Here you can download the KI Wissen public deliverables:

Public deliverables


D1 Catalogue, characterisation and representation of relevant domain knowledge for L3 to L5 driving functions / D4 Methods for data-independent validation of the predictions and decisions of an AI function

Deliverables 1 and 4(pdf:14 MB)

D2 Learning techniques for integrating formalised knowledge and network knowledge for training reduction and performance improvement

Deliverable 2(pdf:7 MB)

Scientific contributions and publications from KI Wissen are listed below:

  1. Dominik Grundt, Sorin Liviu Jurj: Verification of Sigmoidal Artificial Neural Networks using iSAT. Präsentiert auf dem 7th International Workshop on Symbolic-Numeric Methods for Reasoning about CPS and IoT.

  2. Gesina Schwalbe, Bettina Finzel: XAI Method Properties: A (Meta-)study. In: Data Mining and Knowledge Discovery, Special Issue on Explainable and Interpretable Machine Learning and Data Mining.

  3. Sorin Liviu Jurj, Dominik Grundt, Tino Werner, Philipp Borchers, Eike Möhlmann: Increasing the Safety of Adaptive Cruise Control using Physics-guided Reinforcement Learning. In: Energies, Special Issue "Advances in Automated Driving Systems".
  4. Gesina Schwalbe: Concept Embedding Analysis: A Review. In: Artificial Intelligence Review, März 2022.
  5. Daniel Bogdoll, Moritz Nekolla, Tim Joseph, J. Marius Zöllner: Quantification of Actual Road User Behavior on the Basis of Given Traffic Rules. In: 33rd IEEE Intelligent Vehicles Symposium, 05.-09.06.2022.
  6. Jörg Reichardt: Trajectories as Markov States for Long Term Traffic Scene Prediction. UniDAS FAS Workshop, 09.05.2022.
  7. Tianming Qiu: SViT: Hybrid Vision Transformer Models with Scattering Transform. In: 32nd IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2022), Xi'an, China, 22.08.2022.
  8. Sorin Liviu Jurj, Tino Werner, Dominik Grundt, Eike Möhlmann: Towards Safe and Sustainable Autonomous Vehicles using Environmentally-Friendly Criticality Metrics. Sustainability, Special Issue "Research on Sustainable Transportation and Urban Traffic”, 07.06.2022
  9. Dominik Grundt, Eike Möhlmann: Towards Runtime Monitoring of Complex System Requirements for Autonomous Driving Functions. In: Formal Methods for Autonomous Systems 2022.
  10. Abdul Hannan Khan, Mohsin Munir, Ludger van Elst: F2DNet: Fast Focal Detection Network for Pedestrian Detection. In: 26th International Conference on Pattern Recognition, Montréal, 22.-25.08.2022.
  11. Julian Wörmann, Daniel Bogdoll, Etienne Bührle, Han Chen, Evaristus Fuh Chuo, Kostadin Cvejoski, Tobias Gleißner, Philip Gottschall, Stefan Griesche, Christian Hellert, Christian Hesels, et al.: Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey.
  12. Alexander Steen, David Fuenmayor, Tobias Gleißner, Geoff Sutcliffe, Christoph Benzmüller: Automated Reasoning in Non-classical Logics in the TPTP World, Haifa, Israel, 11.08.2022
  13. Kumar Manas, Stefan Zwicklbauer, Adrian Paschke: Robust Traffic Rules and Knowledge Representation for Conflict Resolution in Autonomous Driving, Virtual, 26.09.22
  14. Abdul Hannan Khan: Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving, The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023, Vancouver Canada, 18.-22.06.2023
  15. Himanshu Agarwal, Christian Brunner, Tobias Latka, Stefan Pilar von Pilchau: A Causal Model for Physics-Conform Vehicle Trajectories, IEEE ITSC-2023, 24.-28.09.2023
  16. Adrien Wantiez, Tianming Qiu, Stefan Matthes, Hao Shen: Scene Understanding for Autonomous Driving Using Visual Question Answering, Gold coast, Queensland, Australia, 18 Jun 2023
  17. Yue Yao, Joerg Reichardt, Daniel Goehring: An Empirical Bayes Analysis of Object Trajectory Representation Models, ITSC 2023 Bilbao, Spain, 24.-28.09.2023
  18. Joshua Niemeijer Sudhanshu Mittal, Thomas Brox: Synthetic Dataset Acquisition for a Specific Target Domain, ICCV BRAVO Workshop, Paris, France, 3.10.2023
  19. Kumar Manas, Adrian Paschke: Legal Compliance Checking of Autonomous Driving with Formalized Traffic Rule Exceptions, ICLP 2023, London, UK, 09.07.2023

  20. Ya Wang, Adrian Paschke: Extracting Interpretable Hierarchical Rules from Deep Neural Networks’ Latent Space, The 7th International Joint Conference on Rules and Reasoning, Oslo, Norway, 18.09.2023

  21. Julian Wörmann, Daniel Bogdoll, Christian Brunner, Etienne Bührle, Han Chen, Evaristus Fuh Chuo, Kostadin Cvejoski, Ludger van Elst, Philip Gottschall, Stefan Griesche, Christian Hellert, et al.: Knowledge Augmented Machine Learning with Applications in Autonomous Driving: A Survey, 15.11.2023

  22. Joshua Niemeijer, Jan-Aike Termöhlen, Manuel Schwonberg, Nico M. Schmid, Tim Fingscheidt: Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentation, Waikoloa, Hawaii, USA, 04.-08.01.2024

  23. Abhishek Vivekanandan, Niels Maier, J. Marius Zöllner: Plausibility Verification For 3D Object Detectors Using Energy-Based Optimization, European Conference on Computer Vision, 15.02.2023

  24. Georgii Mikriukov, Gesina Schwalbe, Christian Hellert, Korinna Bade: Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability, XAI 2023 Lisboa, Portugal, 26-28.07.2023
  25. Georgii Mikriukov, Gesina Schwalbe, Christian Hellert, Korinna Bade: Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces, AIMLAI 2023 (ECML 2023) Torino, Italy, 18-22.09.2023
  26. Christian Schlauch, Christian Wirth: Informed Priors for Knowledge Integration in Trajectory Prediction, ECML-PKDD 2023 in Turin, Italy, 18-22.09.2023
  27. Mert Keser, Gesina Schwalbe: Interpretable Model-Agnostic Plausibility Verification for 2D Object Detectors Using Domain-Invariant Concept Bottleneck Models, CVPR 2023 SAIAD Workshop, Vancouver, Canada, 19.07.2023
  28. Kumar Manas, Adrian Paschke: Semantic Role Assisted Natural Language Rule Formalization for Intelligent Vehicle, 18.09.2023
  29. Daniel Bogdoll, Jing Qin, Moritz Nekolla, Ahmed Abouelazm, Tim Joseph, J. Marius Zöllner: Informed Reinforcement Learning for Situation-Aware Traffic Rule Exceptions, ICRA in Yokohama, Japan, 13.05.2024
  30. Mohamed-Khalil BouzidiYue YaoJoerg Reichardt: Learning-Aided Warmstart of Model Predictive Control in Uncertain Fast-Changing Traffic, Yokohama, Japan, 05.2024



Here the public KI Wissen presentations are listed.



Stefan Rudolph, Tobias Latka: Towards Causality-Driven Reinforcement LEarning for Autonomous Driving

Presentation at Computational Science Lab Seminar, 20.01.2022(pdf:1 MB)

Here you can find more project material.

Project materials