Mathias Rudolph, Manuel Mühlig, Michael Gienger, Hans-Joachim Böhme,
"Learning the Consequences of Actions: Representing Effects as Feature Changes",
Proceedings of the International Symposium on Learning and Adaptive Behavior in Robotic Systems, 2010.
Abstract
In advanced Programming by Demonstration (PbD) it is important to give a robot the ability to understand the effects of an action. This ability can enable a robot to not only mimic an action but to imitate, by determining whether an action succeeded or not, or to emulate, by finding another action that causes the same effects as observed. In this paper we propose a system that uses a Bayesian Network structure to store actions as a representation...
Download Bibtex file
Download PDF
Jonathan Maycock, Daniel Dornbusch, Christof Elbrechter, Robert Haschke, Thomas Schack, Helge Ritter,
"Approaching Manual Intelligence",
Kuenstliche Intelligenz, vol. 24, no. 4, pp. 287-294, 2010.
Download Bibtex file
Download PDF
Nils Einecke, Sven Rebhan, Volker Willert, Julian Eggert,
"Direct Surface Fitting",
Proceedings of VISAPP 2010 International Conference on Computer Vision Theory and Applications, pp. 125–133, 2010.
Abstract
In this paper, we propose a new method for estimating the shape of a surface from visual input. Assuming a parametric model of a surface, the parameters best explaining the perspective changes of the surface between different views are estimated. This is in contrast to the usual approach of fitting a model into a 3-D point cloud, generated by some previously calculated local correspondence matching method. The main ingredients of our approach are...
Download Bibtex file
Download PDF
Andreas Alin,
"Task-Specific Environment Rrepresentations for Driving Behavior Generation",
Universität Würzburg, 2010.
Abstract
The goal of this diploma thesis is to develop a metric representation of the environment, which illustrates the free area in front of a vehicle. This can be part of an advanced driver assistance system developed at the Honda Research Institute in O ffenbach. The representation is based on the brain-inspired theory of population codes. Probabilities of object presence are processed like activities, which are propagated through the representation i...
Download Bibtex file
Per Mail Request
Matthias Rolf, Jochen Steil, Michael Gienger,
"Bootstrapping inverse Kinematics with Goal Babbling",
Proceedings of the International Conference on Development and Learning, 2010.
Abstract
We present an approach to learn inverse kinematics of redundant systems without prior- or expert-knowledge. The method allows for an iterative bootstrapping and refinement of the inverse kinematics estimate. We show that the information structure induced by goal-directed exploration enables an efficient resolution of inconsistent samples solely from observable data. The bootstrapped solutions are aligned for a maximum of movement efficiency, i.e....
Download Bibtex file
Download PDF
Irene Clemente, Martin Heckmann, Alexander Denecke, Britta Wrede, Christian Goerick,
"Incremental Word Learning Using Large Margin Discriminative Training and Variance Floor Estimation",
Proceedings of the INTERSPEECH, 2010.
Abstract
We investigate incremental word learning in a Hidden Markov Model (HMM) framework suitable for human-robot interaction. In interactive learning, the tutoring time is a crucial factor. Hence our goal is to use as few training samples as possible while maintaining a good performance level. To adapt the states of the HMMs, different large-margin discriminative training strategies for increasing the separability of the classes are proposed. We also p...
Download Bibtex file
Download PDF
Claudius Gläser, Martin Heckmann, Frank Joublin, Christian Goerick,
"Robust Formant Tracking in Echoic and Noisy Environments",
Proceedings of the 9th ITG Conference on Speech Communication, 2010.
Abstract
Despite the fact that formant extraction has been investigated for a long time it still remains a challenging task. Particularly in real-world environments, where noise and echoes are detrimental factors for speech processing, existing methods for formant extraction yield unfavorable results. Here, we present a framework for formant tracking which is specifically tailored for application in such difficult settings. Keys to our method are, firstly...
Download Bibtex file
Download PDF
Martin Heckmann, Xavier Domont, Frank Joublin, Christian Goerick,
"Investigating the Complementarity of Spectral and Spectro-temporal Features",
Proceedings of DAGA 2010, 2010.
Abstract
Most common speech features as Mel Ceptstral Coefficients (MFCCs) and RASTA-PLP features use only spectral information. From measurements in the mammalian auditory cortex it is known that the mammalian brain jointly uses spectral and temporal information. To model this we previously developed Hierarchical Spectro-Temporal (HIST) features. They consist of two layers, the first capturing local spectro-temporal variations and the second integrating ...
Download Bibtex file
Download PDF
Julian Eggert, Jörg Deigmöller, Volker Willert,
"Layered Motion Segmentation with a Competitive Recurrent Network",
Artificial Neural Networks - ICANN 2010 Proceedingts, pp. 124-133, 2010.
Abstract
Using local motion information data such as that obtained from optical flow, we present a network for a multilayered segmentation into motion regions that are governed by affine motion patterns. Using an energy-based competitive multilayer architecture based on non-negative activations and multiplicative update rules, we show how the network can perform segmentation tasks that require a combination of affine estimation with local integration and ...
Download Bibtex file
Download PDF
Thomas Michalke, Jannik Fritsch, Christian Goerick,
"A Biologically-Inspired Vision Architecture for Resource-Constrained Intelligent Vehicles year = 2010",
Computer Vision and Image Understanding, Special Issue: Intelligent Vision systems for Computer Vision and Image Understanding, 2010.
Abstract
The use of computer vision for assisting the driver dates back to first research projects in the 80', but only recently the progress in vision research and the increase in computational power have resulted in actual products. Although impressive from the robustness point of view, these systems are optimized for specific problems and at best perform reactive tasks like, e.g., lane keeping assistance. However, for a better understanding of generic ...
Download Bibtex file
Download PDF
1 ...
95 96 97 98
99 100 ...
151
