Deep Multi-Task Learning for Joint Localization, Perception, and Prediction
Abstract
Over the last few years, we have witnessed tremendous progress on many subtasks of autonomous driving including perception, motion forecasting, and motion planning. However, these systems often assume that the car is accurately localized against a high-definition map. In this paper we question this assumption, and investigate the issues that arise in state-of-the-art autonomy stacks under localization error. Based on our observations, we design a system that jointly performs perception, prediction, and localization. Our architecture is able to reuse computation between the three tasks, and is thus able to correct localization errors efficiently. We show experiments on a large-scale autonomy dataset, demonstrating the efficiency and accuracy of our proposed approach.
Cite
Text
Phillips et al. "Deep Multi-Task Learning for Joint Localization, Perception, and Prediction." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.00465Markdown
[Phillips et al. "Deep Multi-Task Learning for Joint Localization, Perception, and Prediction." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/phillips2021cvpr-deep/) doi:10.1109/CVPR46437.2021.00465BibTeX
@inproceedings{phillips2021cvpr-deep,
title = {{Deep Multi-Task Learning for Joint Localization, Perception, and Prediction}},
author = {Phillips, John and Martinez, Julieta and Barsan, Ioan Andrei and Casas, Sergio and Sadat, Abbas and Urtasun, Raquel},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2021},
pages = {4679-4689},
doi = {10.1109/CVPR46437.2021.00465},
url = {https://mlanthology.org/cvpr/2021/phillips2021cvpr-deep/}
}