Search our Publications
Latest Publications
Ran Cheng, Markus Olhofer, Yaochu Jin , "Reference Vector based a posteriori Preference Articulation for Evolutionary Multiobjective Optimization", 2015 IEEE Congress on Evolutionary Computation, 2015.
AbstractThe result of a multi objective optimization is usually a set of optimal trade-off solutions for the different criteria. In order to utilize the results, the so called Pareto set, a final decision making process is necessary in most cases in which one single solution has to be selected. In this process a decision maker selects one of the solutions in the set according to his or her preferences and often also based on knowledge gained by observing...
Download Bibtex file
ChangHyun Sung, Manuel Mühlig, Michael Gienger , "Task-dependent Distribution and Constrained Optimization of Via-points for Smooth Robot Motions", 2015 IEEE International Conference on Robotics and Automation, 2015.
AbstractThis paper presents an effective method for planning and optimizing robot motions in joint space using via-points. The via-point formulation allows for a sparse movement representation which is inherently smooth according to a minimum jerk criterion. In this research we focus on two aspects. First, we present an initialization method to find a feasible number of via-points and their distribution in time. This initialization takes the difficulty o...
Download Bibtex file
Mathias Franzius , "Wo bin ich? Selbstlokalisierung im Gehirn", Heidelberger Bildverarbeitungsforum, 2015.
AbstractNavigation in komplexen Umgebungen setzt voraus zu wissen wo man ist. Viele Tiere bestimmen die eigene Position mit einer Genauigkeit und Robustheit, die die meisten technischen Systeme noch immer in den Schatten stellen. 45 Jahre nachdem das erste Mal Gehirnzellen vermessen wurden, die die eigene Position eines Tieres im Raum kodieren, haben sich Daten und Modelle herauskristallisiert, wie diese Funktion im Gehirn erreicht wird. Im Hippocamp...
Download Bibtex file Per Mail Request
Lydia Fischer, Barbara Hammer, Heiko Wersing , "Combining Offline and Online Classifiers for Life-long Learning", International Joint Conference on Neural Networks (IJCNN), pp. 2808-2815, 2015.
AbstractWe propose a flexible system combining a static offline classifier and an incremental online classifier that is well suited for life-long learning scenarios. The pre-trained offline classifier preserves knowledge that should be kept and the online classifier enables learning of new or specific information encountered during use. A dynamic classifier selection based on a certainty estimation provides the most reliable classification for new data. ...
Download Bibtex file
Nils Einecke and Julian Eggert , "A Multi Block-Matching Approach for Stereo", Intelligent Vehicles Symposium, pp. 585-592, 2015.
AbstractBlock-Matching stereo is commonly used in applications with minimal computing resources in order to get some rough depth estimates. However, research on this simple stereo estimation technique has been very low since the advent of energy-based methods which promise higher quality and a larger creational research freedom. In the domain of intelligent vehicles, especially semi-global-matching (SGM) is widely spread due to its good performance. In t...
Download Bibtex file
Edoardo Casapietra, Thomas H Weisswange, Jannik Fritsch, Franz Kummert, Christian Goerick , "Building a probabilistic grid-based road representation from direct and indirect visual cues", IEEE Intelligent Vehicles Symposium (IV 2015), pp. 273-279, 2015.
AbstractDetecting the road area ahead of the ego-vehicle is an important issue for modern driver assistance systems. In particular, vehicle motion planning in inner city environment requires the detection of road up to 3 seconds in advance. State-of-the-art visual road detection systems have a hard time fulfilling this task, due to their relatively short range and the presence of occlusions (other vehicles, buildings, etc.), which are expected to occur o...
Download Bibtex file
Viktor Losing, Barbara Hammer, Heiko Wersing , "Interactive Online Learning for Obstacle Classification on a Mobile Robot", International Joint Conference on Neural Networks IJCNN, Killarney Ireland, pp. 2310-2317, 2015.
AbstractWe present an architecture for incremental online learning in high-dimensional feature spaces and apply it on a mobile robot. The model is based on learning vector quantization, approaching the stability-plasticity problem of incremental learning by adaptive insertions of representative vectors. We employ a cost-function-based learning vector quantization approach and introduce a new insertion strategy optimizing a cost-function based on a ...
Download Bibtex file
Nikola Aulig, Emily Nutwell, Stefan Menzel, Duane Detwiler , "A Weight Balanced Multi-Objective Topology Optimization for Automotive Development", European LS-DYNA Conference 2015, 2015.
AbstractTopology optimization in the field of automotive development strives for conceptual car components which are efficiently designed for multiple, partly conflicting loadings. Crashworthiness loadings typically require a maximization of energy absorption while static loadings typically require a minimization of compliance. The hybrid cellular automata algorithm which aims for a uniform distribution of the internal energy density offers an efficient ...
Download Bibtex file
Andrea Schnall and Martin Ernst Heckmann , "Optical Flow Field Features for Audio-visual Word Prominence Detection", Int. Joint Conf. on Neural Networks (IJCNN), 2015.
AbstractIn this paper we investigate visual features for the automatic labeling of the prominence of words. Visual motion is a rich source of information. Modifying the articulatory parameters to raise the prominence of a segment of an utterance, is usually accompanied by a stronger and different movement of mouth and head. One way to describe such motion is to use optical flow fields. During the recording of the underlying audio-visual database, the ...
Download Bibtex file
Benjamin Metka, Annika Besetzny, Mathias Franzius, Ute Bauer-Wersing , "Predicting the Long-term Robustness of Visual Features", International Conference on Advanced Robotics, 2015.
AbstractMany vision based localization methods extract local visual features to build a sparse map of the environment and estimate the position of the camera from feature correspondences. However, the majority of features is typically only detectable for short time-frames so that most information in the map becomes obsolete over longer periods of time. Long-term localization is therefore a challenging problem especially in outdoor scenarios where ...
Download Bibtex file
1 ... 98 99 100 101 102 103 ... 183
Follow us
