Current end-to-end autonomous driving methods either run a controller based on a planned
trajectory or perform control prediction directly, which have spanned two separately studied …

End-to-end driving systems have recently made rapid progress, in particular on CARLA.
Independent of their major contribution, they introduce changes to minor system …

End-to-end driving has made significant progress in recent years, demonstrating benefits
such as system simplicity and competitive driving performance under both open-loop and …

In end-to-end autonomous driving, the utilization of existing sensor fusion techniques for
imitation learning proves inadequate in challenging situations that involve numerous …

In the field of autonomous driving, there have been many excellent perception models for
object detection, semantic segmentation, and other tasks, but how can we effectively use the …

Due to the complex and safety-critical nature of autonomous driving, recent works typically
test their ideas on simulators designed for the very purpose of advancing self-driving …

Oppgaven med autonom kjøring er vanskelig, og oppgaven med autonom kjøring basert på
visuell input er enda vanskeligere. Fremskritt innen visuell intelligens og autonome …

In this Supplementary document, we first provide a detailed description of the dataset in Sec.
A. Implementation and training details are in Sec. B. We show detailed infraction statistics for …

End-to-end driving systems have made rapid progress, but have so far not been applied to
the challenging new CARLA Leaderboard 2.0. Furthermore, while there is a large body of …