Fabio Muratore, Felix Treede, Michael Gienger, Jan Peters , "Domain Randomization for Simulation-Based Policy Optimization with Transferability Assessment", Conference on Robot Learning (CoRL) - 2018 Edition, 2018.
AbstractLearning new policies on real robot systems is generically time-intensive and may lead to catastrophic robot failures. Therefore, simulation-based policy search ap- pears to be an appealing alternative. Unfortunately, running policy search on a slightly faulty simulator can easily lead to the maximization of the so-called ’op- timality gap’, where the policy exploits modeling errors of the simulator such that the resulting behavior can poten...
Lydia Fischer, Stephan Hasler, Jörg Deigmöller, Thomas Schnürer, Michael Redert, Ulrike Pluntke, Katrin Nagel, Chris Senzel, Andreas Richter, Julian Eggert , "Which tool to use? Grounded reasoning in everyday environments with assistant robots", International Cognitive Robotics Workshop (CogRob), 2018.
AbstractIn this paper, we present a reasoning agent embodied into a mobile robot that is able to explore its environment by a camera. The robot can infer missing knowledge given an intent and object by the user, like for example "I want to open a wine bottle". Available tools are shown to the robot and it finally recommends the most suitable one. The reasoning is on one hand side a static ontology that describes how to relate the intends like “ope...
Benedict Flade, Marcos Nieto, Gorka Vélez Isasmendi, Julian Eggert , "Lane Detection Based Camera to Map Alignment Using Open-Source Map Data", 21st International IEEE Conference on Intelligent Transportation Systems, 2018.
AbstractFor accurate self-localization of vehicles, many approaches rely on on the match between high definition (HD) 3D map data and sensor data obtained from laser scanners or camera images. However, when depending on HD-maps, any small changes of the road network have to be detected and the corresponding map section needs to be updated which is associated with considerable effort. As an alternative, in this paper we propose an approach which is able t...
Dennis Orth, Nico Andreas Steinhardt, Bram Bolder, Mark Dunn, Dorothea Kolossa, Martin Ernst Heckmann , "Analysis of a Speech-Based Intersection Assistant in Real Urban Traffic", The 21st IEEE International Conference on Intelligent Transportation Systems, 2018.
AbstractWe have recently proposed a speech-based on-demand intersection assistant, which supports the driver at urban intersections. It provides information on the current traffic situation on the right-hand side and recommends suitable gaps in the traffic. This system has previously assumed a more or less constant flow of the traffic. To also handle situations of more dynamic urban traffic, including vehicles that may be slowing down or stopping, we ha...
Jörg Deigmöller, Herbert Janßen, Nils Einecke, Oliver Fuchs , "Road Surface Scanning using Stereo Cameras for Motorcycles", Proceedings of the 14th International Conference on Computer Vision Theory and Applications, 2018.
AbstractActive and semi-active suspension systems for vehicles became quite popular in the recent years as they allow for a smoother and safer ride compared to conventional suspension systems. The performance of an active/semi-active suspension system can be even more improved if the road condition in front of the vehicle is known. Currently only a few luxury cars combine fully active suspension with stereo cameras for such a predictive adaptatio...
Tobias Rodemann and René Unger , "FMI-based Controller Development Environment for Building Control Systems", ESI SimulationX Conference, 2018.
AbstractThis paper describes a simulation system for a smart building complex that integrates local energy production, flexible loads and energy storage with electric mobility. Our target is to increase overall efficiency of the building complex and thus reduce costs and greenhouse gas emissions. To achieve this we developed a digital twin model of the considered building complex including energy supply and charging infrastructure utilizing the Green Cit...
Tamas Bates, Michael Gienger, Jens Kober , "Head-tracked off-axis perspective projection improves gaze readability of 3D virtual avatars", SIGGRAPH Asia Technical Briefs, 2018.
AbstractVirtual avatars have been employed in many contexts, from simple conversational agents to communicating the internal state and intentions of large robots when interacting with humans. Rarely, however, are they employed in scenarios which require non-verbal communication of spatial information or dynamic interaction from a variety of perspectives. When presented on a flat screen, many illusions and visual artifacts interfere with such applications...
Ran Cheng, Mohammad Nabi Omidvar, Amir H. Gandomi, Bernhard Sendhoff, Stefan Menzel, Xin Yao , "Solving Incremental Optimization Problems via Cooperative Coevolution", IEEE Transactions on Evolutionary Computation, 2018.
AbstractEngineering designs can involve multiple stages, where at each stage, the design models are incrementally modified and optimized. In contrast to traditional dynamic optimization problems where the changes are caused by some objective factors, the changes in such incremental optimization problems are usually caused by the modifications made by the decision makers during the design process. While existing work in the literature is mainly focused o...
Martin Ernst Heckmann , "Audio-visual Word Prominence Detection from Clean and Noisy Speech", Computer Speech and Language, 2018.
AbstractIn this paper we introduce the audio-visual detection of word prominence and investigate how the additional visual information can be used to increase the robustness when acoustic background noise is present. We evaluate the detection performance for each modality individually and also perform experiments using feature and decision fusion. Our experiments are based on a corpus with 11 English speakers which contains in addition to the speech si...
Florian Damerow, Tim Puphal, Benedict Flade, Yuda Li, Julian Eggert , "Intersection Warning System for Occlusion Risks using Local Dynamic Maps ", Intelligent Transportation Systems Magazine, 2018.
AbstractThis work addresses the problem of risk evaluation in limited observable traffic scenarios due to restricted sensory coverage. Here we concentrate on intersection scenarios, which are particularly difficult to access visually. To distinguish the area of sight, we employ ray casting on a local dynamic map consisting of road geometry and information about buildings occluding areas in the environment. Based on the reduced visibility area, we model ...