arXiv：cs.AI· Zhenjun Qiu, Jianing Huang, Dongang Liu, Baiyu Du, Yixun Niu, Hao Yang, Xinyu Huang, Chuan Hu, Shu Liu·· 3 小时前
BridgeGuard：面向扩散式自动驾驶的显式安全漂移约束规划方法
BridgeGuard: Explicit Safety Drift for Diffusion-based Autonomous Driving
AI 导读
BridgeGuard 是一种安全约束扩散规划方法，在去噪过程中逐步强化约束项，将中间轨迹推向随场景变化的安全域，修正发生在低维曲线空间以保持几何一致性。其 DistanceFieldNet 从鸟瞰特征预测时变距离场，并通过对专家轨迹之外采样点的值与空间梯度监督学习安全与不安全区域，注入约束时预训练感知骨干与规划器保持冻结。
正文
Abstract:Diffusion-based driving planners capture diverse behaviors but can generate unsafe trajectories under distribution shift. We propose BridgeGuard, a safety-constrained diffusion planning method that progressively strengthens a constraint term during denoising to drive intermediate trajectories toward a scene-dependent safety domain. Corrections operate in a low-dimensional curve space, promoting geometric coherence. A learned module, DistanceFieldNet, predicts a time-dependent distance field from bird's-eye-view features. Value and spatial-gradient supervision at queries sampled beyond expert trajectories teaches this field about both safe and unsafe regions. The learned field supplies the constraint term through safety injection while the pretrained perception backbone and planner remain frozen. We further establish sufficient conditions for terminal safety in an idealized continuous-time bridge. On Bench2Drive, BridgeGuard improves driving score/success rate from 87.99/74.99% to 90.88/76.36% for BridgeDrive and from 80.79/58.18% to 90.46/74.09% for $\text{DiffusionDrive}^{\text{geo}}$, demonstrating cross-model generalization.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11483 [cs.AI] |
| (or arXiv:2610.11483v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11483 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jianing Huang [view email]
[v1]
Thu, 8 Oct 2026 08:26:52 UTC (4,275 KB)
来源：arXiv：cs.AI · arxiv.org