Outputs (4)

Investigating factors influencing takeover performance in conditionally automated driving: The role of uncertainty communication (2025)
Journal Article

Safe transition following a Takeover Request (ToR) in Level 3 automated driving requires a high situational awareness, which is influenced by traffic complexity, non-driving-related tasks (NDRTs), and communication strategies. These factors are often... Read More about Investigating factors influencing takeover performance in conditionally automated driving: The role of uncertainty communication.

Ensemble of pre-trained models for long-tailed trajectory prediction (2025)
Presentation / Conference Contribution

This work explores the application of ensemble modeling to the multidimensional regression problem of tra-jectory prediction for vehicles in urban environments. We show how, perhaps surprisingly, combining state-of-the-art deep learning models out-of... Read More about Ensemble of pre-trained models for long-tailed trajectory prediction.

MinkOcc: Towards real-time label-efficient semantic occupancy prediction (2025)
Presentation / Conference Contribution

Developing 3D semantic occupancy prediction models often relies on dense 3D annotations for supervised learning, a process that is both labor and resource-intensive, underscoring the need for label-efficient or even label-free approaches. To address... Read More about MinkOcc: Towards real-time label-efficient semantic occupancy prediction.

GraphSCENE: On-demand critical scenario generation for autonomous vehicles in simulation (2025)
Presentation / Conference Contribution

Testing and validating Autonomous Vehicle (AV) performance in safety-critical and diverse scenarios is crucial before real-world deployment. However, manually creating such scenarios in simulation remains a significant and time-consuming challenge. T... Read More about GraphSCENE: On-demand critical scenario generation for autonomous vehicles in simulation.