外观
论文arXiv 2610.1148320 天前
BridgeGuard：面向基于 Diffusion 的自动驾驶的显式安全漂移
原文链接：BridgeGuard: Explicit Safety Drift for Diffusion-based Autonomous Driving（arXiv 2610.11483 · 发布日期：2026-10-08）
BridgeGuard: Explicit Safety Drift for Diffusion-based Autonomous Driving
针对分布偏移下扩散驾驶规划可能不安全，BridgeGuard以渐强安全约束修正轨迹，并在Bench2Drive上验证提升。
核心要点
- 扩散式驾驶规划能捕获多样行为，但在分布偏移下可能生成不安全轨迹。
- BridgeGuard在去噪中逐步增强场景相关安全域约束，并在低维曲线空间修正轨迹。
- DistanceFieldNet从鸟瞰图特征预测时变距离场，用安全注入提供约束项。
- 在Bench2Drive上，BridgeGuard提升BridgeDrive和DiffusionDrive^{geo}的驾驶分数与成功率。
验证范围与局限：验证范围为Bench2Drive上的BridgeDrive与DiffusionDrive^{geo}。
英文摘要 (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.
作者：Zhenjun Qiu, Jianing Huang, Dongang Liu, Baiyu Du, Yixun Niu, Hao Yang, Xinyu Huang, Chuan Hu, Shu Liu
来源
本页事实对应的公开页面，以原文为准。