Search our Publications
Latest Publications
Mariusz Bujny, Nikola Aulig, Markus Olhofer, Fabian Duddeck , "Evolutionary Level Set Method for Crashworthiness Topology Optimization", ECCOMAS Congress 2016, 2016.
AbstractVehicle crashworthiness design belongs to one of the most complex problems considered in the design optimization. Physical phenomena that are taken into account in crash simulations range from complex contact modeling to mechanical failure of materials. This results in high nonlinearity of the optimization problem and involves remarkable amount of numerical noise and discontinuities of the objective functions that are being optimized. Consequentl...
Download Bibtex file Per Mail Request
Andrea Schnall and Martin Ernst Heckmann , "Speaker Adaptation for Word Prominence Detection with Support Vector Machines", Speech Prosody 2016, 2016.
AbstractIn this paper we propose a new adaptation method to improve the detection of prominent from non-prominent words. Prosodic cues are difficult to extract, due to the different features different speakers are using to express for example prominence in speech. To overcome the problem of variations from the pool of speakers used during training time and those encountered during deployment, in speech recognition speaker-adaptation techniques like fe...
Download Bibtex file
Nikola Aulig, Emily Nutwell, Stefan Menzel, Duane Detwiler , "Preference-based Topology Optimization of Body-in-white Structures for Crash and Static Loads", 14th LS-DYNA Conference 2016, 2016.
AbstractTopology optimization methods are increasingly applied tools for the design of lightweight structural concepts in the automotive design process. Ideally, topology optimization provides the optimum distribution of material within a user-defined design space for a given objective function. In the vehicle design process, two important objectives are to maximize stiffness of components for regular working conditions and to maximize energy absorption ...
Download Bibtex file
Federico Moro, Michael Gienger, Ambarish Goswami , "GUEST EDITORIAL OF THE SPECIAL ISSUE ON WHOLE-BODY CONTROL FOR ROBOTS IN THE REAL WORLD", International Journal of Humanoid Robotics, vol. 13, no. DOI: 10.1142/S0219843616020011 , 2016.
AbstractResearch in whole-body control (WBC) aims to contribute to provide robots with those capabilities that are necessary to move and perform in real world scenarios. Until recent years, limitations on hardware relegated whole-body control to almost purely theoretical research. Recently a growing number of experimental platforms have become available (in particular torque-controlled humanoids). This new opportunity has triggered the deployment on...
Download Bibtex file
Nikola Aulig and Markus Olhofer , "State-based Representation for Structural Topology Optimization and Application to Crashworthiness", Proceedings of: IEEE Congress on Evolutionary Computation, 2016.
AbstractStructural topology optimization is a valuable tool for designers and engineers to obtain concepts of mechanical structures early in a design process. When applying evolutionary algorithms to topology optimization, due to the high-dimensionality of a typical topology optimization problem the representation of the structure is especially important. In this work we propose a novel adaptive state-based representation, taking the phenotypic, physical...
Download Bibtex file
Nikola Aulig and Markus Olhofer , "Evolutionary Computation for Topology Optimization of Mechanical Structures: An Overview of Representations", Proceedings of: IEEE Congress on Evolutionary Computation, 2016.
AbstractDuring the past decade, continuum topology optimization became a standard industrial tool for the conceptual design of mechanical structures. Efficient gradient-based mathematical topology optimization methods exist that can be applied for large-scale problems. However, in some cases gradient information is difficult to obtain, or problems show strong nonlinearity rendering the application of a gradient-based method impractical. In these cases, o...
Download Bibtex file
Mariusz Bujny, Nikola Aulig, Markus Olhofer, Fabian Duddeck , "Hybrid Evolutionary Approach for Level Set Topology Optimization", IEEE Congress on Evolutionary Computation, 2016.
AbstractAlthough Topology Optimization is widely used in many industrial applications, it is still in the initial phase of development for highly nonlinear, multimodal and noisy problems, where the analytical sensitivity information is either not available or difficult to obtain. Since for such problems, gradient-based methods cannot be applied, a search for alternative approaches is inevitable. One possibility is a use of Evolutionary Algorithms, which ...
Download Bibtex file
Lydia Fischer, Barbara Hammer, Heiko Wersing , "Online Metric Learning for an Adaptation to Confidence Drift", International Joint Conference on Neural Networks, pp. 748-755, 2016.
AbstractOne of the main aims of life-long learning architectures is to efficiently and reliably cope with the stability-plasticity dilemma. A powerful solution of this dilemma combines a static offline classifier, which preserves ground knowledge that should be respected during training, with an incremental online learning of new or specific information encountered during use. A successful realisation of this idea has been published lately based on intui...
Download Bibtex file
Edoardo Casapietra, Thomas H Weisswange, Franz Kummert, Christian Goerick , "Inferring a Grid-based Road Representation from the behavior of real world traffic participants", IEEE Intelligent Vehicles Symposium 2016, pp. 1185-1191, 2016.
AbstractThe detection of road area in the surroundings of the ego-vehicle is a key issue for modern ADAS. Camera-based direct detection systems are able to reliably accomplish this task only within a limited spatial range or in very simple environment, due to hardware limitations and unfavorable situations, e.g. shadows or occlusions. In complex environments, like inner city, the traffic is a real issue, since the mere presence of other cars can signific...
Download Bibtex file
Andreas Johannes Richter, Jascha Achenbach, Stefan Menzel, Mario Botsch , "Evolvability as a Quality Criterion for Linear Deformation Representations in Evolutionary Optimization", IEEE Congress on Evolutionary Computation, 2016.
AbstractIndustrial product design is characterized by increasing complexity due to the high number of involved parameters, objectives, and boundary conditions, all typically changing over time. Population-based evolutionary design optimization targets to solve these kinds of application problems, offering efficient algorithms striving for high-quality solutions. An important factor in the optimization setup is the representation, which defines the encodi...
Download Bibtex file
1 ... 93 94 95 96 97 98 ... 183
Follow us
