Jacob Langner
YOU?
Author Swipe
View article: A Data-Driven Novelty Score for Diverse In-Vehicle Data Recording
A Data-Driven Novelty Score for Diverse In-Vehicle Data Recording Open
High-quality datasets are essential for training robust perception systems in autonomous driving. However, real-world data collection is often biased toward common scenes and objects, leaving novel cases underrepresented. This imbalance hi…
View article: Point Cloud Recombination: Systematic Real Data Augmentation Using Robotic Targets for LiDAR Perception Validation
Point Cloud Recombination: Systematic Real Data Augmentation Using Robotic Targets for LiDAR Perception Validation Open
The validation of LiDAR-based perception of intelligent mobile systems operating in open-world applications remains a challenge due to the variability of real environmental conditions. Virtual simulations allow the generation of arbitrary …
View article: GOOSE: Goal-Conditioned Reinforcement Learning for Safety-Critical Scenario Generation
GOOSE: Goal-Conditioned Reinforcement Learning for Safety-Critical Scenario Generation Open
Scenario-based testing is considered state-of-the-art for verifying and validating Advanced Driver Assistance Systems (ADASs) and Automated Driving Systems (ADSs). However, the practical application of scenario-based testing requires an ef…
View article: Unveiling Objects with SOLA: An Annotation-Free Image Search on the Object Level for Automotive Data Sets
Unveiling Objects with SOLA: An Annotation-Free Image Search on the Object Level for Automotive Data Sets Open
Huge image data sets are the fundament for the development of the perception of automated driving systems. A large number of images is necessary to train robust neural networks that can cope with diverse situations. A sufficiently large da…
View article: Analysis and Comparison of Datasets by Leveraging Data Distributions in Latent Spaces
Analysis and Comparison of Datasets by Leveraging Data Distributions in Latent Spaces Open
Automated driving is widely seen as one of the areas, where key innovations are driven by the application of deep learning. The development of safe and robust deep neural network (DNN) functions requires new validation methods. A core insu…
View article: Logical Scenario Derivation by Clustering Dynamic-Length-Segments Extracted from Real-World-Driving-Data
Logical Scenario Derivation by Clustering Dynamic-Length-Segments Extracted from Real-World-Driving-Data Open
For the development of Advanced Driver Assistant Systems (ADAS) and Automated Driving Systems (ADS) a change from test case-based testing towards scenario-based testing can be observed. Based on current approaches to define scenarios and t…
View article: Framework for using real driving data in automotive feature development and validation
Framework for using real driving data in automotive feature development and validation Open
The increasing complexity and interconnectivity of
automotive features raises the significance of comprehensive Verification and Validation (V&V) activities. High-level automotive features use the information provided by complex environme…