Search our Publications
Latest Publications
Florian Damerow and Julian Eggert , "Framework for risk aversive and efficient behavior planning under multiple situations with uncertainty", 18th IEEE International Conference on Intelligent Transportation Systems 2015 (ITSC), pp. 656-663, 2015.
AbstractThis paper addresses the problem of future behavior evaluation and planning for upcoming ADAS, especially for inner city traffic scenarios. Situations in inner city traffic scenarios are generally highly complex and of high uncertainty. The behavior in such complex scenarios differs strongly depending on the actual present situation. In general the current situation can only be determined with high uncertainty based on current and past measuremen...
Download Bibtex file
Ran Cheng, Yaochu Jin, Kaname Narukawa , "An Adaptive Reference Vector Generation Strategy for Inverse Model Based Evolutionary Multiobjective Optimization", The 8th International Conference on Evolutionary Multi-Criterion Optimization, 2015.
AbstractThe objective space and the decision space are two spaces in multiobjective optimization problems (MOPs). Very recently, noticing the fact that to maintain diversity in the objective space is much easier than in the decision space, the authors have proposed an inverse modeling based multiobjective evolutionary algorithm. To facilitate the process of inverse modeling, the objective space is partitioned into several subregions by predefining some r...
Download Bibtex file
Christian Goerick and Frank Joublin , "From Babies to Robots (Intelligent Robotics and Autonomous Agents)", From Babies to Robots (Intelligent Robotics and Autonomous Agents), The Mit Press, 2015.
Abstractno abstract...
Download Bibtex file
Tobias Rodemann, Kaname Narukawa, Michael Fischer, Mohammed Awada , "Many-Objective Optimization of a Hybrid Car Controller", EvoStar 2015 Conference, 2015.
AbstractHybrid cars are considered to be a promising approach for providing individual mobility with lower CO -emissions without compromising on affordability and driving range. In order to reach these targets a highly efficient control (energy management) is required. In mass production vehicles control is often organized using simple, quick and easy to understand rule-based systems. Such a rule-base typically contains a moderate number of parameters wh...
Download Bibtex file
Nikola Aulig and Markus Olhofer , "Neuro-evolutionary Topology Optimization with Adaptive Improvement Requirement", 18th European Conference on the Applications of Evolutionary Computation, 2015.
AbstractRecently a hybrid combination of neuro-evolution with a gradient-based topology optimization method was proposed, facilitating topology optimization of structures subject to objective functions for which gradient information is difficult to obtain. The approach substitutes analytical sensitivity information by an update signal represented by a neural network approximation model. Topology optimization is performed by optimizing the network paramet...
Download Bibtex file
Lars Gräning , "Flow Field Data Mining based on a Compact Stream Line Representation", SAE 2015 World Congress & Exhibition, 2015.
AbstractIn many engineering domains like aerospace, vehicle or engine design the analysis of flow fields, acquired from computational fluid dynamics (CFD) simulations can reveal important insights on the behavior of the simulated objects. However, the huge amount of flow data produced by each simulation complicates the data processing and limits the application of data mining and machine learning tools for the flow analysis. The paper introduces a compac...
Download Bibtex file
Marvin Struwe, Stephan Hasler, Ute Bauer-Wersing , "A Two-stage Classifier Architecture for Detecting Objects under Real-world Occlusion Patterns ", Heidelberger Bildverarbeitungs Forum, 2015.
AbstractDespite extensive efforts, state-of-the-art detection approaches show a strong degradation of performance with increasing level of occlusion. In this paper we investigate a strategy to improve the detection of occluded objects based on the analytic feature framework from \cite{struwe13} and compare the results in a car detection task. Motivated by an analysis of annotated traffic scenes we focus on a general concept to handle vertical occlusion p...
Download Bibtex file Per Mail Request
Benjamin Metka, Ute Bauer-Wersing, Mathias Franzius , "Visual Self-Localization in Outdoor Environments Using Slow Feature Analysis", Heidelberger Bildverarbeitungsforum, 2015.
AbstractWe apply slow feature analysis (SFA) to the problem of selflocalization with a mobile robot. A similar unsupervised hierarchical model has earlier been shown to extract a virtual rat's position as slowly varying features by directly processing the raw, high dimensional views captured during a training run. The learned representations encode the robot's position, are orientation invariant and similar to cells in a rodent's hippocampus. Here...
Download Bibtex file Per Mail Request
Lydia Fischer, Barbara Hammer, Heiko Wersing , "Certainty-based Prototype Insertion/Deletion for Prototype-based Classification with Metric Adaptation", 23th European Symposium on Artificial Neural Networks ESANN 2015, pp. 7-12, 2015.
AbstractWe propose an extension of prototype-based classification models to automatically adjust model complexity, thus offering a powerful technique for online, incremental learning tasks. The incremental technique is based on the notion of the certainty of an observed classification. Unlike previous work, we can incorporate matrix learning into the framework by relying on the cost function of generalised learning vector quantisation (GLVQ) for prototy...
Download Bibtex file
Jens Kober, Michael Gienger, Jochen Steil , "Learning Force-Interaction Motor Primitives from Kinesthetic Demonstrations", 2015 IEEE International Conference on Robotics and Automation (ICRA), 2015.
AbstractIn this paper we discuss our framework for reconstructing motor primitives that were demonstrated by kinesethetic demonstrations. We focus on skills where force interactions with the environment are required. Our process covers the segmentation of the raw demonstrations, assigning control frames and modalities per primitive, as well as discovering termination criteria. The approach is evaluated on a Barrett WAM, where a box is manipulated in cont...
Download Bibtex file
1 ... 97 98 99 100 101 102 ... 183
Follow us
