|
|
cosyBib2007.bib
@PHDTHESIS{seemann2007phd,
TITLE = {People Detection in Crowded Scenes},
AUTHOR = {Edgar Seemann},
YEAR = {2007},
MONTH = {July},
SCHOOL = {TU Darmstadt},
ADDRESS = {Darmstadt, Germany}
}
@INPROCEEDINGS{arras2007icra,
AUTHOR = {Arras, K. O. and Mart\'{i}nez Mozos, O. and Burgard, W.},
TITLE = {Using Boosted Features for the Detection of People in 2D Range Data},
BOOKTITLE = {Proc.~of the IEEE Int.~Conf.~on Robotics \& Automation (ICRA)},
YEAR = {2007},
ABSTRACT = {This paper addresses the problem of detecting people in two dimensional
range scans. Previous approaches have mostly used pre-defined features
for the detection and tracking of people. We propose an approach
that utilizes a supervised learning technique to create a classifier
that facilitates the detection of people. In particular, our approach
applies AdaBoost to train a strong classifier from simple features
of groups of neighboring beams corresponding to legs in range data.
Experimental results carried out with laser range data illustrate
the robustness of our approach even in cluttered office environments.},
URL = {http://www.informatik.uni-freiburg.de/~omartine/publications/arras2007icra.pdf}
}
@INPROCEEDINGS{ballesta2007robomat,
AUTHOR = {Ballesta, M. and Gil, A. and Mart\'{i}nez Mozos, O. and Reinoso,
O.},
TITLE = {Local Descriptors for Visual SLAM},
BOOKTITLE = {Proc.~of the Workshop on Robotics and Mathematics},
YEAR = {2007},
ADDRESS = {Coimbra, Portugal},
ABSTRACT = {We present a comparison of several local image descriptors in the
context of visual Simultaneous Localization and Mapping (SLAM). In
visual SLAM a set of points in the environment are extracted from
images and used as landmarks. The points are represented by local
descriptors used to resolve the association between landmarks. In
this paper, we study the class separability of several descriptors
under changes in viewpoint and scale. Several experiments were carried
out using sequences of images in 2D and 3D scenes.},
URL = {http://www.informatik.uni-freiburg.de/~omartine/publications/ballesta2007robomat.pdf}
}
@INPROCEEDINGS{brenneretal07ijcai,
AUTHOR = {Brenner, M. and Hawes, N. and Kelleher, J. and Wyatt, J.},
TITLE = {Mediating Between Qualitative and Quantitative Representations for
Task-Orientated Human-Robot Interaction},
BOOKTITLE = {Proc.~of the Twentieth International Joint Conference on Artificial
Intelligence (IJCAI)},
YEAR = {2007},
ADDRESS = {Hyderabad, India},
MONTH = {January},
ABSTRACT = {In human-robot interaction (HRI) it is essential that the robot interprets
and reacts to a human's utterances in a manner that reflects their
intended meaning. In this paper we present a collection of novel
techniques that allow a robot to interpret and execute spoken commands
describing manipulation goals involving qualitative spatial constraints
(e.g. ``put the red ball near the blue cube''). The resulting implemented
system integrates computer vision, potential field models of spatial
relationships, and action planning to mediate between the continuous
real world, and discrete, qualitative representations used for symbolic
reasoning.},
URL = {http://www.cs.bham.ac.uk/~nah/bibtex/papers/brenneretal07ijcai.pdf}
}
@INPROCEEDINGS{sfCVPR07,
AUTHOR = {S. Fidler and A. Leonardis},
TITLE = {Towards Scalable Representations of Object Categories: Learning a
Hierarchy of Parts },
BOOKTITLE = { IEEE Computer Society Conference on Computer Vision and Pattern
Recognition },
YEAR = {2007},
ADDRESS = {Minnesota, USA},
MONTH = {June},
ABSTRACT = {This paper proposes a novel approach to constructing a hierarchical
representation of visual input that aims to enable recognition and
detection of a large number of object categories. Inspired by the
principles of efficient indexing (\emph{bottom-up}), robust matching
(\emph{top-down}), and ideas of compositionality, our approach \emph{learns}
a hierarchy of spatially flexible compositions, i.e. parts, in an
unsupervised, statistics-driven manner. Starting with simple, frequent
features, we learn the statistically most significant compositions
(\emph{parts composed of parts}), which consequently define the next
layer. Parts are learned sequentially, layer after layer, optimally
adjusting to the visual data. Lower layers are learned in a category-independent
way to obtain complex, yet sharable visual building blocks, which
is a crucial step towards a scalable representation. Higher layers
of the hierarchy, on the other hand, are constructed by using specific
categories, achieving a category representation with a small number
of highly generalizable parts that gained their structural flexibility
through composition within the hierarchy. Built in this way, new
categories can be efficiently and continuously added to the system
by adding a small number of parts only in the higher layers. The
approach is demonstrated on a large collection of images and a variety
of object categories. Detection results confirm the effectiveness
and robustness of the learned parts.}
}
@ARTICLE{Folkesson07a,
AUTHOR = {John Folkesson and Patric Jensfelt and Henrik Christensen},
TITLE = {The M-space Feature Representation for SLAM},
JOURNAL = {IEEE Transactions on Robotics},
YEAR = {2007},
VOLUME = {23},
PAGES = {1024--1035},
NUMBER = {5},
MONTH = OCT
}
@INPROCEEDINGS{fritz07,
AUTHOR = {M. Fritz and G-J. M. Kruijff and B. Schiele},
TITLE = {Cross-Modal Learning Of Visual Categories Using Different Levels
of Supervision},
BOOKTITLE = {International Conference on Computer Vision Systems (ICVS), Bielefeld,
Germany},
YEAR = {2007},
MONTH = {March},
URL = {http://www.mis.informatik.tu-darmstadt.de/People/mfritz/fritz07icvs.pdf}
}
@INPROCEEDINGS{Hawes/etal:2007,
AUTHOR = {N. Hawes and A. Sloman and J. Wyatt and M. Zillich and H. Jacobsson
and G.J.M. Kruijff and M. Brenner and G. Berginc and D. Skocaj},
TITLE = {Towards an integrated robot with multiple cognitive functions},
BOOKTITLE = {Proceedings of the 22nd Conference on Artificial Intelligence (AAAI-07)},
YEAR = {2007},
ADDRESS = {Vancouver, Canada}
}
@INPROCEEDINGS{jacobsson+frank+federici_2007_ijcnn,
AUTHOR = {Henrik Jacobsson and Stefan L. Frank and Diego Federici},
TITLE = {Automated Abstraction of Dynamic Neural Systems for Natural Language
Processing},
BOOKTITLE = {Proceedings of International Conference on Neural Networks 2007},
YEAR = {to appear},
ABSTRACT = {This paper presents a variant of the Crystallizing Substochastic Sequential
Machine Extractor (CrySSMEx), an algorithm capable of extracting
finite state descriptions of dynamic systems such as recurrent neural
networks, without any regard to their topology or weights. The algorithm
is applied to a network performing a language prediction task. The
extracted state machines provide a very detailed view of the operations
of the RNN by abstracting and discretizing its functional behaviour.
Here we extend previous work also by extracting state machines in
Moore, rather than in Mealy, format. This subtle difference opens
up the rule extractor to more domains, including sensorimotor modelling
of autonomous robotic systems. Experiments are also conducted on
far more input symbols, providing a greater insight into the behaviour
of the algorithm.},
URL = {http://www.dfki.de/~henrikj/publications/ijcnn2007.pdf}
}
@INPROCEEDINGS{jacobssonLANGRO07,
AUTHOR = {H. Jacobsson and N. Hawes and D. Sko\v{c}aj and GJ Kruijff},
TITLE = {Interactive learning and cross-modal binding - a combined approach},
BOOKTITLE = {Language and robots : proceedings of the symposium},
YEAR = {2007},
PAGES = {53-54},
ADDRESS = {Aveiro, Portugal},
MONTH = {December},
OWNER = {danijels vicos cosy DSSP2},
TIMESTAMP = {2007.12.10},
URL = {http://vicos.fri.uni-lj.si/data/publications/jacobssonLANGRO07.pdf}
}
@INPROCEEDINGS{jacobsson+kruijff+staudte_2007_icra,
AUTHOR = {Henrik Jacobsson and Geert-Jan Kruijff and Maria Staudte},
TITLE = {From Rule Extraction to Active Learning Symbol Grounding},
BOOKTITLE = {Proceedings of {ICRA} 2007 Workshop on Concept Learning for Embodied
Agents},
YEAR = {2007},
ADDRESS = {Rome, Italy},
MONTH = {April},
ABSTRACT = {The paper focuses on a fundamental learning problem in adaptive, embodied
cognitive systems: Namely, how to learn discrete models of situated,
embodied experience which can act as a mediation between sensori-motoric
experience and high-level cognitive processes. The paper suggests
to address the problem using a combination of bottom up active learning
of embodied concepts solely on the basis of the actions and perceptions
of the robot, and top-down information obtained through interaction
with other agents. The embodied concepts are constructed to be informative
for the robot in terms of its sensorimotor prediction capability.
From that point the effort of constructing humanlike concepts is
shifted towards producing a translation between the sensorimotor
based bottom-up ontology and more conventional top-down constructed
ontologies. The suggested framework is based on a parameter free
rule extraction algorithm that successfully has been applied to the
problem of creating finite state descriptions of large, complex and
even chaotic simulated dynamic systems. We will briefly describe
how this algorithm can be ported to an autonomous robot domain.},
URL = {http://www.dfki.de/~henrikj/publications/icra2007.pdf}
}
@INPROCEEDINGS{Jacobsson/etal:2007-pascal,
AUTHOR = {Jacobsson, H. and Kruijff, G.J.M. and Staudte, M.},
TITLE = {Language Acquisition from Neural and Sensorimotor Systems},
BOOKTITLE = {Proceedings of the PASCAL workshop on Machine Learning and Cognitive
Science of Language Acquisition},
YEAR = {2007}
}
@ARTICLE{kersting07ar,
AUTHOR = {Kersting, K. and Plagemann, C. and Cocora, A. and Burgard, W. and
De Raedt, L.},
TITLE = {Learning to Transfer Optimal Navigation Policies},
JOURNAL = {Advanced Robotics. Special Issue on Imitative Robots},
YEAR = {2007},
VOLUME = {21},
NUMBER = {9},
MONTH = {September},
ABSTRACT = {Autonomous agents that act in the real world utilizing sensory input
greatly rely on the ability to plan their actions and to transfer
these skills across tasks. The majority of path planning approaches
for mobile robots, however, solve the current navigation problem
from scratch given the current and goal configuration of the robot.
Consequently, these approaches yield highly efficient plans for the
specific situation, but the computed policies typically do not transfer
to other, similar tasks. In this paper, we propose to apply techniques
from statistical relational learning to the path planning problem.
More precisely, we propose to learn relational decision trees as
abstract navigation strategies from example paths. Relational abstraction
has several interesting and important properties. First, it allows
a mobile robot to imitate navigation behavior shown by users or by
optimal policies. Second, it yields comprehensible models of behavior.
Finally, a navigation policy learned in one environment naturally
transfers to unknown environments. In several experiments with real
robots and in simulated runs, we demonstrate that our approach yields
efficient navigation plans. We show that our system is robust against
observation noise and can outperform hand-crafted policies.},
PDFURL = {http://www.informatik.uni-freiburg.de/~plagem/bib/kersting07ar.pdf}
}
@INPROCEEDINGS{kersting07icml,
AUTHOR = {Kersting, K. and Plagemann, C. and Pfaff, P. and Burgard, W.},
TITLE = {Most Likely Heteroscedastic Gaussian Process Regression},
BOOKTITLE = {International Conference on Machine Learning (ICML)},
YEAR = {2007},
ADDRESS = {Corvallis, Oregon, USA},
MONTH = {March},
ABSTRACT = {This paper presents a novel Gaussian process (GP) approach to regression
with input-dependent noise rates. We follow Goldberg et al.'s approach
and model the noise variance using a second GP in addition to the
GP governing the noise-free output value. In contrast to Goldberg
et al., however, we do not use a Markov chain Monte Carlo method
to approximate the posterior noise variance but a most likely noise
approach. The resulting model is easy to implement and can directly
be used in combination with various existing extensions of the standard
GPs such as sparse approximations. Extensive experiments on both
synthetic and real-world data, including a challenging perception
problem in robotics, show the effectiveness of most likely heteroscedastic
GP regression.},
PDFURL = {http://www.informatik.uni-freiburg.de/~plagem/bib/kersting07icml.pdf}
}
@INPROCEEDINGS{mkBMVC07,
AUTHOR = {M. Kristan and J. Per\v{s} and A. Leonardis and S. Kova\v{c}i\v{c}},
TITLE = {Local-motion-based probabilistic tracking},
BOOKTITLE = {submitted},
YEAR = {2007},
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 color information, we propose
an additional colorindependent feature based on the target’s local
motion. This feature 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 hybrid color/local-motion-based
tracker is constructed. The hybrid tracker was compared to a purely
color-based tracker on a challenging dataset. The experiments show
that the proposed method largely resolves complete occlusions between
visually similar objects.}
}
@INPROCEEDINGS{mkCVWW07,
AUTHOR = {M. Kristan and J. Per\v{s} and A. Leonardis and S. Kova\v{c}i\v{c}},
TITLE = {Probabilistic tracking using optical flow to resolve color ambiguities},
BOOKTITLE = {Computer Vision Winter Workshop 2007},
YEAR = {2007},
ADDRESS = {St. Lambrecht, Austria},
MONTH = {February},
ABSTRACT = {Color-based tracking is prone to failure in situations where visually
similar targets are moving in close proximity to each other. To deal
with the ambiguities in color information we propose an additional
color-independent feature based on the target’s local motion, which
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 hybrid color/local-motion-based tracker
is constructed. The hybrid tracker was compared to a purely color-based
tracker on a challenging data-set that involved near-collisions and
complete occlusions between visually similar persons. The optical
flow was estimated using a robust and a nonrobust method. The experiments
show that even if a nonrobust method is used to estimate the optical
flow, the local-motion feature largely resolves ambiguities caused
by the visual similarity between persons..},
URL = {http://www.cognitivesystems.org/publications/uol_mk_cvww07.pdf}
}
@INPROCEEDINGS{Kruijff/Brenner:2007,
AUTHOR = {G.J.M. Kruijff and M. Brenner},
TITLE = {Modelling Spatio-Temporal Comprehension in Situated Human-Robot Dialogue
as Reasoning about Intentions and Plans},
BOOKTITLE = {Proceedings of the Symposium on Intentions in Intelligent Systems},
YEAR = {2007},
ADDRESS = {Stanford University, Palo Alto, CA, USA},
MONTH = {March},
PUBLISHER = {AAAI Spring Symposium Series 2007}
}
@INPROCEEDINGS{Kruijff/etal:2007-sitdial,
AUTHOR = {G.J.M. Kruijff and P. Lison and T. Benjamin and H. Jacobsson and
N. Hawes},
TITLE = {Incremental, multi-level processing for comprehending situated dialogue
in human-robot interaction},
BOOKTITLE = {Language and Robots: Proceedings from the Symposium (LangRo'2007)},
YEAR = {2007},
ADDRESS = {Aveiro, Portugal},
MONTH = {December}
}
@INPROCEEDINGS{Kruijff/Staudte:2007,
AUTHOR = {G.J.M. Kruijff and M. Staudte},
TITLE = {Producing believeable robot gaze when comprehending visually situated
dialogue},
BOOKTITLE = {Language and Robots: Proceedings from the Symposium (LangRo'2007)},
YEAR = {2007},
ADDRESS = {Aveiro, Portugal},
MONTH = {December}
}
@ARTICLE{Kruiff07a,
AUTHOR = {Geert-Jan M. Kruijff and Hendrik Zender and Patric Jensfelt and Henrik
I. Christensen},
TITLE = {Situated Dialogue and Spatial Organization: What, Where\ldots and
Why?},
JOURNAL = {International Journal of Advanced Robotic Systems},
YEAR = {2007},
VOLUME = {4},
NUMBER = {2},
URL = { http://www.dfki.de/~zender/publications/kruijff_etal07-jars.pdf}
}
@INPROCEEDINGS{lang07rss,
AUTHOR = {Lang, T. and Plagemann, C. and Burgard, W.},
TITLE = {Adaptive Non-Stationary Kernel Regression for Terrain Modeling},
BOOKTITLE = {Robotics: Science and Systems (RSS)},
YEAR = {2007},
ADDRESS = {Atlanta, Georgia, USA},
MONTH = {June},
ABSTRACT = {Three-dimensional digital terrain models are of fundamental importance
in many areas such as the geo-sciences and outdoor robotics. Accurate
modeling requires the ability to deal with a varying data density
and to balance smoothing against the preservation of discontinuities.
The latter is particularly important for robotics applications, as
discontinuities that arise, for example, at steps, stairs, or building
walls are important features for path planning or terrain segmentation
tasks. In this paper, we present an extension of the well-established
Gaussian process regression technique, that utilizes non-stationary
covariance functions to locally adapt to the structure of the terrain
data. In this way, we achieve strong smoothing in flat areas and
along edges and at the same time preserve edges and corners. The
derived model yields predictive height distributions for arbitrary
locations of the terrain and therefore allows us to fill gaps in
data and to perform conservative predictions in occluded areas.},
PDFURL = {http://www.informatik.uni-freiburg.de/~plagem/bib/lang07rss.pdf}
}
@INPROCEEDINGS{alISSR07,
AUTHOR = {Ales Leonardis and Sanja Fidler},
TITLE = {Learning hierarchical representations of object categories for robot
vision},
BOOKTITLE = {13th International Symposium of Robotics Research, (ISRR 2007)},
YEAR = {2007},
ADDRESS = {Hiroshima, JAPAN},
NOTE = {Invited talk},
ABSTRACT = {This paper presents our recently developed approach to constructing
a hierarchical representation of visual input that aims to enable
recognition and detection of a large number of object categories.
Inspired by the principles of efficient indexing, robust matching,
and ideas of compositionality, our approach learns a hierarchy of
spatially flexible compositions, i.e. parts, in an unsupervised,
statistics-driven manner. Starting with simple, frequent features,
we learn the statistically most significant compositions (parts composed
of parts), which consequently define the next layer. Parts are learned
sequentially, layer after layer, optimally adjusting to the visual
data. Lower layers are learned in a category-independent way to obtain
complex, yet sharable visual building blocks, which is a crucial
step towards a scalable representation. Higher layers of the hierarchy,
on the other hand, are constructed by using specific categories,
achieving a category representation with a small number of highly
generalizable parts that gained their structural flexibility through
composition within the hierarchy. Built in this way, new categories
can be efficiently and continuously added to the system by adding
a small number of parts only in the higher layers. The approach is
demonstrated on a large collection of images and a variety of object
categories.},
URL = {http://vicos.fri.uni-lj.si/data/alesl/isrr07LeonardisFidler.pdf}
}
@INPROCEEDINGS{Looije/etal:2007,
AUTHOR = {R. Looije and M. Neerincx and G.J.M. Kruijff},
TITLE = {Affective Collaborative Robots for Safety \& Crisis Management in
the Field},
BOOKTITLE = {Proceedings of the 4th International Conference on Information Systems
for Crisis Response and Management (ISCRAM 2007)},
YEAR = {2007},
ADDRESS = {Delft, The Netherlands},
MONTH = {May}
}
@INPROCEEDINGS{luo07iros,
AUTHOR = {Luo, J. and Pronobis, A. and Caputo, B. and Jensfelt, P.},
TITLE = {Incremental Learning for Place Recognition in Dynamic Environments},
BOOKTITLE = {Proceedings of the IEEE/RSJ International Conference on Intelligent
Robots and Systems (IROS07)},
YEAR = {2007},
ADDRESS = {San Diego, CA, USA},
MONTH = {October},
URL = {http://www.csc.kth.se/~pronobis/research/luo07iros/luo07iros.pdf}
}
@ARTICLE{mozos2007ras,
AUTHOR = {Mart\'{i}nez Mozos, O. and Triebel, R. and Jensfelt, P. and Rottmann,
A. and Burgard, W.},
TITLE = {Supervised semantic labeling of places using information extracted
from sensor data},
JOURNAL = {Robotics and Autonomous Systems},
YEAR = {2007},
VOLUME = {55},
PAGES = {391--402},
NUMBER = {5},
MONTH = {May},
ABSTRAC = {Indoor environments can typically be divided into places with different
functionalities like corridors, rooms or doorways. 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 sensor range data 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. In this case we additionally use as
features objects extracted from images. Secondly, we introduce an
approach to learn topological maps from geometric maps by applying
our semantic classification procedure in combination with a probabilistic
relaxation method. Alternatively, we apply associative Markov networks
to classify geometric maps and compare the results with the relaxation
approach. Experimental results obtained in simulation and with real
robots demonstrate the effectiveness of our approach in various indoor
environments.},
URL = {http://www.informatik.uni-freiburg.de/~omartine/publications/mozos2007RAS.pdf}
}
@INPROCEEDINGS{mozos2007icra_workshop,
AUTHOR = {\'{O}scar Mart\'{i}nez Mozos and Patric Jensfelt and Hendrik Zender
and Geert-Jan M. Kruijff and Wolfram Burgard},
TITLE = {From Labels to Semantics: An Integrated System for Conceptual Spatial
Representations of Indoor Environments for Mobile Robots},
BOOKTITLE = {Proc. of the IEEE ICRA 2007 Workshop: Semantic information in robotics
(ICRA)},
YEAR = {2007},
ADDRESS = {Roma, Italy},
ABSTRACT = {We present an integrated approach for creating conceptual representations
of human-made environments using mobile robots. The concepts represent
spatial and functional properties of typical indoor environments.
Our model is composed of layers which represent maps at different
levels of abstraction. The complete system was integrated in a service
robot which is endowed with laser and vision sensors for place and
object recognition. It also incorporates a linguistic framework which
actively supports the map acquisition process and is used for situated
dialogue. In the experiments we show how the robot acquires the conceptual
information and how it is used for situational and functional awareness.},
URL = {http://www.informatik.uni-freiburg.de/~omartine/publications/mozos2007icra_workshop.pdf},
VIDEO = {http://video.google.com/googleplayer.swf?docId=4538999908591170429&hl=de}
}
@INPROCEEDINGS{Mozos/etal:2007,
AUTHOR = {O. Mart\'{\i}nez Mozos and P. Jensfelt and H. Zender and G.J.M. Kruijff
and W. Burgard},
TITLE = {An Integrated System for Conceptual Spatial Representations of Indoor
Environments for Mobile Robots},
BOOKTITLE = {Proceedings of the IROS 2007 Workshop: From Sensors to Human Spatial
Concepts (FS2HSC)},
YEAR = {2007},
ADDRESS = {San Diego, CA, USA},
MONTH = {November}
}
@INPROCEEDINGS{doICCV07,
AUTHOR = {Du\v{s}an Omer\v{c}evi\v{c} and Ondrej Drbohlav and Ale\v{s} Leonardis},
TITLE = {High-dimensional feature matching: Employing the concept of meaningful
nearest neighbors},
BOOKTITLE = {Eleventh IEEE International Conference on Computer Vision ICCV 2007},
YEAR = {2007},
ADDRESS = {Rio de Janeiro, Brazil},
MONTH = {October 14-20},
ABSTRACT = {High-dimensional feature matching using nearest neighbors search is
an important problem in image matching using local invariant features.
In this work we highlight effects pertinent to high-dimensional spaces
that are significant for matching, yet have not been explicitly accounted
for in previous work. In our approach, we require any nearest neighbor
to be meaningful, that is, sufficiently close to a query feature
such that it is an outlier to a background feature distribution.
We estimate the background feature distribution from the extended
query feature neighborhood. Based on the concept of meaningful nearest
neighbors, we have developed a novel matching method and evaluated
its performance by conducting image matching on two challenging image
data sets. A superior performance is shown in comparison to several
state of the art approaches. To speed-up nearest neighbors search
in high-dimensions, we have developed a novel method for approximate
near neighbor search. This method provides a ten-fold speed-up over
an exhaustive search even for high dimensional spaces and retains
excellent approximation to an exact nearest neighbor search.}
}
@INPROCEEDINGS{plagemann07ijcai,
AUTHOR = {Plagemann, C. and Fox, D. and Burgard, W.},
TITLE = {Efficient Failure Detection on Mobile Robots Using Particle Filters
with Gaussian Process Proposals},
BOOKTITLE = {Proc.~of the Twentieth International Joint Conference on Artificial
Intelligence (IJCAI)},
YEAR = {2007},
ADDRESS = {Hyderabad, India},
ABSTRACT = {The ability to detect failures and to analyze their causes is one
of the preconditions of truly autonomous mobile robots. Especially
online failure detection is a complex task, since the effects of
failures are typically difficult to model and often resemble the
noisy system behavior in a fault-free operational mode. In this paper
we present an approach that applies Gaussian process classification
and regression techniques for learning highly effective proposal
distributions of a particle filter that is applied to track the state
of the system. As a result, the efficiency and robustness of the
state estimation process is substantially improved. In practical
experiments carried out with a real robot we demonstrate that our
system is capable of detecting collisions with unseen obstacles while
at the same time estimating the changing point of contact with the
obstacle.},
PDFURL = {http://www.informatik.uni-freiburg.de/~plagem/bib/plagemann07ijcai.pdf}
}
@INPROCEEDINGS{plagemann07rss,
AUTHOR = {Plagemann, C. and Kersting, K. and Pfaff, P. and Burgard, W.},
TITLE = {Gaussian Beam Processes: A Nonparametric Bayesian Measurement Model
for Range Finders},
BOOKTITLE = {Robotics: Science and Systems (RSS)},
YEAR = {2007},
ADDRESS = {Atlanta, Georgia, USA},
MONTH = {June},
ABSTRACT = {In probabilistic mobile robotics, the development of measurement models
plays a crucial role as it directly influences the efficiency and
the robustness of the robot's performance in a great variety of tasks
including localization, tracking, and map building. In this paper,
we present a novel probabilistic measurement model for range finders,
called Gaussian Beam Processes, which treats the measurement modeling
task as a nonparametric Bayesian regression problem and solves it
using Gaussian processes. The major advantage of our approach lies
in the smoothness of the resulting model which appropriately represents
correlations between adjacent beams using covariance functions. Moreover,
the Gaussian process treatment results in a sound probabilistic measurement
model with a pool of well-established techniques for likelihood estimation
and range prediction for an arbitrary number of beams. Experiments
on real world and synthetic data show that Gaussian Beam Processes
combine the advantages of two popular measurement models.},
PDFURL = {http://www.informatik.uni-freiburg.de/~plagem/bib/plagemann07rss.pdf}
}
@INPROCEEDINGS{pronobis07iros,
AUTHOR = {Pronobis, A. and Caputo, B.},
TITLE = {Confidence-based Cue Integration for Visual Place Recognition},
BOOKTITLE = {Proceedings of the IEEE/RSJ International Conference on Intelligent
Robots and Systems (IROS07)},
YEAR = {2007},
ADDRESS = {San Diego, CA, USA},
MONTH = {October},
URL = {http://www.csc.kth.se/~pronobis/research/pronobis07iros/pronobis07iros.pdf}
}
@INPROCEEDINGS{seemann07,
AUTHOR = {Edgar Seemann and Mario Fritz and Bernt Schiele},
TITLE = {Towards Robust Pedestrian Detection in Crowded Image Sequences},
BOOKTITLE = {Proceedings of the Conference on Computer Vision and Pattern Recognition,
Minneapolis, USA},
YEAR = {2007},
MONTH = {June},
URL = {http://www.mis.informatik.tu-darmstadt.de/seemann/seemann07cvpr.pdf}
}
@INPROCEEDINGS{skocajICVS07,
AUTHOR = {D. Sko\v{c}aj and G. Berginc and B. Ridge and A. \v{S}timec and M.
Jogan and O. Vanek and A. Leonardis and M. Hutter and N. Hewes},
TITLE = {A System for Continuous Learning of Visual Concepts},
BOOKTITLE = {International Conference on Computer Vision Systems ICVS 2007},
YEAR = {2007},
ADDRESS = {Bielefeld, Germany},
MONTH = {March},
ABSTRACT = {We present an artifficial cognitive system for learning visual concepts.
It comprises of vision, communication and manipulation sub- systems,
which provide visual input, enable verbal and non-verbal com munication
with a tutor and allow interaction with a given scene. The main goal
is to learn associations between automatically extracted visual features
and words that describe the scene in an open-ended, continuous manner.
In particular, we address the problem of cross-modal learning of
visual properties and spatial relations. We introduce and analyse
several learning modes requiring different levels of tutor supervision.},
OWNER = {danijels vicos cosy visiontrain rpcv leonardo DSSP2},
TIMESTAMP = {2007.03.20},
URL = {http://vicos.fri.uni-lj.si/data/publications/skocajICVS07.pdf}
}
@INPROCEEDINGS{skocajCVWW07,
AUTHOR = {D. Sko\v{c}aj and B. Ridge and G. Berginc and A. Leonardis},
TITLE = {A Framework for Continuous Learning of Simple Visual Concepts},
BOOKTITLE = {Computer Vision Winter Workshop 2007},
YEAR = {2007},
PAGES = {99-105},
ADDRESS = {St. Lambrecht, Austria},
MONTH = {February},
ABSTRACT = {We present a continuous learning framework for learning simple visual
concepts and its implementation in an artificial cognitive system.
The main goal is to learn associations between automatically extracted
visual features and words that describe the scene in an open-ended,
continuous manner. In particular, we address the problem of cross-modal
learning of elementary visual properties and spatial relations; we
show that the same learning mechanism can be used to both types of
concepts. We introduce and analyse several learning modes requiring
different levels of tutor supervision, ranging from a completely
tutor driven to a completely autonomous exploratory approach.},
OWNER = {danijels vicos rscv cosy visiontrain DSSP3},
TIMESTAMP = {2007.02.05},
URL = {http://vicos.fri.uni-lj.si/data/publications/skocajCVWW07.pdf}
}
@ARTICLE{stachniss2007it,
AUTHOR = {Cyrill Stachniss and Giorgio Grisetti and \'{O}scar Mart\'{i}nez
Mozos and Wolfram Burgard},
TITLE = {Efficiently Learning Metric and Topological Maps with Autonomous
Service Robots},
JOURNAL = {it--Information Technology},
YEAR = {2007},
VOLUME = {49},
PAGES = {232--237},
NUMBER = {4},
ABSTRACT = {Models of the environment are needed for a wide range of robotic applications,
from search and rescue to automated vacuum cleaning. Learning maps
has therefore been a major research focus in the robotics community
over the last decades. In general, one distinguishes between metric
and topological maps. Metric maps model the environment based on
grids or geometric representations whereas topologicalmaps model
the structure of the environment using a graph. The contribution
of this paper is an approach that learns a metric as well as a topological
map based on laser range data obtained with a mobile robot. Our approach
consists of two steps. First, the robots solves the simultaneous
localization and mapping problem using an efficient probabilistic
filtering technique. In a second step, it acquires semantic information
about the environment using machine learning techniques. This semantic
information allows the robot to distinguish between different types
of places like, e.g., corridors or rooms. This enables the robot
to construct annotated metric as well as topological maps of the
environment. All techniques have been implemented and thoroughly
tested using real mobile robot in a variety of environments.},
ISSN = {1611--2776},
URL = {http://www.informatik.uni-freiburg.de/~omartine/publications/stachniss2007it.pdf}
}
@INPROCEEDINGS{stark07,
AUTHOR = {Michael Stark and Bernt Schiele},
TITLE = {How Good are Local Features for Classes of Geometric Objects},
BOOKTITLE = {Proceedings of the 11th International Conference on Computer Vision,
Rio de Janeiro, Brazil},
YEAR = {2007},
MONTH = {October},
URL = {http://www.mis.informatik.tu-darmstadt.de/People/stark/iccv07.pdf}
}
@INBOOK{triebel2007gfki,
CHAPTER = {Relational Learning in Mobile Robotics: An Application to Semantic
Labeling of Objects in 2D and 3D Environment Maps},
TITLE = {Studies in Classification, Data Analysis, and Knowledge Organization},
AUTHOR = {Rudolph Triebel and \'{O}scar Mart\'{i}nez Mozos and Wolfram Burgard},
ABSTRACT = {In this paper, we present an algorithm to identify types of places
and objects from 2D and 3D laser range data obtained in indoor environments.
Our approach is a combination of a collective classi cation method
based on associative Markov networks together with an instance-based
feature extraction using nearest neighbor. Additionally, we show
how to select the best features needed to represent the objects and
places, reducing the time needed for the learning and inference steps
while maintaining high classi cation rates. Experimental results
in real data demonstrate the e ectiveness of our approach in indoor
environments.},
URL = {http://www.informatik.uni-freiburg.de/~omartine/publications/triebel2007gfkl_book.pdf}
}
@INPROCEEDINGS{triebel2007ijcai,
AUTHOR = {Triebel, R. and Schmidt, R. and Mart\'{i}nez Mozos, O. and Burgard,
W.},
TITLE = {Instace-based AMN Classification for Improved Object Recognition
in 2D and 3D Laser Range Data},
BOOKTITLE = {Proc.~of the Twentieth International Joint Conference on Artificial
Intelligence (IJCAI)},
YEAR = {2007},
PAGES = {2225--2230},
ADDRESS = {Hyderabad, India},
ABSTRACT = {In this paper, we present an algorithm to identify different types
of objects from 2D and 3D laser range data. Our method is a combination
of an instance-based feature extraction similar to the Nearest-Neighbor
classifier (NN) and a collective classification method that utilizes
associative Markov networks (AMNs). Compared to previous approaches,
we transform the feature vectors so that they are better separable
by linear hyperplanes, which are learned by the AMN classifier. We
present results of extensive experiments in which we evaluate the
performance of our algorithm on several recorded indoor scenes and
compare it to the standard AMN approach as well as the NN classifier.
The classification rate obtained with our algorithm substantially
exceeds those of the AMN and the NN.},
URL = {http://www.informatik.uni-freiburg.de/~omartine/publications/triebel2007ijcai.pdf}
}
@TECHREPORT{ullah07cold,
AUTHOR = {Ullah, M. M. and Pronobis, A. and Caputo, B. and Luo, J. and Jensfelt,
P.},
TITLE = {The {COLD} Database},
INSTITUTION = {Kungliga Tekniska Hoegskolan, CVAP/CAS},
YEAR = {2007},
NUMBER = {TRITA-CSC-CV 2007:1},
MONTH = {October},
URL = {http://www.csc.kth.se/~pronobis/research/ullah07cold}
}
@INPROCEEDINGS{urayBMVC07,
AUTHOR = {M. Uray and D. Sko\v{c}aj and P. Roth and H. Bischof and A. Leonardis},
TITLE = {Incremental {LDA} learning by combining reconstructive and discriminative
approaches},
BOOKTITLE = {British machine vision conference 2007},
YEAR = {2007},
PAGES = {272-281},
ABSTRACT = {Incremental subspace methods have proven to enable efficient training
if large amounts of training data have to be processed or if not
all data is available in advance. In this paper we focus on incremental
LDA learning which provides good classification results while it
assures a compact data representation. In contrast to existing incremental
LDA methods we additionally consider reconstructive information when
incrementally building the LDA subspace. Hence, we get a more flexible
representation that is capable to adapt to new data. Moreover, this
allows to add new instances to existing classes as well as to add
new classes. The experimental results show that the proposed approach
outperforms other incremental LDA methods even approaching classification
results obtained by batch learning.},
OWNER = {danijels vicos cosy mobvis rpcv DSSP2},
TIMESTAMP = {2007.09.10},
URL = {http://vicos.fri.uni-lj.si/data/publications/urayBMVC07.pdf}
}
@INPROCEEDINGS{zender/etal:2007-roman,
AUTHOR = {Hendrik Zender and Patric Jensfelt and Geert-Jan M. Kruijff},
TITLE = {Human- and Situation-Aware People Following},
BOOKTITLE = {Proc. of the 16th IEEE International Symposium on Robot and Human
Interactive Communication (RO-MAN 2007)},
YEAR = {2007},
ADDRESS = {Jeju Island, Korea},
MONTH = {August},
ABSTRACT = {The paper presents an approach to intelligent, interactive people
following for autonomous robots. The approach combines robust methods
for simultaneous localization and mapping and for people tracking
in order to yield a socially and environmentally sensitive people
following behavior. Unlike current purely reactive approaches ("nearest
point following") it enables the robot to follow a human in a socially
acceptable way, providing verbal and non-verbal feedback to the user
where necessary. At the same time, the robot makes use of information
about the spatial and functional organization of its environment,
so that it can anticipate likely actions performed by a human, and
adjust its motion accordingly. As a result, the robot's behaviors
become less reactive and more intuitive when following people around
an indoor environment. The approach has been fully implemented and
tested.},
URL = {http://www.dfki.de/~zender/publications/zender_etal07-roman_pplfoll.pdf}
}
@INPROCEEDINGS{Zender/etal:2007-aaai,
AUTHOR = {H. Zender and P. Jensfelt and O. Mart\'{\i}nez Mozos and G.J.M. Kruijff
and W. Burgard},
TITLE = {An Integrated Robotic System for Spatial Understanding and Situated
Interaction in Indoor Environments},
BOOKTITLE = {Proceedings of the Twenty-Second Conference on Artificial Intelligence
(AAAI-07)},
YEAR = {2007},
PAGES = {1584--1589},
ADDRESS = {Vancouver, Canada},
MONTH = {July},
NOTE = {Special Track on Integrated Intelligence}
}
@INPROCEEDINGS{Zender/Kruijff:2007,
AUTHOR = {H. Zender and G.J.M. Kruijff},
TITLE = {Towards Generating Referring Expressions in a Mobile Robot Scenario},
BOOKTITLE = {Language and Robots: Proceedings from the Symposium (LangRo'2007)},
YEAR = {2007},
ADDRESS = {Aveiro, Portugal},
MONTH = {December}
}
@INPROCEEDINGS{Zender2007,
AUTHOR = {Hendrik Zender and Geert-Jan M. Kruijff},
TITLE = {Multi-Layered Conceptual Spatial Mapping for Autonomous Mobile Robots},
BOOKTITLE = {Control Mechanisms for Spatial Knowledge Processing in Cognitive
/ Intelligent Systems},
YEAR = {2007},
EDITOR = {Holger Schultheis and Thomas Barkowsky and Benjamin Kuipers and Bernhard
Hommel},
VOLUME = {Technical Report SS-07-01},
SERIES = {Papers from the AAAI Spring Symposium},
PAGES = {62--66},
ADDRESS = {Menlo Park, CA, USA},
MONTH = {March},
PUBLISHER = {AAAI Press}
}
@INPROCEEDINGS{Zender2007d,
AUTHOR = {Hendrik Zender and Geert-Jan M. Kruijff},
TITLE = {Towards Generating Referring Expressions in a Mobile Robot Scenario},
BOOKTITLE = {Language and Robots: Proceedings of the Symposium},
YEAR = {2007},
PAGES = {101--106},
ADDRESS = {Aveiro, Portugal},
MONTH = {December}
}
@INPROCEEDINGS{zillich2007incremental,
AUTHOR = {Zillich, Michael},
TITLE = {Incremental {I}ndexing for {P}arameter-{F}ree {P}erceptual {G}rouping},
BOOKTITLE = {31st {W}orkshop of the {A}ustrian {A}ssociation for {P}attern {R}ecognition},
YEAR = {2007},
ABSTRACT = {The detection of closed convex contours in edge segmented images quickly
leads to a large number of hypotheses. Typically two methods are
used to limit the combinatorial explosion inherent in such perceptual
grouping tasks: indexing and early thresholding of less salient hypotheses.
We show that the adoption of an incremental indexing scheme removes
the need for thresholds, leading to improved robustness. Furthermore
incremental processing quite naturally leads to anytime processing.},
URL = {http://www.cs.bham.ac.uk/~mxz/bibtex/papers/zillich2007incremental.pdf}
}
This file has been generated by
bibtex2html 1.79
Print this page
|
