Dr. Holger Caesar, Assistant Professor
Intelligent Vehicles Lab, TU Delft
Autonomous vehicles (AVs) have come a long way in the past two decades. Yet they are nowhere close to safely carrying our children to an arbitrary location. Until AVs become a net provider of safety, comfort and reduced carbon emissions, a lot of work remains to be done. The real world is full of challenging corner-cases and unexpected behavior. My research focuses on finding more scalable approaches to address these corner cases by collecting, mining, labeling, training from and evaluating sensor data more cleverly.
Latest news
07/2023: Our HiLo paper for panoptic scene graph generation was accepted to ICCV 2023.
07/2023: Holger gives a keynotes speech at the Traffic Flow Theory and Characteristics Committee Summer Meeting.
06/2023: Holger is an invited speaker at IV 2023 and organizes a workshop at CVPR 2023.
05/2023: Our proposal to equip a bicycle with automotive sensors receives the "Climate Action Research and Education Seed Call" award for 30k EUR.
05/2023: LaneLet2 for nuScenes accepted as a CVPR workshop paper.
03/2023: A preprint of our HiLo paper for panoptic scene graph generation is now available.
03/2023: Our SliceMatch method for cross-view pose estimation was accepted at CVPR 2023.
11/2022: Our ICLR 2023 workshop proposal "Scene Representations for Autonomous Driving" was accepted.
11/2022: Holger becomes an ELLIS member.
11/2022: Awarded a TKI grant for 502k EUR, co-sponsored by Motional and the top sector High Tech Systems and Materials.
10/2022: Keynote at the "Workshop on Learning from Limited and Imperfect Data" at ECCV 2022 in Tel Aviv.
10/2022: Yancong joins the group as postdoc, Ted joins as PhD.
07/2022: One PhD position available. Update: Position closed!
06/2022: Two keynotes at the 33rd IEEE Intelligent Vehicles (IV) Symposium at workshops on unsupervised learning and map-less driving. See you there!
05/2022: One paper published at the 2022 International Conference on Robotics and Automation (ICRA).
05/2022: One PhD and one PostDoc position available. Update: Positions closed!
04/2022: Started as Assistant Professor at TU Delft.
Topics
Outperforming the state-of-the-art in
3d detection/tracking
Segmentation/mapping
Prediction/planning
Use of prior knowledge to solve these tasks
Lesser forms of supervision (self, weakly or semi supervised)
Active learning and partial labeling techniques to select which data to annotate
Domain adaptation and transfer learning
Sensor fusion
Collaborative perception
Vacancies
There are currently no open vacancies. For student projects and theses, please see the Education page.
Biography
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.
Besides being an Assistant Professor, Holger has the following roles:
Co-organizer of NCCV 2023
Mobiliser at the "Pathways to mobility futures" initiative of the TU Delft Transport & Mobility Institute
TU Delft Robotics Institute "Robotics in the Field" representative
Founding member of the Board of Directors of the non-profit Project OpenBytes
Previously, Holger was also:
Area Chair at ICCV 2023