USC: Uncompromising Spatial Constraints for Safety-Oriented 3D Object Detectors in Autonomous Driving
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909556112621568 |
|---|---|
| author | Liao, Brian Hsuan-Cheng Cheng, Chih-Hong Esen, Hasan Knoll, Alois |
| author_facet | Liao, Brian Hsuan-Cheng Cheng, Chih-Hong Esen, Hasan Knoll, Alois |
| contents | In this work, we consider the safety-oriented performance of 3D object detectors in autonomous driving contexts. Specifically, despite impressive results shown by the mass literature, developers often find it hard to ensure the safe deployment of these learning-based perception models. Attributing the challenge to the lack of safety-oriented metrics, we hereby present uncompromising spatial constraints (USC), which characterize a simple yet important localization requirement demanding the predictions to fully cover the objects when seen from the autonomous vehicle. The constraints, as we formulate using the perspective and bird's-eye views, can be naturally reflected by quantitative measures, such that having an object detector with a higher score implies a lower risk of collision. Finally, beyond model evaluation, we incorporate the quantitative measures into common loss functions to enable safety-oriented fine-tuning for existing models. With experiments using the nuScenes dataset and a closed-loop simulation, our work demonstrates such considerations of safety notions at the perception level not only improve model performances beyond accuracy but also allow for a more direct linkage to actual system safety. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2209_10368 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | USC: Uncompromising Spatial Constraints for Safety-Oriented 3D Object Detectors in Autonomous Driving Liao, Brian Hsuan-Cheng Cheng, Chih-Hong Esen, Hasan Knoll, Alois Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning In this work, we consider the safety-oriented performance of 3D object detectors in autonomous driving contexts. Specifically, despite impressive results shown by the mass literature, developers often find it hard to ensure the safe deployment of these learning-based perception models. Attributing the challenge to the lack of safety-oriented metrics, we hereby present uncompromising spatial constraints (USC), which characterize a simple yet important localization requirement demanding the predictions to fully cover the objects when seen from the autonomous vehicle. The constraints, as we formulate using the perspective and bird's-eye views, can be naturally reflected by quantitative measures, such that having an object detector with a higher score implies a lower risk of collision. Finally, beyond model evaluation, we incorporate the quantitative measures into common loss functions to enable safety-oriented fine-tuning for existing models. With experiments using the nuScenes dataset and a closed-loop simulation, our work demonstrates such considerations of safety notions at the perception level not only improve model performances beyond accuracy but also allow for a more direct linkage to actual system safety. |
| title | USC: Uncompromising Spatial Constraints for Safety-Oriented 3D Object Detectors in Autonomous Driving |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2209.10368 |