Steffen Limmer and Tobias Rodemann , "Combination of Charging Policies for Fair and Efficient EV Charging under Limited Capacity", 2024 22nd International Conference on Intelligent Systems Applications to Power Systems (ISAP), pp. 1-6, 2024.
AbstractRule-based charging control based on simple charging policies is a practical approach for distributing a limited amount of energy or power to electric vehicles of multiple users. Depending on the behavior and characteristics of the users, different efficiencies in terms of overall user satisfaction might be achieved with different charging policies. Analogously, users might be treated differently fairly by different policies in the sense that cer...
Stephan Hasler, Daniel Tanneberg, Michael Gienger , "Efficient symbolic planning with views", arxiv.org, 2024.
AbstractRobotic planning systems model spatial relations detailed as these are needed for manipulation tasks. In contrast to this, other physical attributes of objects and the effect of devices are usually oversimplified and expressed by abstract compound attributes, e.g., describing a piece of bread as toasted. This limits the ability of planners to find alternative solutions. We propose to break these compound attributes down into a shared set of eleme...
Jose Almeida, Joao Soares, Steffen Limmer, Ehsan Aliyan, Ricardo Faia, Fernando Lezama, Sergio Ramos, Zita Vale , "Community-Based Energy Sharing using Game Theory Approaches for Benefit Distribution", 2024 22nd International Conference on Intelligent Systems Applications to Power Systems (ISAP), pp. 1-6, 2024.
AbstractThis paper is centered on the concept of community-based energy sharing, focusing on the integration of electric vehicles and battery management systems. The study employs mixed integer linear programming optimization techniques to minimize the total energy costs of the entire community by maximizing energy sharing within it. The investigation focuses on exploring methods of distribution of benefits among community members considering BESS and E...
Hao Tong, Leandro L. Minku, Stefan Menzel, Bernhard Sendhoff, Xin Yao , "Evaluating Meta-heuristic Algorithms for Dynamic Capacitated Arc Routing Problems by Deriving Lower Bounds", IEEE Computational Intelligence Magazine, 2024.
AbstractMeta-heuristic algorithms, especially evolutionary algorithms, have been frequently used to find near optimal solutions to combinatorial optimization problems. The evaluation of such algorithms is often conducted through comparisons with other algorithms on a set of benchmark problems. However, even if one algorithm is the best among all those compared, it still has difficulties in determining the true quality of the solutions found because the ...
Philipp Brockmann, Hatim Ennayar, Max Lannert, Xulan Dong, Yuhao Cao, Sebastian Brulin, Ilia Roisman, Jeanette Hussong , "Enhancement of interfacial instabilities by solid particles during fast stretching of a liquid suspension bridge", 16th International Conference on Liquid Atomization and Spray Systems 2024, 2024.
AbstractIn this experimental study, the rapid stretching dynamics and interfacial instabilities of a suspension liquid bridge are studied using a highspeed video system. The bridge is formed between two parallel plates with an initial gap width ranging from 30 to 60 µm. One of the plates is fixed while the second plate moves with a constant acceleration whose magnitude reaches 180 m/s2. The particle size in the suspensions is varied from 6 to 40 µm. Fast...
Christian Internó, Elena Raponi, Niki van Stein, Thomas Bäck, Markus Olhofer, Yaochu Jin, Barbara Hammer , "Adaptive Model Pruning in Federated Learning through Loss Exploration", ICML 2024 Workshop on Advancing Neural Network Training , 2024.
AbstractThe rapid proliferation of smart devices coupled with the advent of 6G networks has profoundly reshaped the domain of collaborative machine learning. Alongside growing privacy-security concerns in sensitive fields, these developments have positioned federated learning (FL) as a pivotal technology for decentralized model training. Despite its vast potential, FL encounters challenges such as elevated communication costs, computational constraint, a...
Jonathan Huenten , "Exploring Stable Diffusion-based Text-to-image Tools", 2024.
AbstractIn this project, we explored two stable diffusion-based text-to-image tools, namely SDXL1.0 and Flux.1 (schnell) on their basic capabilities and performance using different parameters. We studied the results of both models using prompts from different topics and difficulty level by visual inspection. Both models show a very good quality and producing images for the given prompt but also struggle eventually with e.g. many objects, reflections or h...
Xilu Wang, Yaochu Jin, Sebastian Schmitt, Markus Olhofer , "Alleviating Search Bias in Evolutionary Bayesian Optimization with Many Heterogeneous Objectives", IEEE Transactions on Systems, Man and Cybernetics: Systems, vol. 54, no. 1, pp. 143-155, 2024.
AbstractMulti-objective optimization problems whose objectives have different evaluation costs are commonly seen in the real world. Such problems are now known as multi-objective optimization problems with heterogeneous objectives (HE-MOPs). So far, however, only a few studies have been reported to address HE-MOPs, and most of them focus on bi-objective problems with one fast objective and one slow objective. In this work, we aim to deal with HE-MOPs hav...
Theodoros Stouraitis and Michael Gienger , "Predictive and Robust Robot Assistance for Sequential Manipulation", Innovations and Applications of Human Modelling in Physical Human-Robot Interaction (ICRA 2024 Workshop), 2024.
AbstractThis extended abstract presents a novel concept to support physically impaired humans in daily object manipulation tasks with a robot. Given a user’s manipulation sequence, we pro- pose a predictive model that uniquely casts the user’s sequential behavior as well as a robot support intervention into a hierarchi- cal multi-objective optimization problem. A major contribution is the prediction formulation, which allows to consider several di...
Christian Internó, Elena Raponi, Niki van Stein, Thomas Bäck, Markus Olhofer, Yaochu Jin, Barbara Hammer , "Adaptive Hybrid Model Pruning in Federated Learning through Loss Exploration ", NeurIPS2024, International Workshop on Federated Foundation Models in Conjunction, 2024.
AbstractThe rapid proliferation of smart devices coupled with the advent of 6G networks has profoundly reshaped the domain of collaborative machine learning. Alongside growing privacy-security concerns in sensitive fields, these developments have positioned federated learning (FL) as a pivotal technology for decentralized model training. Despite its vast potential, specially in the age of complex foundation models, FL encounters challenges such as e...