Results

Booklet - Posters - Presentations - Video

Booklet

The poster booklet contains general KI Wissen information, illustrates the project's trajectory, and presents research findings.
>>>  Download Booklet : KI Wissen - Powered by Knowledge   <<<

Posters for Download

No. Title
1.2 Model-Agnostic Body Part Relevance Assessment for Pedestrian Detection
1.3 Investigating the Effects of Augmentation Techniques on Interpretability and Performance of Pedestrian Detection Models
1.4 Static Scene Knowledge for Pedestrian Detection
1.5 Method to Fuse Map Layer and Pedestrian State Space to Improve 3D Detector Output
1.7 Knowledge Aware Pedestrian Detection
1.8 Geo-Informed Conformity Check of Pedestrian Detection Models
1.9 Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving
1.12 Plausibility Verification for 3D Object Detectors Using Energy-Based Optimization
1.13 Object Detection Plausibility with Concept-Bottleneck Models
1.14 Digital Twin Creation and Evaluation of Color-Dependent Object Detection
1.15 Multi-Modal Sensor Fusion for Robust Obstacle Detection
1.16 Leveraging Knowledge for Traffic Sign Detection
2.1 Informed Motion Planning
2.2 Knowledge Integrated Plausible Motion Forecasting
2.3 An Empirical Bayes Analysis of Object Trajectory Representation Models
2.4 An Efficient and Robust Multi-Modal Trajectory Predictor Baseline for Autonomous Driving
2.6 Integration of a Priori Knowledge Using a Causal Model of Vehicle Trajectories
2.7 Causality-Driven Checks of the Physical Conformity of Vehicle Trajectories
2.8 Tracking and Trajectory Prediction Using Scene Semantics
2.9 Learning-Aided Warmstart of Model Predictive Control in Uncertain Fast-Changing Traffic
2.10 Motion Planning Under Temporal Logic Specifications
2.11 An Outlier-Robust and Efficient Bayesian Filter and Smoother
2.12 Behavior-Conditioned Driving Policies
3.1 Harnessing Symbolic Knowledge Extraction and Utilization for Informed Decision-Making
3.2 Model Agnostic Local Analysis with Latent Attacks (MALALA)
3.3 A Concept to Support AI Models by Using Ontologies
3.4 Knowledge-Based Comparison of CNNs
3.5 AI Net Observer
3.6 Legal Norm Formalization – An Overview
3.7 From Legal Documents to Formalized Rules with Large Language Models
3.9 Traffic Sequence Charts for Knowledge Formalization and AI Application
3.10 Risk Assessment and Adaptive Decision-Making for Autonomous Vehicle Safety
3.11 Monitoring Traffic Rule Conformance and Integrated Knowledge Impact
3.12 Runtime Monitoring Using TSC-Based Knowledge Building Blocks
3.15 Consistent Joint Action and Explanation Prediction for Autonomous Driving
3.16 Generating Training Data from Formalized Traffic Dynamics
3.17 TSC-Based Generation of Concrete Scenarios for Synthetic Data
3.18 Local Concept-Based Explanations for Object Detectors
3.19 The Corpus of Traffic Rules

Presentations

Presentations of the excellent KI Wissen Final Event:

Keynote: From Road to Cloud. From Virtual to Real. | Gilles Mabire, CTO Continental
KI Wissen: Project Overview | Simon Heinz, Jörg Dietrich, Continental
Knowledge Integration Jörg Reichardt, Continental
Knowledge Extraction Antje Loyal, Continental
Knowledge Conformity Johannes Link, Valeo
Highlight Session 1
      Interpretable Model-Agnostic Plausibility Verification for 2D Object Detectors | Mert Keser, Continental
      Efficient Pedestrian Detection with Inter-stage Knowledge Integration Abdul Hannan Khan, DFKI
      Knowledge-augmented Pedestrian Detection Julian Wörmann, fortiss
Highlight Session 2
      A Causal Model of Vehicle Trajectories for Integration of a Priori Knowledge Christian Brunner, e:fs
      Advancements of Local and Global Explanation Methods for Failure Case Detection Christian Hellert, Continental
      Knowledge Formalization, Integration & Monitoring with Traffic Sequence Charts (TSCs)  |  Dominik Grundt, DLR
      The Normative Body of Traffic Rules for Autonomous Driving Georg Borges, Universität des Saarlands
Highlight Session 3
      Model Predictive Control under Temporal Logic Specifications Etienne Bührle, FZI

      Knowledge Integration in Tracking, Prediction and Planning Mohamed-Khalil Bouzidi, Yue Yao, Jonas Neuhöfer, Christian Schlauch, Continental AG

Enabeling, Integration and Demonstration Federica Paolicelli, AVL
Demonstrator Thomas Knorr, AVL
Demonstration of Causality-driven Physical Conformity Checks of Vehicle Trajectories Himanshu Agarwal, e:fs
Demonstration of Trajectory Prediction and Planning Yue Yao, Mohamed-Khalil Bouzidi, Continental
Demonstration of the Interactive Visual Analytics System Kostadin Cvejoski, Fraunhofer IAIS

Video

>>>  Download Video : KI Wissen Final Event  (720p/mp4)   <<<