TY - JOUR A1 - Siefke, Lennart A1 - Sommer, Volker A1 - Wudka, Björn A1 - Thomas, Carsten T1 - Robotic Systems of Systems Based on a Decentralized Service-Oriented Architecture JF - Robotics KW - autonomous robotics KW - multi-robot systems KW - systems of systems KW - service-oriented architectures KW - multi-agent systems Y1 - 2020 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:523-14461 SN - 2218-6581 VL - 9 IS - 4 PB - MDPI ER - TY - JOUR A1 - Hiebert, Tina A1 - Hofstetter, Florian A1 - Thomas, Carsten A1 - Mushtaq, Savera A1 - Kaan, Eero A1 - Parameswaran, Biranavan ED - Torres-Sospedra, Joaquín T1 - Labels4Rails: A Railway Image Annotation Tool and Associated Reference Dataset JF - Data N2 - The development of autonomous train systems relies heavily on machine learning (ML) models, which in turn depend on large, high-quality annotated datasets for training and evaluation. The railway domain lacks adequate public datasets and efficient annotation tools. To address this gap, we present Labels4Rails, a tool designed specifically for the annotation of railway scenes. It captures track topology, switch states including switch directions, and informational tags regarding the images’ content and leverages consistent camera perspectives and the fixed track geometries inherent to railways for annotation efficiency. We used Labels4Rails to create the L4R_NLB reference dataset from Norwegian railway footage. The dataset contains 10,253 annotated images across four seasons, including 1415 switch annotations. Both the tool and dataset are publicly available. KW - Artificial intelligence KW - rail transportation KW - autonomous train operation KW - artificial intelligence KW - computer vision KW - track detection KW - switch detection KW - annotation KW - dataset KW - Computer Vision Y1 - 2025 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:523-22070 SN - 2306-5729 VL - 10 IS - 12 PB - MDPI ER - TY - JOUR A1 - Jaß, Philipp A1 - Thomas, Carsten ED - Javaheri, Danial T1 - Using N-Version Architectures for Railway Segmentation with Deep Neural Networks JF - Machine Learning and Knowledge Extraction N2 - Autonomous trains require reliable and accurate environmental perception to take over safety-critical tasks from the driver. This paper investigates the application of N-version architectures to rail track detection using Deep Neural Networks (DNNs) as a means to improve the safety of machine learning (ML)-enabled perception systems. We combine three different neural network architectures (WCID, VGG16-UNet, MobileNet–SegNet) in a 3M1I configuration. In this configuration, we apply two fusion methods to increase accuracy and to enable error detection: Maximum Confidence Voting (MCV), combining the DNN predictions at the image level, and Pixel Majority Voting (PMV), a novel approach for combining the predictions at the pixel level. In addition, we implement a new method for evaluating and combining prediction confidence values in the N-version architecture during runtime. We adjust the overall prediction confidence according to the conformity of all individual predictions, which is not possible with an individual network. Our results show that the N-version architecture not only enables a detection of erroneous predictions by utilizing those adjusted confidence values, but it can also partially improve the predictions by using the PMV combination algorithm. This work emphasizes the importance of model diversity and appropriate thresholds for an accurate assessment of prediction safety. These approaches can significantly improve the practical applicability of ML-based systems in safety-critical domains such as rail transportation. KW - Machine learning KW - machine learning KW - N-version KW - safety KW - autonomous rail systems KW - semantic segmentation KW - safety-critical AI KW - model diversity KW - confidence evaluation KW - rail track detection KW - N-version programming KW - Safety KW - Semantic Segmentation Y1 - 2025 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:523-20867 SN - 2504-4990 VL - 7 IS - 2 PB - MDPI ER -