paper-conference

Graph-based Trajectory Prediction with Cooperative Information
For automated driving, predicting the future trajectories of other road users in complex traffic situations is a hard problem. Modern …
Jan Strohbeck, Sebastian Maschke, Max Mertens, Michael Buchholz
PDF Cite DOI
Deep Kernel Learning for Uncertainty Estimation in Multiple Trajectory Prediction Networks
Predicting future paths of vehicles or pedestrians is an essential task for automated vehicles to allow for planning the own …
Jan Strohbeck, Johanner Müller, Martin Herrmann, Michael Buchholz
PDF Cite DOI
An Extension Proposal for the Collective Perception Service to Avoid Transformation Errors and Include Object Predictions
The collective perception service, which is in progress of standardization by the European Telecommunication Standards Institute, …
Jan Strohbeck, Martin Herrmann, Johanner Müller, Michael Buchholz
PDF Cite DOI
DeepSIL: A Software-in-the-Loop Framework for Evaluating Motion Planning Schemes Using Multiple Trajectory Prediction Networks
Testing and verification is still an open issue on the way to fully automated driving. Simulations can help to reduce the required …
Jan Strohbeck, Johanner Müller, Adrian Holzbock, Michael Buchholz
PDF Cite DOI
Multiple Trajectory Prediction with Deep Temporal and Spatial Convolutional Neural Networks
Automated vehicles need to not only perceive their environment, but also predict the possible future behavior of all detected traffic …
Jan Strohbeck, Vasileios Belagiannis, Johanner Müller, Marcel Schreiber, Martin Herrmann, Daniel Wolf, Michael Buchholz
PDF Cite DOI