InVDriver: Intra-Instance Aware Vectorized Query-Based Autonomous Driving Transformer

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Bo, Huang, Heye, Liu, Chunyang, Zhang, Yaqin, Xu, Zhenhua
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