@inproceedings{, author = {Kr{\"{a}}mmer, Annkathrin and Sch{\"{o}}ller, Christoph and Gulati, Dhiraj and Lakshminarasimhan, Venkatnarayanan and Kurz, Franz and Rosenbaum, Dominik and Lenz, Claus and Knoll, Alois}, title = {Providentia - A Large-Scale Sensor System for the Assistance of Autonomous Vehicles and Its Evaluation}, booktitle = {Journal of Field Robotics}, year = {2022}, month = jun, abstract = {The environmental perception of an autonomous vehicle is limited by its physical sensor ranges and algorithmic performance, as well as by occlusions that degrade its understanding of an ongoing traffic situation. This not only poses a significant threat to safety and limits driving speeds, but it can also lead to inconvenient maneuvers. Intelligent Infrastructure Systems can help to alleviate these problems. An Intelligent Infrastructure System can fill in the gaps in a vehicle's perception and extend its field of view by providing additional detailed information about its surroundings, in the form of a digital model of the current traffic situation, i.e. a digital twin. However, detailed descriptions of such systems and working prototypes demonstrating their feasibility are scarce. In this paper, we propose a hardware and software architecture that enables such a reliable Intelligent Infrastructure System to be built. We have implemented this system in the real world and demonstrate its ability to create an accurate digital twin of an extended highway stretch, thus enhancing an autonomous vehicle's perception beyond the limits of its on-board sensors. Furthermore, we evaluate the accuracy and reliability of the digital twin by using aerial images and earth observation methods for generating ground truth data.}, } @inproceedings{, author = {Kr{\"{a}}mmer, Annkathrin and Sch{\"{o}}ller, Christoph and Kurz, Franz and Rosenbaum, Dominik and Knoll, Alois}, title = {Vorausschauende Wahrnehmung f{\"{u}}r sicheres automatisiertes Fahren: Validierung intelligenter Infrastruktursysteme am Beispiel von Providentia}, booktitle = {Internationales Verkehrswesen}, year = {2020}, month = feb, abstract = {Intelligente Infrastruktursysteme k{\"{o}}nnen den Wahrnehmungshorizont von automatisier-ten Fahrzeugen stark erweitern und dadurch sicheres, vorausschauendes Fahren erm{\"{o}}g-lichen. Daf{\"{u}}r muss klar sein, wie genau das von ihnen erstellte Abbild der aktuellen Verkehrssituation ist. Aufgrund der fehlenden Grundwahrheit der Fahrzeugpositionen gestaltet sich eine Validierung jedoch schwierig, es bedarf neuer Ideen. In diesem Artikel wird am Beispiel des Providentia-Systems ein Konzept pr{\"{a}}sentiert, wie intelligente Infrastruktursysteme mittels Luftbildauswertung validiert werden k{\"{o}}nnen.}, } @inproceedings{, author = {Sch{\"{o}}ller, Christoph and Schnettler, Maximilian and Kr{\"{a}}mmer, Annkathrin and Hinz, Gereon Michael and Bakovic, Maida and G{\"{u}}zet, M{\"{u}}ge and Knoll, Alois}, title = {Targetless Rotational Auto-Calibration of Radar and Camera for Intelligent Transportation Systems}, booktitle = {Intelligent Transportation Systems Conference (ITSC)}, publisher = {IEEE}, year = {2019}, month = oct, address = {Auckland, New Zealand}, location = {Auckland, New Zealand}, abstract = {Most intelligent transportation systems use a combination of radar sensors and cameras for robust vehicle perception. The calibration of these heterogeneous sensor types in an automatic fashion during system operation is challenging due to differing physical measurement principles and the high sparsity of traffic radars. We propose - to the best of our knowledge - the first data-driven method for automatic rotational radar-camera calibration without dedicated calibration targets. Our approach is based on a coarse and a fine convolutional neural network. We employ a boosting-inspired training algorithm, where we train the fine network on the residual error of the coarse network. Due to the unavailability of public datasets combining radar and camera measurements, we recorded our own real-world data. We demonstrate that our method is able to reach precise and robust sensor registration and show its generalization capabilities to different sensor alignments and perspectives.}, } @inproceedings{Kraemmer2019a, author = {Kr{\"{a}}mmer, Annkathrin and Sch{\"{o}}ller, Christoph and Gulati, Dhiraj and Knoll, Alois}, title = {Providentia - A Large Scale Sensing System for the Assistance of Autonomous Vehicles}, booktitle = {Robotics Science and Systems Workshops ({RSS} Workshops)}, publisher = {RSS Foundation}, year = {2019}, month = jun, address = {Freiburg, Germany}, abstract = {The environmental perception of autonomous vehicles is not only limited by physical sensor ranges and algorithmic performance, but also occlusions degrade their understanding of the current traffic situation. This poses a great threat for safety, limits their driving speed and can lead to inconvenient maneuvers that decrease their acceptance. Intelligent Transportation Systems can help to alleviate these problems. By providing autonomous vehicles with additional detailed information about the current traffic in form of a digital model of their world, i.e. a digital twin, an Intelligent Transportation System can fill in the gaps in the vehicle's perception and enhance its field of view. However, detailed descriptions of implementations of such a system and working prototypes demonstrating its feasibility are scarce. In this work, we propose a hardware and software architecture to build such a reliable Intelligent Transportation System. We have implemented this system in the real world and show that it is able to create an accurate digital twin of an extended highway stretch. Furthermore, we provide this digital twin to an autonomous vehicle and demonstrate how it extends the vehicle's perception beyond the limits of its on-board sensors.}, keywords = {Intelligent Transportation Systems, Autonomous Driving, Robotics}, url = {https://sites.google.com/view/uad2019/accepted-posters}, } @inproceedings{Hinz2017, author = {Hinz, Gereon Michael and Buechel, Martin and Diehl, Frederik and Chen, Guang and Kr{\"{a}}mmer, Annkathrin and Kuhn, Juri and Lakshminarasimhan, Venkatnarayanan and Schellmann, Malte and Baumgarten, Uwe and Knoll, Alois}, title = {Designing a far-reaching view for highway traffic scenarios with {5G-}based intelligent infrastructure}, booktitle = {8. Tagung Fahrerassistenzsysteme}, publisher = {T{\"{U}}V S{\"{u}}d}, year = {2017}, month = nov, address = {Munich, Germany}, abstract = {Cooperative vehicle infrastructure systems offer significant potential for improved traffic safety, throughput and improved energy efficiency. Infrastructure sensors along the road can substitute vehicular sensor-sets, providing improved robustness and performance through different mounting positions and orientations, reducing occlusions, stationary locations, facilitating system-wide calibration, optimization for the specific traffic area in view, and vastly increase perception range by combining multiple measurement points. Communication via fifth Generation (5G) networks offers solutions to the corresponding substantial requirements for high bandwidth, low latency and high reliability for data and information communication. We propose a concept, which aims to provide a far-reaching view to (self-driving) vehicles and drivers with infrastructure sensors and 5G communication, as a cognitive system. The system detects and localizes traffic objects and predicts their future movements. The resulting information will be provided to traffic participants allowing for safer, more proactive and comfortable driving.}, keywords = {V2X, autonomous driving, connected cars, 5G, sensor-sets, far-reaching view, big data, environmental perception}, url = {https://mediatum.ub.tum.de/doc/1421303/1421303.pdf}, }