Search our Publications
Latest Publications
Jennifer Kreger, Lydia Fischer, Stephan Hasler, Thomas H Weisswange, Ute Bauer-Wersing , "A priori reliability prediction with meta-learning based on context information", International Conference on Artificial Neural Networks (ICANN), 2017.
AbstractMachine learning systems are used in a wide variability of tasks, where reliability is very important. Often from the output of these systems their reliability cannot directly be deduced. We propose an approach to predict the reliability of a machine learning system externally. We tackle this by using an additional machine learning component we call meta-learner. This meta-learner can use the original input as well as supplementary context inform...
Download Bibtex file
Mariusz Bujny, Nikola Aulig, Markus Olhofer, Fabian Duddeck , "Identification of optimal topologies for crashworthiness with the evolutionary level set method ", International Journal of Crashworthiness, vol. 23, no. 4, pp. 395-416, 2017.
AbstractStructural topology optimisation methods are well established in many engineering disciplines. However, for highly non-linear problems, including crashworthiness, methods are less developed and still subject to active research. In particular, due to the simplifications made in the state-of-the-art methods as well as heuristic character of most of them, the optimality of the obtained structures is arguable. In this paper, a topology optimisation ...
Download Bibtex file
Andreas Johannes Richter, Stefan Menzel, Mario Botsch , "Preference-guided Adaptation of Deformation Representations for Evolutionary Design Optimization", IEEE Congress on Evolutionary Computation, pp. 2110-2119, 2017.
AbstractA dynamic industrial design optimization requires high-quality optimization algorithms as well as adaptive representations to find the global solution for a given problem. For adapting the representation to changing environments or to new input we utilize the concept of evolvability, which in our interpretation consists of three criteria: variability, regularity, and improvement potential, where regularity and improvement potential characterize c...
Download Bibtex file
Xiaofen Lu, Stefan Menzel, Ke Tang, Xin Yao , "Cooperative Co-evolution based Design Optimisation: A Concurrent Engineering Perspective", IEEE Transactions on Evolutionary Computation, 2017.
AbstractAs a well-known engineering practice, concurrent engineering (CE) considers all elements involved in a product’s life cycle from the early stages of product development, and emphasises executing all design tasks simultaneously. As a result, there exist various complex design problems in CE, which usually have many design parameters or require different disciplinary knowledge to solve them. To address these problems and enable concurrent design, d...
Download Bibtex file
Sheng Dong, Lars Gräning, Allen Sheldon , "Parametric Optimization for CAE Models of Carbon-Fiber Reinforced Plastic (CFRP) Composite Material ", NAFEMS World Congress 2017, 2017.
AbstractCarbon-fiber-reinforced plastic (CFRP) composite material, due to its high strength but light weight, has been increasingly employed in aerospace, automotive, and civil engineering. However, the non-isotropic properties across the layers of composites, due to different fiber orientations, create challenges in modeling the CFRP parts both all by themselves and when integrated into entire mechanical systems. The basic properties in and out of fiber...
Download Bibtex file
Edoardo Casapietra, Thomas H Weisswange, Franz Kummert, Christian Goerick , "Improving spatial trajectory planning by using an enhanced road representation", 4th International Symposium on Future Active Safety Technology: Toward zero traffic accidents (FAST-zero'17), 2017.
AbstractThe detection of road layout and semantics is an important issue in modern ADAS and autonomous driving systems. In particular, trajectory planning needs a spatial road representation to operate on. As typical trajectories are computed for time-spans in the order of a few seconds, the spatial range needed for the road representation to achieve a stable and smooth trajectory can go from tenths to hundreds of meters. This range is very hard to achie...
Download Bibtex file
Michael Gienger and Jochen Steil , "Humanoid kinematics and dynamics: Open Questions and Future Directions", Humanoid Robotics: a Reference (Book chapter), Springer, Springer, 2017.
Download Bibtex fileNils Einecke, Keiji Muro, Jörg Deigmöller, Mathias Franzius , "Working area mapping with an autonomous lawn mower", Field and Service Robotics, pp. 351-365, 2017.
AbstractIn this work we show a new technique for loop closing using the special setup of autonomous lawn mowers. By estimating the movement while travelling around the border wire we get a first shot estimation of the the boundary. This will not be very precise. Additionally, using a loop closing at the base station and by distributing the end point error depending on the estimated motion at each time step, the results are strongly improved. Furthermore...
Download Bibtex file
Viktor Losing, Barbara Hammer, Heiko Wersing , "Incremental On-line learning: A review and comparison of state of the art algorithms", Neurocomputing, vol. 275, pp. 1261-1274, 2017.
AbstractRecently, incremental and on-line learning gained more attention especially in the context of big data and learning from data streams, conflicting with the traditional assumption of complete data availability. Even though a variety of different methods are available, it often remains unclear which of them is suit- able for a specific task and how they perform in comparison to each other. We analyze the key properties of seven popular increme...
Download Bibtex file
Yuka Ogino, Ryoya Iida, Tobias Rodemann , "Using Desirability Functions for Many-Objective Optimization of a Hybrid Car Controller", GECCO 2017 Conference Companion, 2017.
AbstractIn this work we investigate the recently proposed concept of desirability functions for a many-objective optimization of a prototypical application problem, a hybrid car controller where the seven objectives are from many different domains. We compare the results of the optimization with a standard optimization in terms of hypervolume and the ease with which a solution can be picked. We also analyze the impact of wrongly defined desirability func...
Download Bibtex file
1 ... 89 90 91 92 93 94 ... 183
Follow us
