Abstract
We show how to design a motion prediction algorithm that works with 3D object detections and map locations. In particular, we obtain object id’s – even though the training data does not contain any object id’s – across multiple time-steps into the future by propagating a Gaussian Mixture of likely object (e.g., vehicle) locations through time.We validate our approach on the nuScenes dataset. First, we find that a motion prediction algorithm without tracking id’s performs as well as motion prediction algorithm with tracking id’s in the training data. Second, the 3D labels of an on-board perception system are inferior (e.g., loss of detections, positional uncertainty) to those generated by offline labelling (automatic labelling pipeline, manual labelling). Even so, we find that a moderate increase in the size of the training data offsets the deterioration in prediction performance (with no additional offline labelling).
Original language | English |
---|---|
Title of host publication | Proceedings of the 2022 IEEE Intelligent Vehicles Symposium (IV) |
Publisher | IEEE |
Pages | 1241-1247 |
ISBN (Electronic) | 978-1-6654-8821-1 |
DOIs | |
Publication status | Published - 2022 |
Event | 2022 IEEE Intelligent Vehicles Symposium (IV) - Aachen, Germany Duration: 5 Jun 2022 → 9 Jun 2022 |
Conference
Conference | 2022 IEEE Intelligent Vehicles Symposium (IV) |
---|---|
Country/Territory | Germany |
City | Aachen |
Period | 5/06/22 → 9/06/22 |
Bibliographical note
Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-careOtherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.