Learning to Predict Motion from Raw 3D Object Detections

Learning to Predict Motion from Raw 3D Object Detections

Muench, C. (TU Delft Intelligent Vehicles)
Bijelic, Mario (Princeton University)
Gavrila, D. (TU Delft Intelligent Vehicles)

2022

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).

http://resolver.tudelft.nl/uuid:ac5a9da4-2c78-492f-8a4f-26b86233b7bb

https://doi.org/10.1109/IV51971.2022.9827071

IEEE

2023-07-01

978-1-6654-8821-1

Proceedings of the 2022 IEEE Intelligent Vehicles Symposium (IV)

2022 IEEE Intelligent Vehicles Symposium (IV), 2022-06-05 → 2022-06-09, Aachen, Germany

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-care Otherwise 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.

Institutional Repository

conference paper

© 2022 C. Muench, Mario Bijelic, D. Gavrila