About the Talk: To scale autonomous vehicles to drive in any environment we require vast amounts of annotated data. While manual labeling is insufficient to generate this data, promising methods have been proposed for autolabeling. In this talk there will be presented the nuPlan benchmark for autonomous vehicle planning with a vast dataset of nearly 1300h of autolabeled data. Going beyond nuPlan, we will identify gaps in the autolabeling process – namely the identification of driving scenarios and offline tracking under occlusion. There will be presented two novel works that try to address these gaps to enable autolabeling all aspects of future datasets.
About the Speaker: Dr. Holger Caesar is an Assistant Professor in the Intelligent Vehicles group of TU Delft in the Netherlands. Holger’s research interests are in the area of Autonomous Vehicle perception and prediction, with a particular focus on scalability of learning and annotation approaches. Previously Holger was a Principal Research Scientist at an autonomous vehicle company called Motional (formerly nuTonomy). There he started 3 teams with 20+ members that focused on Data Annotation, Autolabeling and Data Mining. Holger received a PhD in Computer Vision from the University of Edinburgh in Scotland under Prof. Dr. Vittorio Ferrari and studied in Germany and Switzerland (KIT Karlsruhe, EPF Lausanne, ETH Zurich). He is best known for developing the influential autonomous driving datasets nuScenes and nuPlan, as well as his contributions to the real-time 3d object detection method PointPillars. In his spare time he likes to hike with his small family, as well as sing, run or cross the Alps by mountainbike.