Search our Publications
Latest Publications
Qiqi Liu, Yaochu Jin, Martin Heiderich, Tobias Rodemann , "Adaptation of Reference Vectors for Evolutionary Many-objective Optimization of Problems with Irregular Pareto Fronts", Proceedings of IEEE Conference on Evolutionary Computation (CEC), pp. 1726-1733, 2019.
AbstractMost decomposition-based algorithms are designed based on the assumption that the Pareto Front (PF) has a regular geometrical structure, i.e, it is smooth, continuous, and well spread. Irregular problems are problems with discontinuous, degenerated, or inverted Pareto fronts, which just take up parts of the objective space. So when decomposition based algorithms are used to solve irregular problems, they do not perform well. The reason is that no...
Download Bibtex file
Manuel Dietrich , "Towards Privacy-preserving Personalized Social Robots By Enabling Dynamic Boundary Management", Proceedings of the Workshop on Personalization in Long-Term Human-Robot Interaction at the 2019 International Conference on Human-Robot Interaction, 2019.
AbstractDesigning personalized social robots, which should become an intrinsic part of everyday life, raises new challenges on how to respect the privacy of people interacting with them. In this paper, we introduce a little recognized conceptual perspective on privacy which, in our opinion, is highly relevant for the design of personalized social robots. This conceptual perspective, introduced by Irwin Altman (Altman 1975) highlights that in everyday soc...
Download Bibtex file
Tim Puphal, Malte Probst , Julian Eggert , "Comfortable Priority Handling with Predictive Velocity Optimization for Intersection Crossings", Intelligent Transportation Systems Conference, 2019.
AbstractWe address the problem of motion planning for four-way intersection crossings with right-of-ways. Road safety typically assigns liability to the follower in rear-end collisions and to the approaching vehicle required to yield in side crashes. As an alternative to previous models based on heuristic state machines, we propose a planning framework which changes the prediction model of other cars (e.g., their prototypical accelerations and decelerati...
Download Bibtex file
Michael J. Mathew, Saif Sidhik, Mohan Sridharan, Morteza Azad, Akinobu Hayashi, Jeremy Wyatt , "Online Learning of Feed-Forward Models for Task-Space Variable Impedance Control", IEEE-RAS International Conference on Humanoid Robots, 2019.
AbstractDuring the initial trials of a novel manipulation task, humans tend to keep their arms considerably stiff in order to reduce the effects of any unforeseen disturbances on the ability to perform the task accurately. After a few repetitions, humans reduce and adapt the stiffness of their arms without any significant reduction in task performance. Research in human motor control strongly indicates that humans learn and continuously revise internal m...
Download Bibtex file
Fabio Muratore, Michael Gienger, Jan Peters , "Assessing Transferability from Simulation to Reality for Reinforcement Learning", Arxiv.org e-print archive, 2019.
AbstractLearning robot control policies from physics simulations is of great interest for the robotics community as it may render the learning process faster, cheaper, and safer by alleviating the need for expensive real-world experiments. However, the direct transfer of the learned behavior from simulation to reality is a major challenge. Optimizing a policy on a slightly faulty simulator can easily lead to the maximization of the ‘Simulation Optimizati...
Download Bibtex file
Timo Friedrich and Stefan Menzel , "Standardization Of Gram Matrix For Improved 3D Neural Style Transfer", IEEE Symposium Series on Computational Intelligence, 2019.
AbstractNeural Style Transfer based on convolutional neural networks has produced visually appealing results for image and video data in the recent years where e.g. the content of a photo and the style of a painting are merged to a novel piece of digital art. In practical engineering development, we utilize 3D objects as standard for optimizing digital shapes. Since these objects can be represented as binary 3D voxel representation, we propose to extend ...
Download Bibtex file
Yali Wang, Steffen Limmer, Markus Olhofer, Michael Emmerich, Thomas Bäck , "Vehicle Fleet Maintenance Scheduling by Multi-objective Evolutionary Algorithms", 2019 IEEE Congress on Evolutionary Computation (CEC), pp. 442-449, 2019.
AbstractIn this paper, a new real-world application problem, i.e., the vehicle fleet maintenance scheduling optimization problem, is defined and a specialized multi-objective evolutionary algorithm framework (grouping strategy, three vector chromosome and corresponding genetic operators) is proposed to solve the problem. State-of-the-art multi-objective evolutionary algorithms such as NSGA-III, SMS-EMOA, DI-MOEA are employed in the proposed algorithm fr...
Download Bibtex file
Fabio Muratore, Michael Gienger, Jan Peters , "Assessing Transferability in Reinforcement Learning from Randomized Simulations", Multidisciplinary Conference on Reinforcement Learning and Decision Making, 2019.
AbstractExploration-based reinforcement learning of control policies on physical systems is generally time-intensive and can leadto catastrophic failures. Therefore, simulation-based policy search appears to be an appealing alternative. Unfortunately,running policy search on a slightly faulty simulator can easily lead to the maximization of the ‘Simulation OptimizationBias’ (SOB), where the policy exploits modeling errors of the simulator such that the r...
Download Bibtex file
Jiawen Kong, Wojtek Kowalczyk, Duc Anh Nguyen, Stefan Menzel, Thomas Bäck , "Hyperparameter Optimisation for Improving Classification under Class Imbalance", IEEE Symposium Series on Computational Intelligence, 2019.
AbstractAlthough the class-imbalance classification problems have caught a huge amount of attention, hyperparameter optimisation has not been studied in detail in this field. Both classification algorithms and resampling techniques involve some hyperparameters that can be tuned. This paper sets up several experiments and draws the conclusion that, compared to using default hyperparameters, applying hyperparameter optimisation for both classification algo...
Download Bibtex file
Stefan Menzel and Timo Friedrich , "Addressing Complex Engineering Systems: The Value Of Evolvability ", IEEE Symposium Series on Computational Intelligence, 2019.
AbstractWhile engineering systems in the automotive development process not only become increasingly complicated, the necessary consideration of time-dependencies shifts the focus furthermore towards system complexity. For an efficient decision-making flow, i.e. making the right decision at the right point in time, it is important to consider simultaneously both engineering paradigms – on the one hand to accurately and computationally efficient solve the...
Download Bibtex file
1 ... 77 78 79 80 81 82 ... 183
Follow us
