Andreas Alin , "Task-Specific Environment Rrepresentations for Driving Behavior Generation", Universität Würzburg, 2010.
AbstractThe 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 Offenbach. 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...
Matthias Rolf, Jochen Steil, Michael Gienger , "Bootstrapping inverse Kinematics with Goal Babbling", Proceedings of the International Conference on Development and Learning, 2010.
AbstractWe 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....
Irene Ayllón Clemente, Martin Ernst Heckmann, Alexander Denecke, Britta Wrede, Christian Goerick , "Incremental Word Learning Using Large Margin Discriminative Training and Variance Floor Estimation", Proceedings of the INTERSPEECH, 2010.
Claudius Gläser, Martin Ernst Heckmann, Frank Joublin, Christian Goerick , "Robust Formant Tracking in Echoic and Noisy Environments", Proceedings of the 9th ITG Conference on Speech Communication, 2010.
Martin Ernst Heckmann, Xavier Domont, Frank Joublin, Christian Goerick , "Investigating the Complementarity of Spectral and Spectro-temporal Features", Proceedings of DAGA 2010, 2010.
AbstractMost 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 ...
Julian Eggert, Jörg Deigmöller, Volker Willert , "Layered Motion Segmentation with a Competitive Recurrent Network", Artificial Neural Networks - ICANN 2010 Proceedingts, pp. 124-133, 2010.
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.
AbstractThe 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 ...
Anton Korell , "Recherchemethoden und Portfoliobewertung im Bereich neuer Technologien am Beispiel der Computational Intelligence", Hochschule Amberg-Weiden, 2010.
Marc Henniges, Gervasio Puertas, Julian Eggert, Jörg Lücke , "Binary Sparse Coding", Proceedings of the LVA, issue 1st edition, 2010.
Michael Gienger, Manuel Mühlig, Jochen Steil , "Human-Robot Interaction for Learning and Adaptation of Object Movements", Proceedings of the IEEE International Conference on Intelligent Robots and Systems (IROS), 2010.