InVDriver: Intra-Instance Aware Vectorized Query-Based Autonomous Driving Transformer
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913705915056128 |
|---|---|
| author | Zhang, Bo Huang, Heye Liu, Chunyang Zhang, Yaqin Xu, Zhenhua |
| author_facet | Zhang, Bo Huang, Heye Liu, Chunyang Zhang, Yaqin Xu, Zhenhua |
| contents | End-to-end autonomous driving with its holistic optimization capabilities, has gained increasing traction in academia and industry. Vectorized representations, which preserve instance-level topological information while reducing computational overhead, have emerged as a promising paradigm. While existing vectorized query-based frameworks often overlook the inherent spatial correlations among intra-instance points, resulting in geometrically inconsistent outputs (e.g., fragmented HD map elements or oscillatory trajectories). To address these limitations, we propose InVDriver, a novel vectorized query-based system that systematically models intra-instance spatial dependencies through masked self-attention layers, thereby enhancing planning accuracy and trajectory smoothness. Across all core modules, i.e., perception, prediction, and planning, InVDriver incorporates masked self-attention mechanisms that restrict attention to intra-instance point interactions, enabling coordinated refinement of structural elements while suppressing irrelevant inter-instance noise. Experimental results on the nuScenes benchmark demonstrate that InVDriver achieves state-of-the-art performance, surpassing prior methods in both accuracy and safety, while maintaining high computational efficiency. Our work validates that explicit modeling of intra-instance geometric coherence is critical for advancing vectorized autonomous driving systems, bridging the gap between theoretical advantages of end-to-end frameworks and practical deployment requirements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17949 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InVDriver: Intra-Instance Aware Vectorized Query-Based Autonomous Driving Transformer Zhang, Bo Huang, Heye Liu, Chunyang Zhang, Yaqin Xu, Zhenhua Robotics Computer Vision and Pattern Recognition End-to-end autonomous driving with its holistic optimization capabilities, has gained increasing traction in academia and industry. Vectorized representations, which preserve instance-level topological information while reducing computational overhead, have emerged as a promising paradigm. While existing vectorized query-based frameworks often overlook the inherent spatial correlations among intra-instance points, resulting in geometrically inconsistent outputs (e.g., fragmented HD map elements or oscillatory trajectories). To address these limitations, we propose InVDriver, a novel vectorized query-based system that systematically models intra-instance spatial dependencies through masked self-attention layers, thereby enhancing planning accuracy and trajectory smoothness. Across all core modules, i.e., perception, prediction, and planning, InVDriver incorporates masked self-attention mechanisms that restrict attention to intra-instance point interactions, enabling coordinated refinement of structural elements while suppressing irrelevant inter-instance noise. Experimental results on the nuScenes benchmark demonstrate that InVDriver achieves state-of-the-art performance, surpassing prior methods in both accuracy and safety, while maintaining high computational efficiency. Our work validates that explicit modeling of intra-instance geometric coherence is critical for advancing vectorized autonomous driving systems, bridging the gap between theoretical advantages of end-to-end frameworks and practical deployment requirements. |
| title | InVDriver: Intra-Instance Aware Vectorized Query-Based Autonomous Driving Transformer |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.17949 |