Publications

Please find here the project publications (German) for download.

 

Deliverable
Eine Defizitanalyse sowie ein Optimierungsplan für die ausgewählten Delta Learning-Methoden mit vorhandenem Datensatz sind vorhanden

 

Deliverable
Synthetische Daten zur Erweiterung des Datensatzes für weiterführende Untersuchungen (Corner Cases, etc.) sind vorhanden

 

Deliverable
Ein optimiertes Produktivsystem auf Basis eines kontinuierlichen Performance-Monitorings und Auswertens der Benutzerakzeptanz ist vorhanden. Ein neuartiges DRM-Konzept zum Handling personenbezogener Sensordaten im Rahmen der KI-Entwicklung für autonome Fahrfunktionen ist erarbeitet und prototypisch umgesetzt.

Deliverables

Deliverables

Publications

publications

  1. Oberdiek, Philipp and Rottmann, Matthias and Fink, Gernot A.: Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 328-329
  2. Schwarz, Katja and Liao, Yiyi and Niemeyer, Michael and Geiger, Andreas: GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis. In: Part of Advances in Neural Information Processing Systems 33 pre-proceedings (NeurIPS 2020). Presentation available here.
  3. Schutera, Mark and Hussein, Mostafa and Abhau, Jochen and Mikut, Ralf and Reischl, Markus: Night-to-Day: Online Image-to-Image Translation for Object Detection Within Autonomous Driving by Night. In: IEEE Transactions on Intelligent Vehicles
  4. Schutera, Mark and Hafner, Frank M. and Abhau, Jochen and Hagenmeyer, Veit and Mikut, Ralf and Reischl, Markus: Cuepervision: self-supervised learning for continuous domain adaptation without catastrophic forgetting. In: Vision and Image Computing as part of the special issue: Advances in Domain Adaptation for Computer Vision.
  5. Monka, Sebastian and Halilaj, Lavdim and Rettinger, Achim: A  Survey on Visual Transfer Learning using Knowledge Graphs. In: Semantic Web Journal (SWJ, IOS Press).
  6. Monka, Sebastian and Halilaj, Lavdim and Schmid, Stefan and Rettinger, Achim: ConTraKG: Contrastive-based Transfer Learning for Visual Object Recognition using Knowledge Graphs. In: arXiv.
  7. Saikia, Tonmoy, Schmid, Cordelia, Brox, Thomas: Improving robustness to distribution shift by combining frequency biased models. CVPR 2021, 19.-25.06.2021.
  8. Kalb, Tobias, Roschani, Masoud, Ruf, Miriam, Beyerer, Jürgen: Continual Learning for Class- and Domain-Incremental Semantic Segmentation. In: 32nd IEEE Intelligent Vehicles Symposium, 10.07.2021.
  9. Helms, Domenik, Amende, Karl, Bukhari, Saqib, de Graaff, Thies, Frickenstein Alexander, Hafner, Frank, Hirscher, Tobias, Mantowsky, Sven, Schneider, Georg, Vemparala, Manoj-Rohit: Optimizing Neural Networks for Embedded Hardware. In: IEEE International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design (SMACD), 19.07.2021.
  10. Sauer, Axel and Geiger, Andreas: Counterfactual Generative Networks. In: ICLR 2021 (International Conference on Learning Representations).
  11. Guerrero-Viu, Julia and Izquierdo, Sergio, Schröppel, Philipp and Brox, Thomas: Semi-Supervised Disparity Estimation with Deep Feature Reconstruction. In: Conference on Computer Vision and Pattern Recognition 2021 (CVPR).
  12. Müller, Norman and Wong, Yu-Shiang and J. Mitra, Niloy and Dai, Angela and Niessner, Matthias: Seeing Behind Objects for 3D Multi-Object Tracking in RGB-D Sequences. In: Conference on Computer Vision and Pattern Recognition 2021 (CVPR).
  13. Prakash, Adity and Chitta, Kashyap and Geiger, Andreas: Multi-Modal Fusion Transformer for End-to-End Autonomous Driving. In: Conference on Computer Vision and Pattern Recognition 2021 (CVPR).
  14. Hanselmann, Niklas and Schneider, Nick and Ortelt, Benedikt and Geiger, Andreas: Learning Cascaded Detection Tasks with Weakly—supervised Domain Adaptation. In: IEEE Intelligent Vehicles Symposium.
  15. Triess, Larissa T. and Dreissig, Mariella and Rist, Christoph Bernd and Zöllner, J. Marius: A  Survey on Deep Domain Adaptation for LiDAR Perception. In: IEEE Intelligent Vehicles Symposium.
  16. Niemeijer, Joshua and Schäfer, Jörg P.: Combining Semantic Self-Supervision and Self-Training for Domain Adaptation in Semantic Segmentation. In: 2021 IEEE Intelligent Vehicles Symposium (IV).
  17. Hornauer, Julia and Nalpantidis, Lazaros and Belagiannis, Vasileios: Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware. In: ICCV2021, ERCVAD Workshop.
  18. Mantowsky, Sven and Heuer, Falk, and Bukhari, Saqib and Keckeisen, Michael and Schneider, Georg: ProAI: An Efficient Embedded AI Hardware for Automotive Applications – a Benchmark Study. In: ICCV2021, ERCVAD Workshop.
  19. Heuer, Falk and Mantowsky, Sven and Bukhari, Syed Saqib and Schneider, Georg: MultiTask-CenterNet (MCN): Efficient and Diverse Multitask Learning Using an Anchor Free Approach. In: ICCV2021, ERCVAD  Workshop.
  20. Poucin, Florentin and Kraus, Andrea and Simon, Martin: Boosting Instance Segmentation With Synthetic Data: A Study To Overcome the Limits of Real World Data Sets. In: ICCV2021, ERCVAD  Workshop.
  21. Lyssenko, Maria and Gladisch, Christoph and Heinzemann, Christian and Woehrle, Matthias and Triebel, Rudolph: Instance Segmentation in CARLA: Methodology and Analysis for Pedestrian-Oriented Synthetic Data Generation in Crowded Scenes. In: ICCV2021, ERCVAD  Workshop.
  22. Chitta, Kashyap and Prakash, Aditya and Geiger, Andreas: NEAT: Neural Attention Fields for End-to-End Autonomous Driving. In: ICCV 2021.
  23. Hubschneider, Christian, Birkenbach, Marius , Zöllner, J. Marius: Unsupervised Domain Adaptation via Shared Content Representation for Semantic Segmentation. In: 24th IEEE International Conference on Intelligent Transportation - ITSC2021, Indianapolis, 19.-22.09.2021.
  24. Termöhlen, Jan-Aike, Klingner, Marvin, Brettin, Leon J., Schmidt, Nico M., Fingscheidt, Tim: Continual Unsupervised Domain Adaptation for Semantic Segmentation by Online Frequency Domain Style Transfer. In: 24th IEEE International Conference on Intelligent Transportation - ITSC2021, Indianapolis, 19.-22.09.2021.
  25. Triess, Larissa T. and Peter, David and Baur, Stefan A. and Zöllner, Marius J.: Quantifying point cloud realism through adversarially learned latent space representations. In: 2021 German Conference on Pattern Recognition (GCPR).
  26. Bouazizi, Arij and Wiederer, Julian and Kressel, Ulrich and Belagiannis, Vasileios: Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry. In: IEEE - International Conference on Automatic Face & Gesture Recognition.
  27. Makansi, Osama, Çiçek, Özgün, Marrakchi, Yassine, Brox, Thomas: On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors. In: International Conference on Computer Vision (ICCV), 11.10.2021.
  28. Wiederer, Julian, Bouazizi, Arij, Troina, Marco, Kressel, Ulrich, Belagiannis, Vasileios: Anomaly Detection in Multi-Agent Trajectories for Automated Driving. In: Conference on Robot Learning (CoRL), 08.11.2021.
  29. Sauer, Axel, Chitta, Kashyap, Müller, Jens, Geiger, Andreas: Projected GANs Converge Faster. In: Neural Information Processing Systems, 06.12.2021.
  30. Schmidt, Julian, Jordan, Julian, Gritschneder, Franz, Dietmayer, Klaus: CRAT-Pred: Vehicle Trajectory Prediction with Crystal Graph Convolutional Neural Networks and Multi-Head Self-Attention. In: IEEE International Conference on Robotics and Automation (ICRA), Philadelphia, 23.-27.05.2022.
  31. Chan, Robin, Lis, Krzysztof, Uhlemeyer, Svenja, Blum, Hermann, Honari, Sina, Siegwart, Roland, Fua, Pascal, Salzmann, Mathieu, Rottmann, Matthias: SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation. In: NeurIPS2021, 06.-14.12.2021.  
  32. Eskandar, George, Abdelsamad, Mohamed, Armanious, Karim, Yang, Bin: USIS: Unsupervised Semantic Image Synthesis.
  33. Schwarz, Katja Schwarz, Liao, Yiyi, Geiger, Andreas: On the Frequency Bias of Generative Models. In: NeurIPS2021, 06.12.2021.
  34. de Graaff, Thies, de Menezes, Arthur Ribeiro: Capsule Networks for Hierarchical Novelty Detection in Object Classification. In: IV 2022, 05.06.2022.
  35. Uhlemeyer, Svenja, Rottmann, Matthias, Gottschalk, Hanno: Towards Unsupervised Open World Semantic Segmentation. In: CVPR 2022 New Orleans, 19.-24.06.2022.
  36. Schrodi, Simon, Saikia, Tonmoy, Brox,Thomas: Towards Understanding Adversarial Robustness of Optical Flow Networks. In: CVPR 2022 New Orleans, 19.-24.06.2022.    
  37. Richter, Jasmine, Faion, Florian, Feng, Di, Becker, Paul Benedikt, Sielecki, Piotr, Glaeser, Claudius: Understanding the Domain Gap in LiDAR Object Detection Networks. In: 14. Uni-DAS e.V. Workshop Fahrerassistenz und automatisiertes Fahren, Berkheim, 09.-11.05.2022.
  38. Eskandar, George, Abdelsamad, Mohamed, Armanious, Karim, Zhang, Shuai, Yang, Bin: Wavelet-based Unsupervised Label-to-Image Translation. In: ICASSP 2022, Singapore, 22.05.2022.
  39. Zhou, Jingxing, Beyerer, Jürgen: Impacts of Data Anonymization on Semantic Segmentation. In: 33rd IEEE Intelligent Vehicles Symposium, 05.-09.06.2022.
  40. Schmidt, Julian, Jordan, Julian, Raba, David, Welz, Tobias, Dietmayer, Klaus: MEAT: Maneuver Extraction from Agent Trajectories. In: 33rd IEEE Intelligent Vehicles Symposium, 05.-09.06.2022.
  41. Hafner, Frank, Zeller, Matthias, Schutera, Mark, Abhau, Jochen , Kooij, Julian: BackboneAnalysis: Structured Insights into Compute Platforms from CNN Inference Latency. In: 2022 IEEE Intelligent Vehicles Symposium (IV), 04.-09.06.2022.
  42. Marsden, Robert A., Bartler, Alexander, Döbler, Mario, Yang, Bin: Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation. In: WCCI 2022 (IJCNN 2022) Padua, 18.-23.07.2022.
  43. Bouazizi, Arij, Kreßel, Ulrich, Holzbock, Adrian, Dietmayer, Klaus, Belagiannis, Vasileios: MotionMixer: MLP-based 3D Human Body Pose Forecasting. In: IJCAI-ECAI 22, 23.-29.07.2022.
  44. Ding, Shuxiao, Rehder, Eike, Schneider, Lukas, Cordts, Marius, Gall, Jürgen: End-to-End Single Shot Detector using Graph-based Learnable Duplicate Removal. In: GCPR Konstanz, 27.-30.09.2022.
  45. Schröppel, Philipp, Amiranashvili, Artemij, Bechtold, Jan, Brox, Thomas: A Benchmark and a Baseline for Robust Multi-view Depth Estimation. In: International Conference on 3D Vision 2022, Prague.
  46. Sommer, Leonhard, Schröppel, Philipp, Brox, Thomas: SF2SE3: Clustering Scene Flow into SE(3)-Motions via Proposal and Selection. In: GCPR Konstanz, 27.-30.09.2022.
  47. Thirunavukkarasu, Arunachalam, Helms, Domenik Helms: Using Network Architecture Search for Optimizing Tensor Compression. In: ITEM Workshop, Grenoble, France, 19.-23.09.2022.
  48. Osterwind, Adrian, Droste-Rehling, Julian, Vemparala, Manoj-Rohit, Helms, Domenik: Hardware Execution Time Prediction for Neural Network Layers. In: ITEM Workshop, Grenoble, France, 19.-23.09.2022.
  49. Henning, Tabea, Grujic, Daniel, Werner, Tino, Kramer, Birte, Möhlmann, Eike: Verifying Safety of Safety-Critical Systems with Rare Events via Optimistic Optimization. In: 19th International Conference on Quantitative Evaluation of SysTems (QEST 2022), Warsaw, 12.-16.09.2022.
  50. Burghoff , Julian, Chan, Robin, Gottschalk, Hanno, Mütze, Annika, Riedlinger, Tobias, Rottmann, Matthias, Schubert, Marius: Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning. In: 11th NIC (The John von Neumann Institute for Computing) Symposium in Jülich.
  51. George Eskandar, Robert A. Marsden, Pavithran Pandiyan, Mario Döbler, Karim Guirguis, Bin Yang: An Unsupervised Domain Adaptive Approach for Multimodal 2D Object Detection in Adverse Weather Conditions, Kyoto, Japan
  52. Julian Wiederer, Julian Schmidt, Ulrich Kreßel, Klaus Dietmayer, Vasileios Belagiannis: A Benchmark for Unsupervised Anomaly Detection in Multi-Agent Trajectories Macau, China
  53. Julia Hornauer: Heatmap-based Out-of-Distribution Detection, WACV Waikoloa, Hawaii
  54. Mariella Dreissig, Florian Piewak, Joschka Boedecker: On the calibration of underrepresented classes in LiDAR-based semantic segmentation, Kyoto, Japan
  55. Joshua Niemeijer, Jörg P. Schäfer: Domain Adaptation and Generalization: A Low-Complexity Approach, Auckland, NZ
  56. Daniel Bogdoll, Svenja Uhlemeyer, Kamil Kowol, J. Marius Zöllner: Perception Datasets for Anomaly Detection in Autonomous Driving: A Survey
  57. Sarina Penquitt, Robin Chan, Hanno Gottschalk: Invertible Neural Networks Based on Matrix Factorization
  58. Michael Essich, Markus Rehmann, Cristóbal Curio: Auxiliary Task-Guided CycleGAN for Black-Box Model Domain Adaptation, Waikoloa, Hawaii
  59. Artem Savkin, Yida Wang, Sebastian Wirkert, Nassir Navab, Federico Tombari: Lidar Upsampling With Sliced Wasserstein Distance
  60. Tobias Kalb, Niket Ahuja, Jingxing Zhou, Jürgen Beyerer: Effects of Architectures on Continual Semantic Segmentation

The publicly held presentations by the project will be listed here.

 

Presentations

presentations

Presentation at BMWi/VDA event

KI Delta Learning(pdf:3 MB)

KI Delta Learning Standard presentation

Standard presentation(pdf:3 MB)

Presentation at TÜV Süd Tagung on Automated Driving, 29./30. March, 2022

TÜV Süd Tagung(pdf:2 MB)

Results

project-material

Here you can download the results of the project:

BookletPresentationsPostersFinal Report

On Thursday March 09, 2023 the KI Delta Learning Final Event took place in Stuttgart-Vaihingen. The project results were presented to the professional public. The project presented project results of all KI Delta Learning research areas to around 150 visitors in presentations, panel discussions and 50 posters.

 

Booklet

The poster booklet contains general KI Delta Learning information, illustrates the projects approaches and presents around 50 research topics.

KI Delta Learning - Autonomy at Scale

 

Presentations

KI Delta Learning – Project, Mission, Results
Keynote: Paths towards Open World Generalization

Data Generation
Data – The Basis for Delta Learning
SceneNeRF:3D Reconstruction ofReal-World Scenes
Simulation of a pulsed LiDAR

Transfer Learning
Transfer Learning – Overview
Heterogeneous Continual Learning
Visual Transfer Learning using Knowledge Graphs
Auxiliary Task-Guided CycleGAN for Black-Box Model Domain Adaptation
Mounting Position based Lidar Domain Gap Analysis
Domain Generalization and (Continuous) Unsupervised Domain Adaptation
Activation-based Domain Shift Quantification for Semantic Segmentation

Didactics
Didactics – Overview
Shared Backbones with MultiTask CenterNet
Self-Supervised 3D Human Pose Estimation for Autonomous Driving
Towards Unsupervised Open World Semantic Segmentation
Active Learning for Semantic Segmentation in Realistic Driving Scenarios
A Low-Complexity Approach for Domain Adaptation

Automotive Suitability
Automotive Suitability – Overview​​​​​​​
A Benchmark and a Baseline for Robust Multi-view Depth Estimation
Unsupervised Learning for Detection of Abnormal Driving Behavior
Automotive Suitability - Overview
Interpretable Pruning

 

Posters

Environment

Improving robustness against common corruptions with frequency biased models
Introducing Intermediate Domains for Effective Self-Training during Test-time
Robustness Against Noisy Labels Through Uncertainty Estimation for LiDAR-based Semantic Segmentation
An Unsupervised Domain Adaptive Approach for Multimodal 2D Object Detection in Adverse Weather Conditions
A Low-Complexity Approach for Domain Adaptation
Continual Learning for Model-Based Reinforcement Learning
Motion Capture-based Virtual Reality Co-Simulation
Domain Shift Quantification using Activations
SceneNeRF: 3D Reconstruction of Real-World Scenes
Environmental adaptation and self-attention in the context of unsupervised domain adaptation
Detection of critical weather situations in scenario-based traffic simulations using optimization techniques

Sensors

3D Detection and Tracking From LiDAR Point Clouds As a Pre-Processing Step for Active Learning
Processing of vehicle sensor data
Real Data Acquisition with Ground Truth
Auxiliary Task-Guided CycleGAN for Black-Box Model Domain Adaptation
Bridging Domain Gaps in Lidar Perception
Lidar Upsampling with Sliced Wasserstein Distance
TransFuser: Imitation with Transformer-Based Sensor Fusion
HALS: A Height-aware Lidar Super-Resolution Approach for Autonomous Driving

Active Learning

Active Learning On Dynamic Scenes using Multi-View Consistency
Active Learning based on a Taxonomy for Scene Description
Active learning for semantic segmentation in realistic driving scenarios
Consistency-based Active Learning for Semantic Segmentation

Knowledge Transfer

SpatialDETR: 3D Object Detection from Multi-View Camera Images with Global Cross-Sensor Attention
Knowledge Transfer for Multitask and Downstream Tasks
Domain Generalization and (Continuous) Unsupervised Domain Adaptation
USIS: Unsupervised Semantic Image Synthesis
CRAT-Pred: Vehicle Trajectory Prediction with Crystal Graph Convolutional Neural Networks and Multi-Head Self-Attention

Semi- and Unsupervised Learning

Towards Unsupervised Open World Semantic Segmentation
Semi-supervised domain adaptation with CycleGAN guided by downstream task awareness
Attention-Based Self-Supervised Monocular Depth Estimation
Cycle-Consistent World Models for Domain Independent Latent Imagination
3D-Aware Image Synthesis with Generative Radiance Fields
Augmentation-based Domain Generalization for Semantic Segmentation
Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception
Self-Supervised Deep Representation Learning for Semantic Segmentation

Training Strategies

PlanT: Explainable Planning Transformers via Object-Level Representations
Automated Detection of Label Errors in Semantic Segmentation Datasets
Severity of Catastrophic Forgetting in Object Detection for Autonomous Driving
MGiaD: Multigrid in all dimension. Efficiency and Robustness by Coarsening in Resolution and Channel Dimensions
Improving Replay-Based Continual Semantic Segmentation with Smart Data Selection
Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation

Embedded Systems

Analyzing and optimizing AI for embedded applications
Interpretable Pruning
Accelerating and Pruning CNNs for Semantic Segmentation on FPGA

Real World Robustness

A Benchmark and a Baseline for Robust Multi-view Depth Estimation
Unsupervised Detection of Abnormal Driving Behavior
Impact of Data Anonymization of Semantic Segmentation

 

Final report

Please download the KI Delta Learning summarising final report (German) here.

 

Press kit

You can find our press kit here:

Press kit

press

Press releases

Press releases of the project and our partners

Hochschule Reutlingen:

https://www.hhz.de/de/aktuelles/news/news/2021-03-03-ki-delta-learning/ (German)

Offis:

https://www.offis.de/offis/projekt/ki-delta-learning.html (German)

https://www.offis.de/en/offis/project/ai-delta-learning.html (English)

DLR:

https://verkehrsforschung.dlr.de/de/projekte/ki-deltalearning (German)

Universität Wuppertal:

https://www.presse.uni-wuppertal.de/de/medieninformationen/2020/02/12/31499-rund-11-millionen-fuer-ki-forschung-an-der-bergischen-universitaet/ (German)

Universität Stuttgart:

https://www.uni-stuttgart.de/universitaet/aktuelles/presseinfo/Fahrstunden-fuer-die-Kuenstliche-Intelligenz/ (German)

https://www.uni-stuttgart.de/en/university/news/press-release/Driving-lessons-for-Artificial-Intelligence/ (English)

InnoSent GmbH

https://www.innosent.de/unternehmen/presse/view/article/ki-macht-autonomes-fahren-bereit-fuer-unterschiedliche-umgebungsszenarien/ (German)

FZI - Forschungszentrum Informatik

https://www.fzi.de/aktuelles/news/detail/artikel/die-ki-familie-bekommt-zuwachs-ki-wissen-nimmt-seine-forschungstaetigkeit-auf/ (German)

https://www.fzi.de/de/aktuelles/news/detail/artikel/halbzeit-bei-ki-delta-learning-erste-forschungsergebnisse-fuer-ein-skalierbares-automatisiertes-fahr/

Daimler AG:

https://media.daimler.com/marsMediaSite/de/instance/ko/Halbzeit-bei-KI-Delta-Learning-erste-Forschungsergebnisse-fuer-ein-skalierbares-automatisiertes-Fahren-werden-praesentiert.xhtml?oid=51620114

Porsche AG:

https://newsroom.porsche.com/de/2021/innovation/porsche-engineering-ki-delta-learning-forschungsprojekt-25984.html

Volkswagen AG:

https://www.volkswagenag.com/de/news/stories/2021/10/ai-delta-learning--simplifying-the-small-differences.html#

Press releases

press

Media coverage

Media coverage of the project

Porsche Magzine: The little difference (PDF)

https://nachrichten.idw-online.de/2020/11/20/fahrstunden-fuer-die-kuenstliche-intelligenz/

https://www.tagblatt.de/Nachrichten/Kuenstliche-Intelligenzam-Steuer-461033.html 

https://intellicar.de/tests-and-research/fahrschule-fuer-die-kuenstliche-intelligenz/

https://www.elektroniknet.de/automotive/assistenzsysteme/uni-stuttgart-erforscht-neue-methoden-des-maschinellen-lernens.181366.html

https://www.wuppertaler-rundschau.de/lokales/wuppertaler-forschung-zum-autonomen-und-vernetzten-fahren_aid-56592201

https://www.donaukurier.de/archiv/gaimersheimer-daten-und-softwareunternehmen-efs-treibt-autonomes-fahren-voran-1529751

https://www.rtunlimited.de/blog/post/autonomes-fahren-und-wandernde-krebszellen

https://www.testen-simulation.com/post/ki-delta-learning-der-kleine-unterschied

https://www.hanser-automotive.de/a/news/neuronale-netze-fuer-autonomes-fahren-tr-349430

https://www.meinauto.de/news/porsche-ki-delta-learning-soll-den-unterschied-machen

https://digitalhub-ai.de/de/nachricht-lesen/halbzeit-bei-ki-delta-learning

https://www.aftermarket-update.de/2021/11/23/training-fuer-porsche-ki/

https://newsroom.porsche.com/de/2022/innovation/porsche-engineering-autonome-fahrzeuge-spielfilme-26977.html

https://www.konstruktionspraxis.vogel.de/damit-autonomes-fahren-sicher-gelingt-a-625b9e553f74766a90ca23ddc6eda4c1/ 

Press Materials

press

test