Martina Hasenjäger, Martin Ernst Heckmann, Heiko Wersing , "A survey of personalized driver assistance systems", IEEE Transactions on Intelligent Vehicles, vol. 5, no. 2, pp. 335 - 344, 2020.
AbstractThe field of advanced driver assistance systems (ADAS) has matured towards more and more complex assistance functions, applied with wider scope and a strongly increasing number of possible users due to wider market penetration. To deal with such a large variety of use conditions and usage patterns, personalization methods have been developed to ensure optimal user experience. In this paper we develop a general conceptual framework to personalizat...
Christiane Wiebel, Matti Krüger, Martina Hasenjäger , "Interactions between Inter-and Intraindividual Differences in Eye Movements in a Visual Search Task", UMAP (User Modeling and Personalization) , 2020.
AbstractUnderstanding the role of individual factors on gaze behavior has important implications for gaze-based applications and theoretical work. Previous work has shown individual differences for fixation durations across tasks and time (e.g.: [Henderson and Luke 2014]) and that differences in scan patterns relate to individual differences in cognitive capacities [Hayes and Henderson 2017]. In the real world, however, we often encounter one task ...
Thiago de Jesus de Araujo Rios, Stefan Menzel, Bernhard Sendhoff , "Engineering Data and Descriptors (ECOLE Deliverable 1.1)", ECOLE Project Deliverables, 2020.
AbstractOur research in the ECOLE project aims at generating computational models for capturing the notion of experience, which is embedded on data collected over the course of sets of optimizations, and exploiting said experience in similar, yet more challenging, optimization tasks. This vision of experience follows the analogy of an engineer who also collects, abstracts and utilizes her/his professional experience built while working on different types...
Thomas Schmitt, Tobias Rodemann, Jürgen Adamy , "Multi-Objective Model Predictive Control for Microgrids", at-Automatisierungstechnik, vol. 68, no. 8, pp. 687-702, 2020.
AbstractEconomic model predictive control is applied to a simplified linear microgrid model. Monetary costs and thermal comfort are simultaneously optimized by using Pareto optimal solutions in every time step. The effects of different metrics and normalization schemes for selecting knee points from the Pareto front are investigated. For German industry pricing with nonlinear peak costs, a linear programming trick is applied to reformulate the optimizati...
Ye Tian, Shichen Peng, Tobias Rodemann, Xingyi Zhang, Yaochu Jin , "Automatic Algorithm Selection for Evolutionary Multi-Objective Optimization", 2019 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 3225-3232, 2020.
AbstractIn the last two decades, many evolutionary algorithms have shown promising performance in solving a variety of multi-objective optimization problems (MOPs). Since there does not exist an evolutionary algorithm having the best performance on all the MOPs, it is unreasonable to use a single evolutionary algorithm to tackle all the MOPs. Since many real-world MOPs are computationally expensive, selecting the best evolutionary algorithm from multip...
Chao Wang, Stephan Hasler, Manuel Mühlig, Frank Joublin, Antonello Ceravola, Jörg Deigmöller, Lydia Fischer , "Designing Interaction for Multi-agent System in an Office Environment", CHINESE CHI 2020, 2020.
AbstractFuture intelligent system will involve very various types of artificial agents, such as mobile robots, smart home infrastructure, or personal devices, which share data and collaborate with each other to execute certain tasks. Designing an efficient human-machine interface, which can support users to express needs to the system, supervise the collaboration progress of different entities, and evaluate the result, will be challenging. This paper pre...
Thomas Jatschka, Tobias Rodemann, Guenther Raidl , "A Large Neighborhood Search for Distributing Service Points in Mobility Applications with Capacities and Limited Resources", CPAIOR 2020, Vienna, 2020.
AbstractIn a previous work we presented a cooperative optimization algorithm for distributing service points with special focus on mobility applications. The problem formulation considered there, called the Service Point Distribution Problem (SPDP), more or less corresponds to a rather generic facility location problem, and the focus was on an interactive optimization approach in which a broader base of potential users provides iteratively feedback on s...
Guo Yu, Yaochu Jin, Markus Olhofer , "Benchmark Problems and Performance Indicators for Search of Knee Points in Multi-objective Optimization", IEEE Transactions on Cybernetics, pp. 3531-3544, 2020.
AbstractDuring the preference-based optimization, the decision makers (DMs) are hard to understand the problem without priori knowledge and give their preference information. Also, solutions have many features, and the searching space is very large and usually not homogenious. Depending on the features, the solutions are more less important, while important might be problem dependent. This can be eg. knee points, robust areas, etc. Therefore, the prefere...
Julian Eggert, Jörg Deigmöller, Lydia Fischer, Andreas Richter , "Action Representation for Intelligent Agents using Memory Nets", Communications in Computer and Information Science, 2020.
AbstractMemory Nets (Eggert et al.: Memory Nets: Knowledge Rep- resentation for Intelligent Agent Operations in Real World, 2019) are a knowledge representation schema targeted at autonomous Intelligent Agents (IAs) operating in real world. Memory Nets are targeted at lever- aging the large body of openly available semantic information, and incre- mentally accumulating additional knowledge from situated interaction. Here we extend the Memory Net co...
Julian Eggert , "TTX Risk Measures Derived from General Survival Theory", ITSC 2020, pp. 1115-1122, 2020.
AbstractAlthough intelligent Advanced Driving Assistance Systems and Autonomous Driving technologies are becoming ubiquitous, efficient and safe driving in dynamic, narrow or congested environment remains a theoretical and technological challenge. The reason mainly lies in the complexity of handling prediction and uncertainty, which are the fundamental ingredients for risk estimation. The theoretical shortcomings can be seen on the level of mesoscopic ri...