Papers, articles, research results, videos and press materials from the Safe AI Engineering consortium.
Paper
- Manuel Schwonberg, Hanno Gottschalk: Domain Generalization for Semantic Segmentation: A Survey, Safe Artificial Intelligence for All Domains (SAIAD) at IEEE / CVF Computer Vision and Pattern
Recognition Conference (CVPR), Nashville, USA, 12.06.2025 - Kira Maag, Tobias J. Riedlinger, Hanno Gottschalk: Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object Detection, ICLR 2026, Rio de Janeiro, Brasil, 23.–27.04.2026
- Liangyu Zhong, Fabio Rosenthal, Joachim Sicking, Fabian Hüger, Thorsten Bagdonat, Hanno Gottschalk, Leo Schwinn: FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering, NeurIPS 2025, San Diego, USA, 02.–07.12.2025
- Ahmed Abouelazm, Johannes Ratz, Philip Schörner, J. Marius Zöllner: Diverse and Adaptive Behavior Curriculum for Autonomous Driving: A Student-Teacher Framework with Multi-Agent RL, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hangzhou, China, 19.10.2025
- Ahmed Abouelazm, Mohammad Mahmoud, Conrad Walter, Oleksandr Shchetsura, Erne Hussong, Helen Gremmelmaier, J. Marius Zöllner: Bridging Simulation and Usability: A User-Friendly Framework for Scenario Generation in CARLA, IEEE International Automated Vehicle Validation Conference (IAVVC), Baden-Baden, Germany, 30.09.–02.10.2025
- Thomas Geipel et al.: Using AI in Opportunity and Idea Management (ISO 56007) – Experiences of the Automotive Skills Alliance Innovation Agent Working Group, EuroSPI2025, Riga, Latvia, 17.09.25
- Franz Motzkus, Christian Schlauch, Sebastian Bernhard, Ute Schmid: Can I Trust My Trajectory Prediction Model?, Trust-AI Workshop, Bologna, Italy, 25.–27.10.2025
- Benjamin Herd, Jessica Kelly, Clarissa Heinemann, João-Vitor Zacchi: A Subjective Logic-based method for runtime confidence updates in safety arguments, SAC 2026 Symposium On Applied Computing, Thessaloniki, Greece, 23.03. – 27.03.26
- Benjamin Herd, Jessica Kelly, Jan Sabsch, Lydia Gauerhof: Towards a compositional semantics for quantitative confidence assessment in assurance arguments, European Dependable Computing Conference, Canterbury, United Kingdom, 07.04.26
- Benjamin Herd, Jessica Kelly, Reinhard Stolle: Temporal Monitoring of Agent Beliefs Under Uncertainty with Subjective LTL, AAAI Spring Symposium on Machine Learning and Knowledge Engineering for Knowledge-Grounded Semantic Agents, San Francisco, USA, 07.04. – 09.04.26
- Ahmed Abouelazm, Jonas Michel, Daniel Bogdoll, Philip Schörner, J. Marius Zöllner: Beyond Scalar Rewards: Distributional Reinforcement Learning with Preordered Objectives for Safe and Reliable Autonomous Driving, IEEE International Conference on Robotics & Automation 2026, Vienna, Austria, 01.06. – 05.06.26
Lucas Görnhardt, Timo Bartels, Niklas Schwarz, Tim Fingscheidt: Adversarial Attack and Disturbance Detection by Hadamard-Coded Output Representations for Object Detection and Semantic Segmentation, ECCV 2026 European Conference on Computer Vision, Malmö, Sweden, 08.09. – 13.09.26
Ahmed Abouelazm, Felix Klingebiel, Philip Schörner, J. Marius Zöllner: Uncertainty-Aware and Temporally Regulated Expert Advice in Reinforcement Learning for Autonomous Driving, IEEE International Conference on Intelligent Transportation Systems (ITSC), Naples, Italy, 15.09.26
Andreas Albrecht, Istvan Bognar, Himanshu Walia, Dinish K. Karunakaran, Thomas Geipel: A Data-Driven Engineering (DDE) Process for Verification and Validation of AI Systems, EuroSPI 2026, Cairo, Egypt, 01.09.26
Articles
Automobil + Motoren, 07.09.2026
Automatisiertes Fahren | KI sicher entwickeln: Die Safe AI Engineering Methodik | springerprofessional.de
Dr. Torsten Stiehm, Dr.-Ing. Sven Hallerbach, Dr. Elena Hoemann, Antje Loyal, Dr. Xinxing Wang, Andreas Rohatschek Striebel, Dr.-Ing. Lukas Hacker
Project Material
Midterm Event Results
The Safe AI Engineering Midterm Event took place at IAA Transportation in Hannover, Germany on 16 September 2026. Results can be found here.