ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929264803184640 |
|---|---|
| author | Lu, Han Jia, Xiaosong Xie, Yichen Liao, Wenlong Yang, Xiaokang Yan, Junchi |
| author_facet | Lu, Han Jia, Xiaosong Xie, Yichen Liao, Wenlong Yang, Xiaokang Yan, Junchi |
| contents | End-to-end differentiable learning for autonomous driving (AD) has recently become a prominent paradigm. One main bottleneck lies in its voracious appetite for high-quality labeled data e.g. 3D bounding boxes and semantic segmentation, which are notoriously expensive to manually annotate. The difficulty is further pronounced due to the prominent fact that the behaviors within samples in AD often suffer from long tailed distribution. In other words, a large part of collected data can be trivial (e.g. simply driving forward in a straight road) and only a few cases are safety-critical. In this paper, we explore a practically important yet under-explored problem about how to achieve sample and label efficiency for end-to-end AD. Specifically, we design a planning-oriented active learning method which progressively annotates part of collected raw data according to the proposed diversity and usefulness criteria for planning routes. Empirically, we show that our planning-oriented approach could outperform general active learning methods by a large margin. Notably, our method achieves comparable performance with state-of-the-art end-to-end AD methods - by using only 30% nuScenes data. We hope our work could inspire future works to explore end-to-end AD from a data-centric perspective in addition to methodology efforts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_02877 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving Lu, Han Jia, Xiaosong Xie, Yichen Liao, Wenlong Yang, Xiaokang Yan, Junchi Computer Vision and Pattern Recognition Artificial Intelligence Robotics End-to-end differentiable learning for autonomous driving (AD) has recently become a prominent paradigm. One main bottleneck lies in its voracious appetite for high-quality labeled data e.g. 3D bounding boxes and semantic segmentation, which are notoriously expensive to manually annotate. The difficulty is further pronounced due to the prominent fact that the behaviors within samples in AD often suffer from long tailed distribution. In other words, a large part of collected data can be trivial (e.g. simply driving forward in a straight road) and only a few cases are safety-critical. In this paper, we explore a practically important yet under-explored problem about how to achieve sample and label efficiency for end-to-end AD. Specifically, we design a planning-oriented active learning method which progressively annotates part of collected raw data according to the proposed diversity and usefulness criteria for planning routes. Empirically, we show that our planning-oriented approach could outperform general active learning methods by a large margin. Notably, our method achieves comparable performance with state-of-the-art end-to-end AD methods - by using only 30% nuScenes data. We hope our work could inspire future works to explore end-to-end AD from a data-centric perspective in addition to methodology efforts. |
| title | ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2403.02877 |