Energy-Aware Imitation Learning for Steering Prediction Using Events and Frames
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915898536755200 |
|---|---|
| author | Cao, Hu Liu, Jiong Yan, Xingzhuo Song, Rui Xia, Yan Zimmer, Walter Chen, Guang Knoll, Alois |
| author_facet | Cao, Hu Liu, Jiong Yan, Xingzhuo Song, Rui Xia, Yan Zimmer, Walter Chen, Guang Knoll, Alois |
| contents | In autonomous driving, relying solely on frame-based cameras can lead to inaccuracies caused by factors like long exposure times, high-speed motion, and challenging lighting conditions. To address these issues, we introduce a bio-inspired vision sensor known as the event camera. Unlike conventional cameras, event cameras capture sparse, asynchronous events that provide a complementary modality to mitigate these challenges. In this work, we propose an energy-aware imitation learning framework for steering prediction that leverages both events and frames. Specifically, we design an Energy-driven Cross-modality Fusion Module (ECFM) and an energy-aware decoder to produce reliable and safe predictions. Extensive experiments on two public real-world datasets, DDD20 and DRFuser, demonstrate that our method outperforms existing state-of-the-art (SOTA) approaches. The codes and trained models will be released upon acceptance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_28008 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Energy-Aware Imitation Learning for Steering Prediction Using Events and Frames Cao, Hu Liu, Jiong Yan, Xingzhuo Song, Rui Xia, Yan Zimmer, Walter Chen, Guang Knoll, Alois Computer Vision and Pattern Recognition In autonomous driving, relying solely on frame-based cameras can lead to inaccuracies caused by factors like long exposure times, high-speed motion, and challenging lighting conditions. To address these issues, we introduce a bio-inspired vision sensor known as the event camera. Unlike conventional cameras, event cameras capture sparse, asynchronous events that provide a complementary modality to mitigate these challenges. In this work, we propose an energy-aware imitation learning framework for steering prediction that leverages both events and frames. Specifically, we design an Energy-driven Cross-modality Fusion Module (ECFM) and an energy-aware decoder to produce reliable and safe predictions. Extensive experiments on two public real-world datasets, DDD20 and DRFuser, demonstrate that our method outperforms existing state-of-the-art (SOTA) approaches. The codes and trained models will be released upon acceptance. |
| title | Energy-Aware Imitation Learning for Steering Prediction Using Events and Frames |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.28008 |