Search our Publications
Latest Publications
Yali Wang, Steffen Limmer, Markus Olhofer, Michael Emmerich, Thomas Bäck , "Automatic Preference Based Multi-objective Evolutionary Algorithm on Vehicle Fleet Maintenance Scheduling Optimization", Swarm and Evolutionary Computation, 2021.
AbstractA preference based multi-objective evolutionary algorithm is proposed for generating solutions in an automatically detected knee point region. It is named Automatic Preference based DI-MOEA (AP-DI-MOEA) where DI-MOEA stands for Diversity-Indicator based Multi-Objective Evolutionary Algorithm). AP-DI-MOEA has two main characteristics: firstly, it generates the preference region automatically during the optimization; secondly, it concentrates the s...
Download Bibtex file
Daniela Aguirre Salazar , "Fast Classification of Driving Behavior Possibilities for Improved Trajectory Prediction", University of Kassel, 2021.
AbstractA fundamental part of the optimal performance of advanced driver assistance systems (ADAS) functions, such as trajectory planners, is to quickly classify other vehicles’ possible behavior. One way to approach this, assuming that both kinematic data from the other vehicles and road information are available, is to use traffic models to perform simulations of vehicle trajectories under the possible interaction scenarios between agents and, after c...
Download Bibtex file Per Mail Request
Nima Nabizadeh, Heiko Wersing, Dorothea Kolossa , "Leveraging Inter-step Dependencies for Information Extraction from Procedural Task Instructions ", Text, Speech, and Dialogue, Springer International Publishing, vol. 1, no. 1, issue 1, 2021.
AbstractWritten instructions are among the most prevalent means of transferring procedural knowledge. Hence, enabling computers to obtain information from textual instructions is crucial for future AI agents. Extracting information from a step of a multi-part instruction is usually performed by solely considering the semantic and syntactic information of the step itself. In procedural task instructions, however, there is a sequential dependency across en...
Download Bibtex file
Muhammad Haris, Mathias Franzius, Ute Bauer-Wersing , "Unsupervised Fast Visual Localization and Mapping with Slow Features", IEEE International Conference on Image Processing (ICIP), 2021.
AbstractVisual localization is the task of accurately estimating the camera's position in a known environment. State-of-the-art methods use the 3D structure of a scene for precise visual localization. However, 3D scene reconstruction is resource-intensive in terms of hardware requirements and computation time, making it infeasible to run on low-cost embedded hardware. Unsupervised spatial representation learning with SlowFeature Analysis (SFA) enables co...
Download Bibtex file
Raphael Wenzel, Malte Probst , Thomas H Weisswange, Tim Puphal, Julian Eggert , "Asymmetry-based behavior planning for cooperation at shared traffic spaces", IEEE Intelligent Vehicle Symposium 2021, 2021.
AbstractThis work is concerned with cooperative behavior planning in a class of scenarios called shared traffic space scenarios. The proposed method does not rely on car-to-car communication and can therefore be used in mixed-traffic as well. Shared traffic space scenarios share two characteristics: First, two agents compete for a limited resource (e.g. road space, place in an order) and second, the agents have to allocate those resources themselves by c...
Download Bibtex file Per Mail Request
Kyle Poland, Abdullah Makkeh, Aaron Gutknecht, Patricia Wollstadt, Anja Sturm, Michael Wibral , "A partial information decomposition for discrete and continuous variables", 2021 International Conference on Mathematical Neuroscience (ICMNS2021), 2021.
AbstractUnderstanding the information mechanisms inside dynamical complex systems often poses intricate questions. In neural systems, information is often represented by an ensemble of agents. Knowledge about how this information is distributed amongst those agents can lead to insights about how to distribute relevant information about a problem with respect to the available agents. These agents can, for instance, be taken to be neurons which are recorde...
Download Bibtex file Per Mail Request
Sebastian Schrom, Stephan Hasler, Jürgen Adamy , "Improved multi-source domain adaptation by preservation of factors", Image and Vision Computing, vol. 112, pp. 104209, 2021.
AbstractDomain Adaptation (DA) is a highly relevant research topic when it comes to image classification with deep neural networks. Combining multiple source domains in a sophisticated way to optimize a classification model can improve the generalization to a target domain. Here, the difference in data distributions of source and target image datasets plays a major role. In this paper, we describe based on a theory of visual factors how real-world scenes...
Download Bibtex file
Matti Krüger, Christiane Wiebel, Heiko Wersing , "Tactile Encoding of Directions and Temporal Distances to Safety Hazards Supports Drivers in Overtaking and Intersection Scenarios", Transportation Research Part F: Traffic Psychology and Behaviour, vol. 81, pp. 201-222, 2021.
AbstractSafe traffic participation requires continuous monitoring of the environment for potential safety hazards. Here we investigate, to what extent an interface using directed tactile stimuli to communicate temporal distances to approaching objects can make drivers feel supported and influence their driving safety. In contrast to previous studies, we focus on conditions in which the driver has relatively high levels of control over the criticality of...
Download Bibtex file
Thiago de Jesus de Araujo Rios, Bas van Stein, Thomas Bäck, Bernhard Sendhoff, Stefan Menzel , "Multi-Task Shape Optimization Using a 3D Point Cloud Autoencoder as Unified Representation", IEEE Transactions on Evolutionary Computation - Special Issue on Multi-task Evolutionary Computation, 2021.
AbstractThe choice of design representations, as of search operators, is central to the performance of evolutionary optimization algorithms, in particular for multi-task problems. The multi-task approach pushes further the parallelization aspect of these algorithms by solving simultaneously multiple optimization tasks using a single population. During the search, the operators implicitly transfer knowledge between solutions to the offspring, taking advan...
Download Bibtex file
Saif Sidhik, Mohan Sridharan, Dirk Ruiken , "Towards a Framework for Changing-Contact Robot Manipulation", Workshop at AAMAS 2021: Autonomous Robots and Multirobot Systems (ARMS) 2021, 2021.
AbstractWe describe a framework for changing-contact robot manipulation tasks, which require the robot to make and break contacts with objects and surfaces. The discontinuous interaction dynamics of such tasks make it difficult to construct and use a single dynamics model or control strategy for such tasks. For any target motion trajectory, the framework incrementally improves its prediction of when contacts will occur. This prediction and a model relati...
Download Bibtex file Per Mail Request
1 ... 58 59 60 61 62 63 ... 183
Follow us
