Search our Publications
Latest Publications
Viktor Losing, Heiko Wersing, Barbara Hammer , "Enhancing Very Fast Decision Trees Using Local Split-Time Prediction", ICDM 2018, 2018.
AbstractAn increasing number of industrial areas recognize the opportunities of Big Data and try to utilize it for their business. However, they also face the related challenges as the excessively growing information flood, ever more requiring highly efficient algorithms which enable real-time processing and reduce the burden of data storage and maintenance. Decision trees are extremely fast, highly accurate and easy to use in practice. Utilized within a...
Download Bibtex file
Christian Limberg, Heiko Wersing, Helge Ritter , "Improving Active Learning by Avoiding Ambiguous Samples", International Conference on Artificial Neural Networks, 2018.
AbstractIf label information in a classification task is expensive, it can be beneficial to use active learning to get the most informative samples to label by a human. However, there can be samples which are mean- ingless to the human or recorded wrongly. If these samples are near the classifier’s decision boundary, they are queried repeatedly for labeling. This is inefficient for training because the human can not label these samples correctly an...
Download Bibtex file
Rodrigo Canaan, Haotian Shen, Ruben Torrado, Julian Togelius, Andy Nealen, Stefan Menzel , "Evolving Agents for the Hanabi 2018 CIG Competition", IEEE Conference on Computational Intelligence and Games (CIG), 2018.
AbstractHanabi is a cooperative card game with hidden information that has won important awards in the industry and received some recent academic attention. A two-track competition of agents for the game will take place in the 2018 CIG conference. In this paper, we develop a genetic algorithm that builds rule-based agents by determining the best sequence of rules from a fixed rule set to use as strategy. In three separate experiments, we remove human ass...
Download Bibtex file
Rodrigo Canaan, Stefan Menzel, Julian Togelius, Andy Nealen , "Towards Game-based Metrics for Computational Co-creativity", IEEE Conference on Computational Intelligence and Games (CIG), 2018.
AbstractWe propose the following question: what game-like interactive system would provide a good environment for measuring the impact and success of a co-creative, cooperative agent? Creativity is often formulated in terms of novelty, value, surprise and interestingness. We review how these concepts are measured in current computational intelligence research and provide a mapping from modern electronic and tabletop games to open research problems in mix...
Download Bibtex file
Martin Ernst Heckmann, Dennis Orth, Dorothea Kolossa , ""Gap after the next two vehicles": A Spatio-temporally Situated Dialog for Human-car Cooperative Driving", 13. ITG Fachtagung Sprachkommunikation Oldenburg, ITG/IEEE, 2018.
AbstractWe present a spatio-temporally situated dialog implemented in a driver assistance system which supports the driver in turning left at a busy urban intersection. The system provides verbal information on the vehicles arriving from the right side. In this highly dynamic scenario the location of the vehicles referred to significantly changes while the system is referring to them. Consequently, the time the system needs for producing the utterance...
Download Bibtex file
Julian Eggert and Tim Puphal , "Continuous Risk Measures for Driving Support ", International Journal of Automotive Engineering, vol. 9, no. 3, pp. 130-137, 2018.
AbstractIn this paper, we compare three different model-based risk measures by evaluating their stengths and weaknesses qualitatively and testing them quantitatively on a set of real longitudinal and intersection scenarios. We start with the traditional heuristic Time-To-Collision (TTC), which we extend towards 2D operation and non-crash cases to retrieve the Time-To- Closest-Encounter (TTCE). The second risk measure models position uncertainty with a Ga...
Download Bibtex file
Matti Krüger , "Approach for Enhancing the Perception and Prediction of Traffic Dynamics with a Tactile Interface.", Doctoral Colloquium, 10th International ACM Conference on Automotive User Interfaces , 2018.
AbstractParticipation in road traffic frequently requires fast and accurate understanding of environmental object characteristics. Here I introduce an assistance function and corresponding interface targeted at enhancing a driver's perception and understanding of environment dynamics in order to improve driving safety and performance. The core functionality of this assistance function lies in the tactile communication of spatio-temporal proximity informa...
Download Bibtex file Per Mail Request
Muhammad Haris, Mathias Franzius, Ute Bauer-Wersing , "Robot Navigation on Slow Feature Gradients", International Conference on Neural Information Processing (ICONIP 2018), Springer, Cham, vol. 11307, issue 25th, pp. 143-154, 2018.
AbstractA model of hierarchical Slow Feature Analysis (SFA) enables a mobile robot to learn a spatial representation of its environment directly from images captured during a random walk. After the unsupervised learning phase a subset of the resulting representations are orientation invariant and code for the position of the robot. Hence, they change monotonically over space even though the variation of the sensory signals received from the environment m...
Download Bibtex file
Benjamin Metka, Ute Bauer-Wersing, Mathias Franzius , "Bio-inspired visual self-localization in real world scenarios using Slow Feature Analysis", PLOS ONE, 2018.
AbstractWe present a biologically motivated model for visual self-localization which extracts a spatial representation of the environment directly from high dimensional image data by employing a single unsupervised learning rule. The resulting representation encodes the position of the camera as slowly varying features while being invariant to its orientation resembling place cells in a rodent’s hippocampus. Using an omnidirectional mirror allows to...
Download Bibtex file
Theodoros Stouraitis, Michael Gienger, Sethu Vijayakumar , "Dyadic Collaborative Manipulation through Hybrid Trajectory Optimization ", Conference on Robot Learning (CoRL), 2018.
AbstractThe proposed approach provides a principled formalism to address the joined planning problem in co-manipulation scenarios, by representing humans intentions into task space forces and solving the joined problem holistically via model-based optimization. Additionally, the proposed method is the first to empower robotic agents with the ability to exploit both the contact and the force space towards finding the optimal solution for the co-manipu...
Download Bibtex file
1 ... 86 87 88 89 90 91 ... 183
Follow us
