Search our Publications
Latest Publications
Matthias Rolf, Jochen Steil, Michael Gienger , "Efficient exploration and learning of whole body kinematics", Proceedings of the The 8th International Conference on Development and Learning, 2009.
AbstractWe present a neural network approach to early motor learning. The goal is to explore the needs for bootstrapping the control of hand movements in a biologically plausible learning scenario. The model is applied to the control of hand postures of the humanoid robot ASIMO by means of full upper body movements. For training, we use an efficient online scheme for recurrent reservoir networks consisting of supervised backpropagation-decorrelation outp...
Download Bibtex file Download PDF
Daniel Weiler and Julian Eggert , "Level-Set Segmentation with Contour based Object Representation", Proceedings of the 2009 International Joint Conference on Neural Networks (IJCNN), 2009.
Download Bibtex file Download PDF
Yaochu Jin, Honglian Guo, Yan Meng , "Robustness analysis and failure recovery of a bio-inspired self-organizing multi-robot system", Third IEEE International Conference on Self-Adaptive and Self-organizing Systems, pp. 154–164, 2009.
Download Bibtex file Download PDF
Chen Zhang and Julian Eggert , "Tracking with Multiple Prediction Models", Artificial Neural Networks - ICANN, 19th International Conference, pp. 855-864, 2009.
AbstractIn Bayesian-based tracking systems, prediction is an essential part of the framework. It models object motion and links the internal estimated motion parameters with sensory measurement of the object from the outside world. In this paper a Bayesian-based tracking system with multiple prediction models is introduced. The benefit of multiple model prediction is that each of the models has individual strengths suited for different situations. For ex...
Download Bibtex file Download PDF
Andre Justus , "Nutzung der Tiefeninformationen eines Lasersensors zur Erweiterung einer Fahrspuridentifikation fuer ein Fahrerassistenzsystem", Bielefeld University, 2009.
AbstractIn new vehicles, increasingly more advanced driver assistance systems (ADASs) have been incorporated in order to assist the driver in dangerous situations. Through warnings and interventions, ADASs increase the safety of the driver and others using the road. At the moment, mainly cameras and radar sensors are used in ADASs for sensing the environment. Laser sensors may also be used and present an advantage to radar in that they can detect slow mo...
Download Bibtex file Per Mail Request
Sven Rebhan and Julian Eggert , "Consistent Modeling of Functional Dependencies along with World Knowledge", Proceedings of the International Conference on Cognitive Information Systems Engineering (ICCISE), pp. 341-348, 2009.
AbstractIn this paper we propose a method for visual systems to consistently represent functional dependencies between different visual routines along with relational short- and long-term knowledge about the world. Here the visual routines are bound to visual properties of objects stored in the memory of the system. Furthermore the functional dependencies between the visual routines are seen as a graph also belonging to the object’s structure. This graph...
Download Bibtex file Download PDF
Markus Olhofer, Thomas Bihrer, Stefan Menzel, Michael Fischer, Bernhard Sendhoff , "Evolutionary Optimisation of an Exhaust Flow Element with Free Form Deformation", Simulation for Innovative Design, Proceedings of the 4th EASC - 2009 European Automotive Simulation Conference, pp. 163-174, 2009.
Download Bibtex file Download PDF
Thomas Michalke , "Task-Dependent Scene Interpretation in Driver Assistance", TU Darmstadt, 2009.
Download Bibtex file Per Mail Request
Ben Jones, Yaochu Jin, Bernhard Sendhoff, Xin Yao , "The evolutionary emergence of neural organization in a hydra-like animat", The Bernstein Conference on Computational Neuroscience, 2009.
Download Bibtex file Download PDF
Claudius Gläser, Frank Joublin, Christian Goerick , "Intrinsically Regulated Self-Organization of Topologically Ordered Neural Maps", Frontiers in Computational Neuroscience. Conference Abstract: Bernstein Conference on Computational Neuroscience, 2009.
AbstractDynamic field theory models the spatio-temporal evolution of activity within the cortex and has been successfully applied in various domains. However, the development of dynamic neural fields (DNFs) is only rarely explored. This is due to the fact that DNFs are sensible to the right balance between excitation and inhibition within the fields. Small changes to this balance will result in runaway excitation or quiescence. Consequently, learning mos...
Download Bibtex file Download PDF
1 ... 136 137 138 139 140 141 ... 183
Follow us
