发表机构
The Hong Kong Polytechnic University; Anhui University; Shenzhen Research Institute of Northwestern Polytechnical University（香港理工大学; 安徽大学; 西北工业大学深圳研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出VG-SAF框架，通过物理增强器、模态专家与混合注意力机制，在CARLA Longest6基准上提升非对称传感器退化下的端到端驾驶鲁棒性。
AI 中文摘要
端到端多模态驾驶通过融合相机与激光雷达（LiDAR）数据流已取得快速进展，现有 pipeline 在非对称传感器退化场景下仍存在脆弱性，即某一模态整体或仅局部区域受损，而其余区域仍可用。关键难点并非简单添加不确定性头，而是获取密集可靠性监督信号、将该可靠性与物理故障严重程度校准，并在不可靠特征干扰规划器前加以利用。本文提出方差引导空间注意力融合（VG-SAF），其中密集异方差可靠性估计可作为可解释的空间门控。该框架耦合三个组件：其一，基于物理的增强器模拟典型相机与激光雷达故障并输出连续空间掩码，无需额外标注即可提供密集监督；其二，模态特定专家通过对数空间内的跨分支密集蒸馏预测逐像素可靠性尺度，强制实现严重程度到尺度的单调响应；其三，经校准的可靠性图驱动混合注意力机制，通过局部空间门控抑制不可靠单元，并通过跨模态信任 Softmax 在模态间进行仲裁。拉普拉斯不确定性头输出系统性路径点不确定性尺度，可指示训练范围外的严重或复合传感器退化。在 CARLA Longest6 基准测试中，VG-SAF 在仅相机、仅激光雷达及联合退化场景下，均较基线方法提升了闭环鲁棒性，评价指标包括驾驶得分、路线完成率及违规得分。
英文摘要
End-to-end multimodal driving has progressed rapidly by fusing camera and LiDAR streams. Existing pipelines remain fragile under asymmetric sensor degradation, where either an entire modality or only a localized region is corrupted while other regions remain useful. The key difficulty is not simply to add an uncertainty head, but to obtain dense reliability supervision, calibrate this reliability against physical fault severity, and use it before unreliable features bias the planner. We propose Variance-Guided Spatial Attention Fusion (VG-SAF), in which dense heteroscedastic reliability estimates act as interpretable spatial gates. The framework couples three components. First, a physically grounded augmentor simulates representative camera and LiDAR failures and emits a continuous spatial mask, providing dense supervision without additional annotation. Second, modality-specific experts predict per-pixel reliability scales through cross-branch dense distillation in log space, enforcing a monotone severity-to-scale response. Third, calibrated reliability maps drive a hybrid attention mechanism that suppresses unreliable cells with a local spatial gate and arbitrates between modalities through a cross-modal trust softmax. A Laplace uncertainty head emits a systemic waypoint uncertainty scale that signals severe or combined sensor degradation, including severities outside the training ranges. On the CARLA Longest6 benchmark, VG-SAF consistently improves closed-loop robustness over the baselines across camera-only, LiDAR-only, and joint degradation regimes, as measured by driving score, route completion, and infraction score.
Comments17 pages, 9 figures, and 4 tables, including supplementary material. Submitted to IEEE Transactions on Vehicular Technology
