Search our Publications
Latest Publications
Raphael Golombek , "Data-driven Fault Detection for Component Based Robotic Systems", University of Bielefeld, 2014.
AbstractAdvancements in the field of robotics enable the creation of systems with cognitive abilities which are capable of close interaction with humans in real world scenarios. These systems may take over jobs previously executed by humans like house cleaning and cooking or they can be supportive and act as an elderly caretaker. One consequence of this progress is the increased need for dependable and fault tolerant behavior of today’s robotic syst...
Download Bibtex file Per Mail Request
Jannik Fritsch, Tobias Kühnl, Franz Kummert , "Monocular Road Terrain Detection by Combining Visual and Spatial Information", IEEE Transactions on Intelligent Transportation Systems, 2014.
AbstractFor future driver assistance systems and autonomous vehicles, the road course, i.e., the width and shape of the driving path, is an important source of information. In this contribution we introduce a new hierarchical two-stage approach for learning the spatial layout of road scenes. In the first stage, base classifiers analyze the local visual properties of patches extracted from monocular camera images and provide metric confidence maps. We use...
Download Bibtex file
Heiko Wersing, David Nebel, Barbara Hammer, Thomas Villmann, Lydia Fischer , "Rejection strategies for Learning Vector Quantization - a comparison of probabilistic and deterministic approaches", Advances in Self-Organizing Maps and Learning Vector Quantization - Proceedings of the 10th International Workshop, WSOM, vol. 295, pp. 109-118, 2014.
AbstractReject options in multiclass classification schemes enable a direct man-machine interaction which allow an improvement of the classification task with human expert knowledge in regions with class overlap or outliers. We compare two rejection strategies which are derived from Generalized Learning Vector Quantization with statistical motivated strategies. These two options are heuristics only but with less additional computational effort on these...
Download Bibtex file
Lydia Fischer, Barbara Hammer, Heiko Wersing , "Rejection Strategies for Learning Vector Quantization", 22th European Symposium on Artificial Neural Networks ESANN 2014, pp. 41-46, 2014.
AbstractReject options in multiclass classification schemes enhance a given classifier by a confidence value which quantifies the security of the classification decision taken for a given data point. Based on this value, man-machine interaction or an improvement of the classification task with human expert knowledge becomes possible in regions with class overlap or outliers. While there exist efficient reject options for popular classifiers such as ...
Download Bibtex file
Stefan Menzel , "Efficient Shape Deformations for Simulation-based Design Optimization", HCO Workshop Industrial Optimization, 2014.
AbstractEfficient design optimization relies on a well-balanced combination of shape representation, optimization algorithm, and design evaluation method. One option for representing geometries are shape morphing methods, such as free form deformation (FFD), direct manipulation of free form deformation (DMFFD), or deformations based on radial basis functions (RBF). These techniques have been frequently employed as representations for design optimization ...
Download Bibtex file Per Mail Request
Anna-Lisa Vollmer, Manuel Mühlig, Jochen Steil, Karola Pitsch, Jannik Fritsch, Katharina Rohlfing, Britta Wrede , "Robots show us how to teach them: Feedback from robots shapes tutoring behavior during action learning", PLoS ONE, vol. 9, no. 3, pp. e91349, 2014.
AbstractRobot learning by imitation requires the detection of a tutor’s action demonstration and its relevant parts. Current approaches implicitly assume a unidirectional transfer of knowledge from tutor to learner. The presented work challenges this predominant assumption based on an extensive user study with an autonomously interacting robot. We show that by providing feedback, a robot learner influences the human tutor’s movement demonstrations in ...
Download Bibtex file
Aniket Murarka and Nils Einecke , "A Meta-technique for Increasing Density of Local Stereo Methods through Iterative Interpolation and Warping", Conference on Computer and Robot Vision, pp. 254-261, 2014.
AbstractDespite much progress in global methods for computing depth from pairs of stereo images, local block matching methods are still immensely popular largely due to low computational cost and ease of implementation. However, such methods usually fail to produce valid depths in several image regions due to various reasons such as violations of a fronto-parallel assumption and lack of texture. In this paper, we present a simple and fast meta-technique ...
Download Bibtex file
Tobias Rodemann, Torsten Schwan, René Unger , "Modeling and Optimization of a Smart Home System", ProduktDaten Journal, vol. 1, 2014.
AbstractDurch die Herausforderungen des Klimawandels, steigender Preise fossiler Brennstoffe und einer Neubewertung des Risikos der Kernkraft, werden neue, innovative Ansätze zur Stromproduktion, - speicherung und -nutzung benötigt. Intelligente Häuser, sogenannte Smart Homes, können einen wichtigen Beitrag leisten, da sie Stromproduktion (durch PV oder BHKWs), mit Energiespeicherung und Verbrauch lokal integrieren können. Die Kombination mit der (elek...
Download Bibtex file
Olga Smalikho and Markus Olhofer , "Growth process in co-evolution of sensory system and signal processing for optimal wing shape control", GECCO 2014, 2014.
AbstractThe development of adaptive systems, which react autonomously to changes in their environment, require the coordinated generation of sensors providing information about the environment and processing structures which generate suitable reactions to changed conditions. In this work we demonstrate the applicability of a co-evolutionary design of the sensory and controller parts of a system for the example of an adaptive wing design. The focus of the...
Download Bibtex file
Simon Manschitz, Jens Kober, Michael Gienger, Jan Peters , "Learning to Unscrew a Light Bulb from Demonstrations", International Symposium on Robotics - ISR 2014, 2014.
AbstractWe present an approach for learning sequential manipulation skills with a robot. The skill is demonstrated several times by kinesthetic teach-in and then gets reproduced by choosing the current action from a predefined library of basic movements. The selection is treated as classification problem. We show how the sequential order of the movements can be used to improve the classification results. Therefore we present a concept called Seque...
Download Bibtex file
1 ... 101 102 103 104 105 106 ... 183
Follow us
