Automated Generation of Transformations to Mitigate Sensor Hardware Migration in ADS

Autonomous driving systems (ADSs) rely on massive amounts of sensed data to train their underlying deep neural networks (DNNs). Common sensor hardware migrations can render an existing DNN-dependent pipeline inadequate. This necessitates the development of bespoke transformations to adapt new sensor...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE robotics and automation letters 2024-07, Vol.9 (7), p.6480-6487
Hauptverfasser:	von Stein, Meriel, Wang, Hongning, Elbaum, Sebastian
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Autonomous vehicle navigation Cameras Coders Datasets deep learning for visual perception Hardware Image reconstruction Image transformation Robot sensing systems Sensors Training vision-based navigation
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!