Project | COPPER

The COPPER project aims to develop new concepts in the context of alternative, advanced training strategies for deep neural networks applied in the field of assisted and autonomous driving. In particular, we will conduct basic research in the area of continuous learning, self-supervised and unsupervised learning, and new approaches for direct supervision by human behavior. With these technological advances, we aim to enable more adaptive models in the context of self-driving vehicles that require fewer resources for training and are suitable for a wider range of use cases. The project is working towards a more complete visual perception of different traffic situations by considering multiple sensors and tasks simultaneously.