Search our Publications
Latest Publications
Charlie Street, Bruno Lacerda, Manuel Mühlig, Nick Hawes , "Multi-Robot Planning Under Uncertainty with Congestion-Aware Models", Nineteenth International Conference on Autonomous Agents and Multi-Agent Systems , 2020.
AbstractWhen planning for multi-robot navigation tasks under uncertainty, plans should prevent robots from colliding while still reaching their goal. Solutions achieving this fall on a spectrum. At one end are solutions which prevent robots from being in the same part of the environment simultaneously at planning time, ignoring the robots’ capabilities to manoeuvre around each other, whilst at the other end are solutions that solve the problem at executi...
Download Bibtex file
Theodoros Georgiou, Sebastian Schmitt, Thomas Bäck, Michael Lew , "Norm loss: A simple and effective regularization method for deep convolutional neural networks", International Conference on Pattern Recognition (ICPR), 2020.
AbstractIn this paper we investigate the norm loss as novel reglarization method for neural networks....
Download Bibtex file Per Mail Request
Theodoros Georgiou, Sebastian Schmitt, Markus Olhofer, Thomas Bäck, Michael Lew , "Comparison of deep learning and hand crafted features for mining simulation data", International Conference on Pattern Recognition, 2020.
AbstractComputational Fluid Dynamics (CFD) simulations are very important for a plethora of industrial applications, such as optimization of aerodynamic properties of different engineering designs, e.g. cars, airplanes etc.. The output of these simulations can become very complex and hard to interpret due to their high dimensionality (3D space + time dependence with more than six values per point in the space-time). There have been many works that try to...
Download Bibtex file Per Mail Request
Bernhard Sendhoff and Heiko Wersing , "Cooperative Intelligence - A Humane Perspective", IEEE International Conference on Human-Machine Systems, 2020.
AbstractIn this contribution we outline our concept of cooperation between humans and intelligent systems which we denote as cooperative intelligence. We argue from a human perspective and emphasize the advantages of keeping the human in the loop rather than targeting autonomous systems. Our focus is respecting human values such as retaining competences, sharing experiences, and self-esteem. We discuss process-oriented requirements for intuitive co...
Download Bibtex file Per Mail Request
Timo Friedrich, Patricia Wollstadt, Stefan Menzel , "The effects of non-linearity operators in voxel-based 3D neural networks for shape reconstruction", IEEE Symposium Series on Computational Intelligence (SSCI), 2020.
AbstractNeural Style Transfer has been successfully applied for generating a plausible novel 2D image based on existing image content and the style of a painting, with further extensions to image, video, motion and animation manipulation. Follow up works have realized 2D/3D hybrid approaches relying on 2D rendering operations for first steps towards 3D shape manipulation. However, for an end-to-end 3D Neural Style Transfer we suggested 3D voxel-based neu...
Download Bibtex file
Martin Ernst Heckmann , "Spoken Language Interaction with Virtual Agents and Robots based on Transparency, Situatedness and Personalization", Dagstuhl Seminar Spoken Language Interaction with Virtual Agents and Robot (SLIVAR), 2020.
AbstractSpoken Language Interaction with Virtual Agents and Robots based on Transparency, Situatedness and Personalization When two humans engage in an interaction, two independent minds with different experiences and views on the world come together. To make this joint activity a success, they have to work together. They need to align their mental representations to be able to form a common ground and define a joint goal for the interaction (Clar...
Download Bibtex file
Rodrigo Canaan, Xianbo Gao, Youjin Chung, Julian Togelius, Andy Nealen, Stefan Menzel , "Behavioral Evaluation of Hanabi Rainbow DQN agents and Rule-based agents", AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE-20), 2020.
AbstractHanabi is a multiplayer cooperative card game, where only your partners know your cards. All players succeed or fail together. This makes the game an excellent testbed for studying collaboration. Recently, it has been shown that deep neural networks can be trained through self-play to play the game very well. However, such agents generally do not play well with others. In this paper, we investigate the consequences of training Rainbow DQN agents ...
Download Bibtex file
Matti Krüger, Heiko Wersing, Christiane Wiebel , "The Lateral Line: Augmenting Spatiotemporal Perception with a Tactile Interface", AHs ’20: Augmented Humans International Conference, 2020.
AbstractIn this paper we investigate a novel tactile interface concept for artificially enhancing peoples' spatiotemporal perception. Our target is to improve performance in tasks that rely on a fast and accurate understanding of movement dynamics in the environment. To provide an exemplary research and application scenario, we implemented a prototype of the concept in a driving simulation environment and used a belt capable of providing directional vi...
Download Bibtex file
Xilu Wang, Yaochu Jin, Sebastian Schmitt, Markus Olhofer , "An Adaptive Bayesian Approach to Surrogate-Assisted Evolutionary Multi-objective Optimization", Information Sciences, 2020.
AbstractSurrogate models have been widely used for solving computationally expensive multi-objective optimization problems (MOPs). The efficient global optimiza- tion (EGO) algorithm, a Bayesian approach to surrogate-assisted optimization, has become very popular in surrogate-assisted evolutionary optimization. In this paper, we propose an adaptive Bayesian approach to surrogate-assisted evolutionary algorithm to solve expensive MOPs. The main idea ...
Download Bibtex file
Guo Yu, Yaochu Jin, Markus Olhofer , "A Multi-objective Evolutionary Algorithm for Finding Knee Regions Using Two Localized Dominance Relationships", IEEE Transactions on Evolutionary Computation, 2020.
AbstractIn preference based optimization, knee points are considered the naturally preferred trade-off solutions, especially when the decision-maker has little a priori knowledge about the problem to be solved. However, identifying all convex knee regions of a Pareto front remains extremely challenging, in particular in a high-dimensional objective space. This paper presents a new evolutionary multi-objective algorithm for locating knee regions using two...
Download Bibtex file
1 ... 70 71 72 73 74 75 ... 183
Follow us
