approach has been implemented
on a real robotic system and results are prese nted showing its practicability
and the quality of the position estimates obtained.},
URL = {http://www.cognitivesystems.org/publications/galvezetal-icra08.pdf}
}
@ARTICLE{leibe08ivc,
AUTHOR = {Bastian Leibe and Alan Ettlin and Bernt Schiele},
TITLE = {Learning semantic object parts for object categorization},
JOURNAL = {Image Vision Comput.},
YEAR = {2008},
VOLUME = {26},
PAGES = {15--26},
NUMBER = {1},
ABSTRACT = {ppearance-based approaches to object recognition mostly rely on measuring
the visual similarity of objects based on global or local descriptors.
They have shown great success in object identification but often
do not generalize to the more challenging case of object categorization,
where category membership is often decided not only on a level of
appearances, but also on a semantic level. It has been argued that
model-based approaches are better suited to this problem, since they
allow to inject high-level knowledge, for example about the constituting
object parts and possible configurations. Postulating a set of object
parts is problematic, though, since it is not guaranteed that those
parts can be reliably extracted from real-world images. There is
a need for a middle layer, forming an interface between the visual
information readily available from the image and the higher-level
semantic information that can be used by reasoning processes. In
this work, we investigate how such an interface can be learned. As
the appearance of object parts may vary considerably, this cannot
be achieved by relying on visual similarity alone. Rather, this paper
proposes to also use co-location and co-activation, together with
weak top-down constraints, such as alignment, as guiding principles
for learning the appearance of local object parts. The learned structures
generalize beyond the appearance of single objects and often correspond
to semantically plausible object parts, such as wheels, trunks, or
windshields of cars. In a later stage, a Bayesian network of those
extracted structures is used to verify object hypotheses successfully
in difficult scenes.},
ADDRESS = {Newton, MA, USA},
DOI = {http://dx.doi.org/10.1016/j.imavis.2007.08.012},
ISSN = {0262-8856},
PUBLISHER = {Butterworth-Heinemann}
}
@ARTICLE{Leibe05c,
AUTHOR = {B. Leibe and A. Leonardis and B. Schiele},
TITLE = {Robust Object Detection with Interleaved Categorization and Segmentation
},
JOURNAL = {International Journal of Computer Vision},
YEAR = {2008},
PAGES = {259--289},
NUMBER = {1--3},
ABSTRACT = {This paper presents a novel method for detecting and localizing objects
of a visual category in cluttered real-world scenes. Our approach
considers object categorization and figure-ground segmentation as
two interleaved processes that closely collaborate towards a common
goal. As shown in our work, the tight coupling between those two
processes allows them to benefit from each other and improve the
combined performance. The core part of our approach is a highly flexible
learned representation for object shape that can combine the information
observed on different training examples in a probabilistic extension
of the Generalized Hough Transform. The resulting approach can detect
categorical objects in novel images and automatically infer a probabilistic
segmentation from the recognition result. This segmentation is then
in turn used to again improve recognition by allowing the system
to focus its efforts on object pixels and to discard misleading influences
from the background. Moreover, the information from where in the
image a hypothesis draws its support is employed in an MDL based
hypothesis verification stage to resolve ambiguities between overlapping
hypotheses and factor out the effects of partial occlusion.},
URL = {http://www.cognitivesystems.org/publications/fulltext.pdf},
VOL = {77}
}
@INPROCEEDINGS{Lison:2008,
AUTHOR = {P. Lison},
TITLE = {A salience-driven approach to speech recognition for human-robot
interaction},
BOOKTITLE = {Proceedings of the ESSLLI 2008 Student Session},
YEAR = {2008},
ADDRESS = {Hamburg, Germany},
MONTH = {August},
ABSTRACT = {We present an implemented model for speech recognition in natural
en- vironments which relies on contextual information about salient
entities to prime utterance recognition. The hypothesis underlying
our approach is that, in situated human-robot interaction, speech
recognition performance can be significantly en- hanced by exploiting
knowledge about the immediate physical environment and the dialogue
history. To this end, visual salience (objects perceived in the physical
scene) and linguistic salience (previously referred-to objects within
the current dialogue) are integrated into a single cross-modal salience
model. The model is dynamically up- dated as the environment evolves,
and is used to establish expectations about uttered words which are
most likely to be heard given the context. The update is realised
by continously adapting the word-class probabilities specified in
the statistical language model. The present article discusses the
motivations behind our approach, describes our implementation as
part of a distributed, cognitive architecture for mobile robots,
and reports the evaluation results on a test suite.},
URL = {http://www.cognitivesystems.org/publications/situatedASR-ESSLLI08.pdf}
}
@INPROCEEDINGS{Lison/Kruijff:2008,
AUTHOR = {P. Lison and G.J.M. Kruijff.},
TITLE = {Salience-driven Contextual Priming of Speech Recognition for Human-Robot
Interaction},
BOOKTITLE = {Proceedings of ECAI 2008},
YEAR = {2008},
ADDRESS = {Athens, Greece},
MONTH = {July},
ABSTRACT = {The paper presents an implemented model for priming speech recognition,
using contextual information about salient entities. The underlying
hypothesis is that, in human-robot interaction, speech recognition
performance can be improved by exploiting knowledge about the immediate
physical situation and the dialogue history. To this end, visual
salience (objects perceived in the physical scene) and linguistic
salience (objects, events already mentioned in the dialogue) are
integrated into a single cross-modal salience model. The model is
dynamically updated as the environment changes. It is used to establish
expectations about which words are most likely to be heard in the
given context. The update is realised by continuously adapting the
word-class probabilities specified in a statistical language model.
The paper discusses the motivations behind the approach, and presents
the implementation as part of a cognitive architecture for mobile
robots. Evaluation results on a test suite show a statistically significant
improvement of salience-driven priming speech recognition (WER) over
a commercial baseline system.},
URL = {http://www.cognitivesystems.org/publications/main.sitASR.ecai08.pdf}
}
@PHDTHESIS{mozos2008phd,
AUTHOR = {Oscar Martinez Mozos},
TITLE = {Semantic Place Labeling with Mobile Robots},
SCHOOL = {University of Freiburg},
YEAR = {2008},
ADDRESS = {Freiburg, Germany},
MONTH = {July},
FILE = {phd_thesis.pdf:http\://www.informatik.uni-freiburg.de/~omartine/publications/phd_thesis.pdf:PDF}
}
@INPROCEEDINGS{plagemann08ecml,
AUTHOR = {Plagemann, C. and Kersting, K. and Burgard, W.},
TITLE = {Nonstationary Gaussian Process Regression using Point Estimates of
Local Smoothness},
BOOKTITLE = {Proc.~of the European Conference on Machine Learning (ECML)},
YEAR = {2008},
ADDRESS = {Antwerp, Belgium},
ABSTRACT = {Gaussian processes using nonstationary covariance functions are a
powerful tool for Bayesian regression with input-dependent smoothness.
A common approach is to model the local smoothness by a latent process
that is integrated over using Markov chain Monte Carlo approaches.
In this paper, we demonstrate that an approximation that uses the
estimated mean of the local smoothness yields good results and allows
one to employ efficient gradient-based optimization techniques for
jointly learning the parameters of the latent and the observed processes.
Extensive experiments on both synthetic and real-world data, including
challenging problems in robotics, show the relevance and feasibility
of our approach.},
URL = {http://www.cognitivesystems.org/publications/plagemann08ecml.pdf}
}
@INPROCEEDINGS{plagemann08iros,
AUTHOR = {Plagemann, C. and Mischke, S. and Prentice, S. and Kersting, K. and
Roy, N. and Burgard, W.},
TITLE = {Learning Predictive Terrain Models for Legged Robot Locomotion},
BOOKTITLE = {Proc.~of the IEEE/RSJ International Conference on Intelligent Robots
and Systems (IROS)},
YEAR = {2008},
ADDRESS = {Nice, France},
ABSTRACT = {Legged robots require the ability to build accurate models of their
environment in order to plan and execute their actions. We present
a novel, probabilistic terrain model based on Gaussian processes
that can be learned and updated efficiently using sparse approximation
techniques. The major benefit of our model is its ability to predict
elevations at unseen locations more reliably than alternative approaches,
while it also yields estimates of the predictive uncertainties. In
particular, our Gaussian process adapts its covariance to the situation
at hand, allowing more accurate inference of terrain height at points
that have not been directly observed. We show how a conventional
motion planner can use the learned terrain model to to plan a path
to a goal location, using a terrain-specific cost model to accept
or reject candidate footholds. In experiments with a real quadruped
robot equipped with a laser range finder, we demonstrate the usefulness
of our approach and discuss its benefits compared to simpler terrain
models such as elevations grids.},
URL = {http://www.cognitivesystems.org/publications/plagemann08iros.pdf}
}
@INPROCEEDINGS{pronobis08icra,
AUTHOR = {Pronobis, A. and Mart\'{i}nez Mozos, O. and Caputo, B.},
TITLE = {{SVM}-based Discriminative Accumulation Scheme for Place Recognition},
BOOKTITLE = {Proceedings of the IEEE International Conference on Robotics and
Automation (ICRA'08)},
YEAR = {2008},
ADDRESS = {Pasadena, CA, USA},
MONTH = {May},
ABSTRACT = {Integrating information coming from different sensors is a fundamental
capability for autonomous robots. For complex tasks like topological
localization, it would be desirable to use multiple cues, possibly
from different modalities, so to achieve robust performance. This
paper proposes a new method for integrating multiple cues. For each
cue we train a large margin classifier which outputs a set of scores
indicating the confidence of the decision. These scores are then
used as input to a Support Vector Machine, that learns how to weight
each cue, for each class, optimally during training. We call this
algorithm SVM-based Discriminative Accumulation Scheme (SVM-DAS).
We applied our method to the topological localization task, using
vision and laser-based cues. Experimental results clearly show the
value of our approach.},
URL = {http://www.cognitivesystems.org/publications/pronobis08icra.pdf}
}
@INPROCEEDINGS{ridgeCogSys08,
AUTHOR = {B. Ridge and D. Sko\v{c}aj, and A. Leonardis},
TITLE = {A System for Learning Basic Object Affordances using a Self-Organizing
Map},
BOOKTITLE = {International Conference on Cognitive Systems CogSys 2008},
YEAR = {2008},
ADDRESS = {Karlsruhe, Germany},
ABSTRACT = {When a cognitive system encounters particular objects, it needs to
know what effect each of its possible actions will have on the state
of each of those objects in order to be able to make effective decisions
and achieve its goals. Moreover, it should be able to generalize
effectively so that when it encounters novel objects, it is able
to estimate what effect its actions will have on them based on its
experiences with previously encountered similar objects. This idea
is encapsulated by the term “affordance”, e.g. “a ball affords being
rolled to the right when pushed from the left.” In this paper, we
discuss the development of a cognitive vision platform that uses
a robotic arm to interact with household objects in an attempt to
learn some of their basic affordance properties. We outline the various
sensor and effector module competencies that were needed to achieve
this and describe an experiment that uses a self-organizing map to
integrate these modalities in a working affordance learning system.},
URL = {http://www.cognitivesystems.org/publications/ridgeCogSys08.pdf}
}
@INPROCEEDINGS{ridgeEpiRob08,
AUTHOR = {Ridge, B. and Sko\v{c}aj, D and Leonardis, A},
TITLE = {Towards Learning Basic Object Affordances from Object Properties},
BOOKTITLE = {Proceedings of Eight International Conference on Epigenetic Robotics},
YEAR = {2008},
ABSTRACT = {The capacity for learning to recognize and exploit environmental affordances
is an important consideration for the design of current and future
developmental robotic systems. We present a system that uses a robotic
arm, camera systems and self-organizing maps to learn basic affordances
of objects.},
BIBTEX_AGE = {6},
BIBTEX_DATE = {2008-07-30},
URL = {http://www.cognitivesystems.org/publications/ridgeEpiRob08.pdf}
}
@INPROCEEDINGS{schnitzspan08eccv,
AUTHOR = {Paul Schnitzspan and Mario Fritz and Bernt Schiele},
TITLE = {Hierarchical Support Vector Random Fields: Joint Training to Combine
Local and Global Features},
BOOKTITLE = {European Conference on Computer Vision (ECCV)},
YEAR = {2008},
ADDRESS = {Marseille, France},
ABSTRACT = {Recently, impressive results have been reported for the de- tection
of ob jects in challenging real-world scenes. Interestingly however,
the underlying models vary greatly even between the most successful
ap- proaches. Methods using a global feature descriptor (e.g. [1])
paired with discriminative classi?ers such as SVMs enable high levels
of performance, but require large amounts of training data and typically
degrade in the presence of partial occlusions. Local feature-based
approaches (e.g. [2–4]) are more robust in the presence of partial
occlusions but often produce a signi?cant number of false positives.
This paper proposes a novel ap- proach called hierarchical support
vector random ?eld that allows 1) to combine the power of global
feature-based approaches with the ?exibility of local feature-based
methods in one consistent multi-layer framework and 2) to automatically
learn the tradeo? and the optimal interplay between local, semi-local
and global feature contributions. Experiments show that both the
combination of local and global features as well as the joint training
result in improved detection performance on challenging datasets.},
URL = {http://www.cognitivesystems.org/publications/hsvrf.pdf}
}
@INPROCEEDINGS{Sjoe08b,
AUTHOR = {Kristoffer Sj\"o and Chandana Paul},
TITLE = {Object Localization using Bearing Only Visual Detection},
BOOKTITLE = {Proceedings of the 10th International Conference on Intelligent Autonomous
Systems},
YEAR = {2008},
MONTH = {july},
ABSTRACT = {This work demonstrates how an autonomous robotic platform can use
intrinsically noisy, coarse-scale visual methods lacking range information
to produce good estimates of the location of objects, by using a
map space representation for weighting together multiple observations
from different vantage points. As the robot moves through the environment
it acquires visual images which are processed by means of a fast
but noisy visual detection algorithm that gives bearing only information.
The results from the detection are then projected from image space
into map space, where data from multiple viewpoints can intrinsically
combine to yield an increasingly accurate picture of the location
of objects. This method has been implemented and shown to work for
object localization on a real robot. It has also been tested extensively
in simulation, with systematically varied false positive and false
negative detection rates. The results demonstrate that this is a
viable method for object localization, even under a wide range of
sensor uncertainties.},
URL = {http://www.cognitivesystems.org/publications/SjooIAS08.pdf}
}
@INPROCEEDINGS{skocajVISAPP08,
AUTHOR = {D. Sko\v{c}aj and M. Kristan and A. Leonardis},
TITLE = {Continuous Learning of Simple Visual Concepts Using Incremental Kernel
Density Estimation},
BOOKTITLE = {International Conference on Computer Vision Theory and Applications},
YEAR = {2008},
PAGES = {598-604},
ADDRESS = {Funchal, Madeira, Portugal},
MONTH = {January},
ABSTRACT = {In this paper we propose a method for continuous learning of simple
visual concepts. The method continuously associates words describing
observed scenes with automatically extracted visual features. Since
in our setting every sample is labelled with multiple concept labels,
and there are no negative examples, reconstructive representations
of the incoming data are used. The associated features are modelled
with kernel density probability distribution estimates, which are
built incrementally. The proposed approach is applied to the learning
of object properties and spatial relations.},
URL = {http://www.cognitivesystems.org/publications/skocajVISAPP08.pdf}
}
@ARTICLE{skocajIMAVIS08,
AUTHOR = {D. Sko\v{c}aj and A. Leonardis},
TITLE = {Incremental and robust learning of subspace representations},
JOURNAL = {Image vis. comput.},
YEAR = {2008},
VOLUME = {26},
PAGES = {27-38},
NUMBER = {1},
ABSTRACT = {Learning is a fundamental capability of any cognitive system. To enable
efficient operation of a cognitive agent in a real-world environment,
visual learning has to be a continuous and robust process. In this
article, we present a method for subspace learning, which takes these
considerations into account. We present an incremental method, which
sequentially updates the principal subspace considering weighted
influence of individual images as well as individual pixels within
an image. We further extend this approach to enable determination
of consistencies in the input data and imputation of the inconsistent
values using the previously acquired knowledge, resulting in a novel
method for incremental, weighted, and robust subspace learning. We
demonstrate the effectiveness of the proposed concept in several
experiments on learning of object and background representations.},
URL = {http://www.cognitivesystems.org/publications/skocajIMAVIS08.pdf}
}
@INPROCEEDINGS{Sloman:2008c,
AUTHOR = {Aaron Sloman},
TITLE = {{Kantian Philosophy of Mathematics and Young Robots}},
BOOKTITLE = {{Intelligent Computer Mathematics}},
YEAR = {2008},
EDITOR = {Autexier, S. and Campbell, J. and Rubio, J. and Sorge, V. and Suzuki,
M. and Wiedijk, F.},
SERIES = {LLNCS no 5144},
PAGES = {558-573},
ADDRESS = {Berlin/Heidelberg},
MONTH = {July},
PUBLISHER = {Springer},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers\#tr0802},
ABSTRACT = {A child, or young human-like robot of the future, needs to develop
an information-processing architecture, forms of representation,
and mechanisms to support perceiving, manipulating, and thinking
about the world, especially perceiving and thinking about actual
and possible structures and processes in a 3-D environment. The mechanisms
for extending those representations and mechanisms, are also the
core mechanisms required for developing mathematical competences,
especially geometric and topological reasoning competences. Understanding
both the natural processes and the requirements for future human-like
robots requires AI designers to develop new forms of representation
and mechanisms for geometric and topological reasoning to explain
a child's (or robot's) development of understanding of affordances,
and the proto-affordances that underlie them. A suitable multi-functional
self-extending architecture will enable those competences to be developed.
Within such a machine, human-like mathematical learning will be possible.
It is argued that this can support Kant's philosophy of mathematics,
as against Humean philosophies. It also exposes serious limitations
in studies of mathematical development by psychologists.},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
INSTITUTION = {School of Computer Science, University of Birmingham},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/maths-ai-sloman.pdf}
}
@INPROCEEDINGS{Sloman/etal:2008b,
AUTHOR = {Aaron Sloman},
TITLE = {Architectural and Representational Requirements for Seeing Processes,
Proto-affordances and Affordances},
BOOKTITLE = {Logic and Probability for Scene Interpretation },
YEAR = {2008},
EDITOR = {Anthony G. Cohn and David C. Hogg and Ralf M{\"o}ller and Bernd Neumann},
NUMBER = {08091},
SERIES = {Dagstuhl Seminar Proceedings},
ADDRESS = {Dagstuhl, Germany},
PUBLISHER = {Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany},
ABSTRACT = {This paper, combining the standpoints of philosophy and Artificial
Intelligence with theoretical psychology, summarises several decades
of investigation by the author of the variety of functions of vision
in humans and other animals, pointing out that biological evolution
has solved many more problems than are normally noticed. For example,
the biological functions of human and animal vision are closely related
to the ability of humans to do mathematics, including discovering
and proving theorems in geometry, topology and arithmetic. Many of
the phenomena discovered by psychologists and neuroscientists require
sophisticated controlled laboratory settings and specialised measuring
equipment, whereas the functions of vision reported here mostly require
only careful attention to a wide range of everyday competences that
easily go unnoticed. Currently available computer models and neural
theories are very far from explaining those functions, so progress
in explaining how vision works is more in need of new proposals for
explanatory mechanisms than new laboratory data. Systematically formulating
the requirements for such mechanisms is not easy. If we start by
analysing familiar competences, that can suggest new experiments
to clarify precise forms of these competences, how they develop within
individuals, which other species have them, and how performance varies
according to conditions. This will help to constrain requirements
for models purporting to explain how the competences work. For example,
Gibson's theory of affordances needs a number of extensions, including
allowing affordances to be composed in several ways from lower level
proto-affordances. The paper ends with speculations regarding the
need for new kinds of information-processing machinery to account
for the phenomena. },
ANNOTE = {Keywords: Vision, affordances, architectures, development, design
space},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
ISSN = {1862-4405},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/08091.SlomanAaron.Paper.1656.pdf}
}
@INPROCEEDINGS{Sloman:2008d,
AUTHOR = {Aaron Sloman},
TITLE = {{Varieties of Meta-cognition in Natural and Artificial Systems}},
BOOKTITLE = {{Workshop on Metareasoning, AAAI'08 Conference}},
YEAR = {2008},
EDITOR = {M. T. Cox and A. Raja},
PAGES = {12--20},
ADDRESS = {Menlo Park, CA},
PUBLISHER = {AAAI Press},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#tr0803},
ABSTRACT = {Some AI researchers aim to make useful machines, including robots.
Others aim to understand general principles of information-processing
machines whether natural or artificial, often with special emphasis
on humans and human-like systems: They primarily address scientific
and philosophical questions rather than practical goals. However,
the tasks required to pursue scientific and engineering goals overlap
considerably, since both involve building working systems to test
ideas and demonstrate results, and the conceptual frameworks and
development tools needed for both overlap. This paper, partly based
on requirements analysis in the CoSy robotics project, surveys varieties
of meta-cognition and draws attention to some types that appear to
play a role in intelligent biological individuals (e.g. humans) and
which could also help with practical engineering goals, but seem
not to have been noticed by most researchers in the field. There
are important implications for architectures and representations.
},
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-meta-aaai08.pdf}
}
@INCOLLECTION{Sloman:2009a,
AUTHOR = {Aaron Sloman},
TITLE = {{Machines in the Ghost}},
BOOKTITLE = {{Simulating the Mind: A Technical Neuropsychoanalytical Approach}},
PUBLISHER = {Springer},
YEAR = {2009},
EDITOR = {Dietrich, D. and Fodor, G. and Zucker, G. and Bruckner, D.},
PAGES = {124--148},
ADDRESS = {Vienna \& New York},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#tr0702},
ABSTRACT = {This paper summarises ideas I have been working on over the last 35
years or so, about relations between the study of natural minds and
the design of artificial minds, and the requirements for both sorts
of minds. The key idea is that natural minds are information-processing
virtual machines produced by evolution. What sort of information-processing
machine a human mind is requires much detailed investigation of the
many kinds of things minds can do. At present, it is not clear whether
producing artificial minds with similar powers will require new kinds
of computing machinery or merely much faster and bigger computers
than we have now. Some things once thought hard to implement in artificial
minds, such as affective states and processes, including emotions,
can be construed as aspects of the control mechanisms of minds. This
view of mind is largely compatible in principle with psychoanalytic
theory, though some details are very different. The therapeutic aspect
of psychoanalysis is analogous to run-time debugging of a virtual
machine. In order to do psychotherapy well we need to understand
the architecture of the machine well enough to know what sorts of
bugs can develop and which ones can be removed, or have their impact
reduced, and how. Otherwise treatment will be a hit-and-miss affair.
},
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-enf07.pdf}
}
@INCOLLECTION{Sloman:2009b,
AUTHOR = {Aaron Sloman},
TITLE = {{Some Requirements for Human-like Robots: Why the recent over-emphasis
on embodiment has held up progress}},
BOOKTITLE = {{Creating Brain-like Intelligence}},
PUBLISHER = {Springer-Verlag},
YEAR = {2009},
EDITOR = {B. Sendhoff and E. Koerner and O. Sporns and H. Ritter and K. Doya},
PAGES = {248--277},
ADDRESS = {Berlin},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#tr0804},
ABSTRACT = {Some issues concerning requirements for architectures, mechanisms,
ontologies and forms of representation in intelligent human-like
or animal-like robots are discussed. The tautology that a robot that
acts and perceives in the world must be embodied is often combined
with false premises, such as the premiss that a particular type of
body is a requirement for intelligence, or for human intelligence,
or the premiss that all cognition is concerned with sensorimotor
interactions, or the premiss that all cognition is implemented in
dynamical systems closely coupled with sensors and effectors. It
is time to step back and ask what robotic research in the past decade
has been ignoring. I shall try to identify some ma jor research gaps
by a combination of assembling requirements that have been largely
ignored and design ideas that have not been investigated -- partly
because at present it is too difficult to make significant progress
on those problems with physical robots, as too many different problems
need to be solved simultaneously. In particular, the importance of
studying some abstract features of the environment about which the
animal or robot has to learn (extending ideas of J.J.Gibson) has
not been widely appreciated.},
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-honda.pdf}
}
@INCOLLECTION{Sloman:2008a,
AUTHOR = {A. Sloman},
TITLE = {{Putting the Pieces Together Again}},
BOOKTITLE = {{Cambridge Handbook on Computational Psychology}},
PUBLISHER = {Cambridge University Press},
YEAR = {2008},
EDITOR = {Ron Sun},
CHAPTER = {26},
PAGES = {684--709},
ADDRESS = {New York},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cogaff/07.html\#710},
ABSTRACT = {This is a 'preprint' for the final chapter of a Handbook of Computational
Psychology which is currently in press. The differences between this
and the version to be published include British vs American spelling
and punctuation. This version also has a few footnotes that had to
be excluded. For some reason the publisher did not want abstracts
for each chapter, so there is no official abstract. The preprint
version also includes a table of contents for the chapter (copied
below).
Overview Instead of surveying achievements of AI and computational
Cognitive Science as might be expected, this chapter complements
the Editor's review of requirements for work on integrated systems
in Chapter 1, by presenting a personal view of some of the major
unsolved problems, and obstacles to solving them. It attempts to
identify some major gaps, and to explain why progress has been much
slower than many people expected. It also includes some recommendations
for improving progress and for countering the fragmentation and factionalism
of the research community.
It it is relatively easy to identify long term ambitions in vague
terms, e.g. the aim of modelling human flexibility, human learning,
human cognitive development, human language understanding or human
creativity; but taking steps to fulfil the ambitions is fraught with
difficulties. So progress in modelling human and animal cognition
is slow despite many impressive narrow-focus achievements, including
those reported in earlier chapters.
An attempt is made to explain why progress in producing realistic
models of human and animal competences is slow, namely (a) the great
difficulty of the problems, (b) failure to understand the breadth,
depth and diversity of the problems, (c) the fragmentation of the
research community and (d) social and institutional pressures against
risky multi-disciplinary, long-term research. Advances in computing
power, theory and techniques will not suffice to overcome these difficulties.
Partial remedies are offered, namely identifying some of the unrecognised
problems and suggesting how to plan research on the basis of `backward-chaining'
from long term goals, in ways that may, perhaps, help warring factions
to collaborate and provide new ways to select targets and assess
progress. },
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-sunbook.pdf}
}
@INCOLLECTION{Sloman:2009,
AUTHOR = {Aaron Sloman},
TITLE = {{Architectural and representational requirements for seeing processes
and affordances}},
BOOKTITLE = {{Computational Modelling in Behavioural Neuroscience: Closing the
gap between neurophysiology and behaviour.}},
PUBLISHER = {Psychology Press},
YEAR = {2009},
ADDRESS = {London},
ABSTRACT = {This paper, combining the standpoints of philosophy and Artificial
Intelligence with theoretical psychology, summarises several decades
of investigation of the variety of functions of vision in humans
and other animals, pointing out that biological evolution has solved
many more problems than are normally noticed. Many of the phenomena
discovered by psychologists and neuroscientists require sophisticated
controlled laboratory settings and specialised measuring equipment,
whereas the functions of vision reported here mostly require only
careful attention to a wide range of everyday competences that easily
go unnoticed. Currently available computer models and neural theories
are very far from explaining those functions, so progress in explaining
how vision works is more in need of new proposals for explanatory
mechanisms than new laboratory data. Systematically formulating the
requirements for such mechanisms is not easy. If we start by analysing
familiar competences, that can suggest new experiments to clarify
precise forms of these competences, how they develop within individuals,
which other species have them, and how performance varies according
to conditions. This will help to constrain requirements for models
purporting to explain how the competences work. The paper ends with
speculations regarding the need for new kinds of information-processing
machinery to account for the phenomena. },
ANNOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#tr0801},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
EDITORS = {Heinke, D. and Mavritsaki, E.},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/sloman-newmod.pdf}
}
@ARTICLE{Sloman:2008,
AUTHOR = {A. Sloman},
TITLE = {{The Well-Designed Young Mathematician}},
JOURNAL = {Artificial Intelligence},
YEAR = {2008},
VOLUME = {172},
PAGES = {2015--2034},
NUMBER = {18},
NOTE = {http://www.cs.bham.ac.uk/research/projects/cosy/papers/\#tr0807},
ABSTRACT = {This paper complements McCarthy's ``The well designed child'', in
part by putting it in a broader context, a space of sets of requirements
and a space of designs, and in part by relating design features to
development of mathematical competences. I moved into AI hoping to
understand myself, especially hoping to understand how I could do
mathematics. Over the ensuing four decades, my interactions with
AI and other disciplines led to: design-based, cross-disciplinary
investigations of requirements, especial those arising from interactions
with a complex environment; a draft partial ontology for describing
spaces of possible architectures, especially virtual machine architectures;
investigations of how different forms of representation relate to
different functions; analysis of biological nature/nurture tradeoffs
and their relevance to machines; studies of control issues in a complex
architecture; and showing how what can occur in such an architecture
relates to our intuitive concepts of motivation, feeling, preferences,
emotions, attitudes, values, moods, consciousness, etc. I conjecture
that working models of human vision can lead to models of spatial
reasoning that would help to support Kant's view of mathematics by
showing that human mathematical abilities are a natural extension
of abilities produced by biological evolution that are not yet properly
understood, and have barely been noticed by psychologists and neuroscientists.
Some requirements for such models, are described, including aspects
of our ability to interact with complex 3-D structures and processes
that extend Gibson's ideas concerning action affordances, to include
proto-affordances, epistemic affordances and deliberative affordances.
Some of what a child learns about structures and processes starts
as empirical then, as a result of reflective processes, can be recognised
as necessary (e.g., mathematical) truths. These processes normally
develop unnoticed in young children, but provide the basis for much
creativity in behaviour, as well as leading, in some, to development
of an interest in mathematics. We still need to understand what sort
of self-monitoring and self-extending architecture, and what forms
of representation, are required to make this possible. This paper
does not presuppose that all mathematical learners can do logic,
though some fairly general form of reasoning seems to be required.},
DATE-ADDED = {2009-01-04 19:55:40 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
EE = {http://dx.doi.org/10.1016/j.artint.2008.09.004},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/sloman-aij-08.pdf}
}
@INPROCEEDINGS{Sridharan/etal:2008,
AUTHOR = {M. Sridharan and R. Dearden and J. Wyatt},
TITLE = {{E-HiPPo}: {E}xtensions to {H}ierarchical {POMDP}-based {V}isual
{P}lanning on a {R}obot},
BOOKTITLE = {The 27th {PlanSIG} Workshop},
YEAR = {2008},
MONTH = {December 11-12},
ABSTRACT = {One major challenge to the widespread deployment of mobile robots
is the ability to autonomously tailor the sensory processing to the
task on hand. In our prior work \cite{mohan:icaps08}, we proposed
an approach for such general-purpose processing of visual input in
an application domain where a robot and a human jointly converse
about and manipulate objects on a tabletop by processing the regions
of interest (ROIs) in input images. We posed the visual processing
management problem as a partially observable Markov decision problem
(POMDP), and introduced a hierarchical decomposition to make it tractable
to plan with POMDPs. In this paper we analyze and eliminate some
of the limitations of the existing approach. First, in addition to
tackling visual actions that analyze the state of the world represented
by the image, we show how to incorporate actions that can change
the state. Secondly, we show how policy caching can be used to speed
the planning performance and analyse the tradeoff between planning
speed and plan quality.},
ANNOTE = {Extensions to the ICAPS-08 paper...},
BIB2HTML_FUNDING = {CoSy, CogX, Leverhulme},
BIB2HTML_PUBTYPE = {Refereed Workshop},
BIB2HTML_RESCAT = {Vision, Planning, Robotics},
BIBAUTHOR = {smohan},
DATE-ADDED = {2009-01-04 19:57:38 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; planning; vision; irlab},
URL = {http://www.cognitivesystems.org/publications/sridharanetal08ehippo.pdf}
}
@INPROCEEDINGS{Sridharan/etal:2008a,
AUTHOR = {M. Sridharan and J. Wyatt and R. Dearden},
TITLE = {{HiPPo}: {H}ierarchical {POMDP}s for {P}lanning {I}nformation {P}rocessing
and {S}ensing {A}ctions on a {R}obot},
BOOKTITLE = {International Conference on Automated Planning and Scheduling (ICAPS)},
YEAR = {2008},
MONTH = {September 14-18},
ABSTRACT = {Flexible general purpose robots need to tailor their visual processing
to their task, on the fly. We propose a new approach to this within
a planning framework, where the goal is to plan a sequence of visual
operators to apply to the regions of interest (ROIs) in a scene.
We pose the visual processing problem as a Partially Observable Markov
Decision Process (POMDP). This requires probabilistic models of operator
effects to quantitatively capture the unreliability of the processing
actions, and thus reason precisely about trade-offs between plan
execution time and plan reliability. Since planning in practical
sized POMDPs is intractable we show how to ameliorate this intractability
somewhat for our domain by defining a hierarchical POMDP. We compare
the hierarchical POMDP approach with a Continual Planning (CP) approach.
On a real robot visual domain, we show empirically that all the planning
methods outperform naive application of all visual operators. The
key result is that the POMDP methods produce more robust plans than
either naive visual processing or the CP approach. In summary, we
believe that visual processing problems represent a challenging and
worthwhile domain for planning techniques, and that our hierarchical
POMDP based approach to them opens up a promising new line of research.},
ANNOTE = {Well, my first ICAPS paper on POMDP-based planning...},
BIB2HTML_FUNDING = {CoSy, CogX, Leverhulme},
BIB2HTML_PUBTYPE = {Refereed Conference},
BIB2HTML_RESCAT = {Vision, Planning, Robotics},
BIBAUTHOR = {smohan},
DATE-ADDED = {2009-01-04 19:57:34 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; planning; vision; irlab},
URL = {http://www.cognitivesystems.org/publications/sridharanetal08hippo.pdf}
}
@ARTICLE{Stachniss2008,
AUTHOR = {C. Stachniss and O. Martinez Mozos and W. Burgard},
TITLE = {Efficient Exploration of Unknown Indoor Environments using a Team
of Mobile Robots},
JOURNAL = {Annals of Mathematics and Artificial Intelligence},
YEAR = {2008},
VOLUME = {accepted}
}
@INPROCEEDINGS{stark08icvs,
AUTHOR = {Michael Stark and Philipp Lies and Michael Zillich and Jeremy Wyatt
and Bernt Schiele},
TITLE = {Functional Object Class Detection Based on Learned Affordance Cues},
BOOKTITLE = {6th International Conference on Computer Vision Systems (ICVS)},
YEAR = {2008},
MONTH = MAY,
NOTE = {Accepted},
ABSTRACT = {Current approaches to visual object class detection mainly focus on
the recognition of abstract object categories, such as cars, motorbikes,
mugs and bottles. Although these approaches have demonstrated impressive
performance in terms of recognition, their restriction to abstract
categories seems artificial and inadequate in the context of embodied,
cognitive agents. Here, distinguishing objects according to functional
aspects based on object affordances is vital for a meaningful human-machine
interaction. In this paper, we propose a complete system for the
detection of functional object classes, based on a representation
of visually distinct hints on object affordances (affordance cues).
It spans the complete cycle from tutor-driven acquisition of affordance
cues, one-shot learning of corresponding object models, and detecting
novel instances of functional object classes in real images.},
LOCATION = {Santorini, Greece},
URL = {http://www.cognitivesystems.org/publications/stark08icvs.pdf}
}
@INPROCEEDINGS{sturm08icra,
AUTHOR = {Sturm, J. and Plagemann, C. and Burgard, W.},
TITLE = {Unsupervised Body Scheme Learning through Self-Perception},
BOOKTITLE = {Proc.~of the IEEE Int.~Conf.~on Robotics \& Automation (ICRA)},
YEAR = {2008},
PAGES = {3328--3333},
ADDRESS = {Pasadena, CA, USA},
ABSTRACT = {In this paper, we present an approach allowing a robot to learn a
generative model of its own physical body from scratch using self-perception
with a single monocular camera. Our approach yields a compact Bayesian
network for the robot's kinematic structure including the forward
and inverse models relating action commands and body pose. We propose
to simultaneously learn local action models for all pairs of perceivable
body parts from data generated through random ``motor babbling.''
From this repertoire of local models, we construct a Bayesian network
for the full system using the pose prediction accuracy on a separate
cross validation data set as the criterion for model selection. The
resulting model can be used to predict the body pose when no perception
is available and allows for gradient-based posture control. In experiments
with real and simulated manipulator arms, we show that our system
is able to quickly learn compact and accurate models and to robustly
deal with noisy observations.},
URL = {http://www.cognitivesystems.org/publications/sturm08icra.pdf}
}
@INPROCEEDINGS{sturm08rss,
AUTHOR = {Sturm, J. and Plagemann, C. and Burgard, W.},
TITLE = {Adaptive Body Scheme Models for Robust Robotic Manipulation},
BOOKTITLE = {Robotics: Science and Systems (RSS)},
YEAR = {2008},
ADDRESS = {Zurich, Switzerland},
MONTH = {June},
URL = {http://www.cognitivesystems.org/publications/sturm08rss.pdf}
}
@INPROCEEDINGS{sturm08rss-workshop,
AUTHOR = {Sturm, J. and Plagemann, C. and Burgard, W.},
TITLE = {Body Scheme Learning and Life-Long Adaptation for Robotic Manipulation},
BOOKTITLE = {Proceedings of the Workshop on Robot Manipulation at Robotics: Science
and Systems Conference (RSS)},
YEAR = {2008},
ADDRESS = {Zurich, Switzerland},
MONTH = {June},
URL = {http://www.cognitivesystems.org/publications/sturm08rss-workshop.pdf}
}
@BOOK{Thomaz/etal:2008-RSS,
TITLE = {Interactive Robot Learning - RSS 2008 workshop},
YEAR = {2008},
AUTHOR = {A. Lockerd Thomaz and G.J.M. Kruijff and H. Jacobssonn and D. Skocaj},
ADDRESS = {Zurich, Switzerland},
MONTH = {June},
ABSTRACT = {This workshop on Interactive Robot Learning will span the breadth
of research questions at the intersection of Machine Learning and
Human-Robot Interaction. Many future applications for autonomous
robots bring them into human environments as helpful assistants to
untrained users in homes, offices, hospitals, and more. These applica-
tions will often require robots to flexibly adapt to the dynamic
needs of human users. Rather than being pre-programmed at the factory
with a fixed repertoire of skills, these personal robots will need
to be able to quickly learn how to perform new tasks and skills from
natural human instruction. Moreover, it is our belief that people
should not have to learn a new form of interaction in order to teach
these machines, that the robots should be able to take advantage
of communication channels that are natural and intuitive for the
human partner.},
URL = {http://www.cognitivesystems.org/publications/InteractiveRobotLearning2008.pdf}
}
@INBOOK{Triebel2008,
CHAPTER = {Studies in Classification, Data Analysis, and Knowledge Organization},
PAGES = {293-300},
TITLE = {Relational Learning in Mobile Robotics: An Application to Semantic
Labeling of Objects in 2D and 3D Environment Maps},
PUBLISHER = {Springer-Verlag},
YEAR = {2008},
AUTHOR = {R. Triebel and O. Mozos and W. Burgard}
}
@INPROCEEDINGS{ullah08icra,
AUTHOR = {Ullah, M. M. and Pronobis, A. and Caputo, B. and Luo, J. and Jensfelt,
P. and Christensen, H. I.},
TITLE = {Towards Robust Place Recognition for Robot Localization},
BOOKTITLE = {Proceedings of the IEEE International Conference on Robotics and
Automation (ICRA'08)},
YEAR = {2008},
ADDRESS = {Pasadena, CA, USA},
MONTH = {May},
ABSTRACT = {Localization and context interpretation are two key competences for
mobile robot systems. Visual place recognition, as opposed to purely
geometrical models, holds promise of higher flexibility and association
of semantics to the model. Ideally, a place recognition algorithm
should be robust to dynamic changes and it should perform consistently
when recognizing a room (for instance a corridor) in different geographical
locations. Also, it should be able to categorize places, a crucial
capability for transfer of knowledge and continuous learning. In
order to test the suitability of visual recognition algorithms for
these tasks, this paper presents a new database, acquired in three
different labs across Europe. It contains image sequences of several
rooms under dynamic changes, acquired at the same time with a perspective
and omnidirectional camera, mounted on a socket. We assess this new
database with an appearance based algorithm that combines local features
with support vector machines through an ad-hoc kernel. Results show
the effectiveness of the approach and the value of the database.},
URL = {http://www.cognitivesystems.org/publications/ullah08icra.pdf}
}
@INPROCEEDINGS{wojekDAGM08b,
AUTHOR = {Christian Wojek and Gyuri Dork{\'o} and Andre Schulz and Bernt Schiele},
TITLE = {Sliding-Windows for Rapid Object-Class Localization: a Parallel Technique},
BOOKTITLE = {Proceedings of DAGM},
YEAR = {2008},
MONTH = JUN,
ABSTRACT = {This paper presents a fast ob ject-class localization frame- work
implemented on a data parallel architecture currently available in
many recent computers. Our case-study, the implementation of His-
tograms of Oriented Gradients (HOG) descriptors, shows that just
by using this recent programming model we can easily speed up an
original CPU-only implementation by a factor of 24, making it unnecessary
to use early rejection cascades that sacrifice classification performance,
even in real-time conditions. Using recent techniques to program
the Graphics Processing Unit (GPU) allows our method to scale-up
to the latest, as well as to future improvements of the hardware,
and have an expected additional speed-up from 2 to 4 on recent solutions.},
URL = {http://www.cognitivesystems.org/publications/hoggpu.pdf}
}
@INPROCEEDINGS{wojekDAGM08a,
AUTHOR = {Christian Wojek and Bernt Schiele},
TITLE = {A performance evaluation of single and multi-cue people detection},
BOOKTITLE = {Proceedings of DAGM},
YEAR = {2008},
MONTH = JUN,
ABSTRACT = {Over the years a number of powerful people detectors have been proposed.
While it is standard to test complete detectors on publicly available
datasets, it is often unclear how the different components (e.g.
features and classifiers) of the respective detectors compare. Therefore,
this paper contributes a systematic comparison of the most prominent
and successful people detectors. Based on this evaluation we also
propose a new detector that outperforms the state-of-art on the INRIA
person dataset by combining multiple cues.},
URL = {http://www.cognitivesystems.org/publications/detector.pdf}
}
@INPROCEEDINGS{Wyatt/etal:2008,
AUTHOR = {Jeremy Wyatt and Nick Hawes},
TITLE = {Multiple Workspaces as an Architecture for Cognition},
BOOKTITLE = {Proceedings of AAAI 2008 Fall Symposium on Biologically Inspired
Cognitive Architectures},
YEAR = {2008},
NOTE = {To appear},
ABSTRACT = {In this paper we describe insights for theories of natural intelligence
that arise from recent advances in architectures for robot intelligence.
In particular we advocate a sketch theory for the study of both natural
and artificial intelligence that consists of a set of constraints
on architectures. The sketch includes the use of multiple shared
workspaces, parallel asynchronous refinement of shared representations,
statistical integration of evidence within and across modalities,
massively parallel prediction and content addressable memory to allow
binding across workspaces.},
DATE-ADDED = {2009-01-04 20:31:55 +0000},
DATE-MODIFIED = {2009-01-06 09:03:50 +0000},
KEYWORDS = {cosy; irlab},
URL = {http://www.cognitivesystems.org/publications/wyatthawes08bica.pdf}
}
@ARTICLE{zender/etal:2008-ras_fs2hsc,
AUTHOR = {H. Zender and O. Mart\'{\i}nez Mozos and P. Jensfelt and G.J.M. Kruijff
and W. Burgard},
TITLE = {Conceptual Spatial Representations for Indoor Mobile Robots},
JOURNAL = {Robotics and Autonomous Systems},
YEAR = {2008},
VOLUME = {56},
NUMBER = {6},
MONTH = {June},
NOTE = {Special Issue "From Sensors to Human Spatial Concepts"},
ABSTRACT = {We present an approach for creating conceptual representations of
human-made indoor environments using mobile robots. The concepts
refer to spatial and functional properties of typical indoor environments.
Following findings in cognitive psychology, our model is composed
of layers representing maps at different levels of abstraction. The
complete system is integrated in a mobile robot endowed with laser
and vision sensors for place and ob ject recognition. The system
also incorporates a linguistic framework that actively supports the
map acquisition process, and which is used for situated dialogue.
Finally, we discuss the capabilities of the integrated system.},
URL = {http://www.cognitivesystems.org/publications/zender_etal08-ras-aam.pdf}
}
This file has been generated by
bibtex2html 1.79
Print this page
|
