CARA：用于可解释碰撞预测的概念感知风险注意力
CARA: Concept-Aware Risk Attention for Interpretable Collision Anticipation
- Shanghai Jiao Tong University（上海交通大学）
- The University of Hong Kong（香港大学）
- Fudan University（复旦大学）
- The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
- University of Pennsylvania（宾夕法尼亚大学）
- Renmin University of China（中国人民大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究自动驾驶碰撞预测问题，提出CARA框架，从事故叙述中获取风险概念并与视频帧对齐成轨迹，将语义风险因素作为动态证据，结合可解释性与预测过程，实验证明其能提高预测准确性和预警及时性。
AI中文摘要：
自动驾驶中的碰撞预测不仅需要准确的早期预警，还需要对所跟踪的风险因素以及风险如何随时间演变进行可解释的推理。现有方法在这方面存在不足：基于特征的模型不透明，事后解释往往缺乏保真度，基于概念的方法大多用于静态识别而非动态驾驶场景。我们提出了CARA（概念感知风险注意力），一种用于碰撞预测的内在可解释的时空框架。CARA从事故叙述中得出基于领域的风险概念，通过视觉语言相似度将它们与视频帧对齐，并将它们组织成不断演变的概念轨迹。这些轨迹提供明确的风险证据，指导空间注意力、时间注意力和预测，使语义概念直接影响模型关注的位置以及它如何随时间预测风险。通过将语义风险因素视为动态中间证据而非辅助事后解释，CARA将可解释性与预测过程紧密结合。在三个基准上的大量实验表明，CARA在强大的基线之上持续提高了预测准确性和预警及时性，同时提供了稀疏且基于语义的概念证据。
英文摘要：
Collision anticipation in autonomous driving requires not only accurate early warnings but also interpretable reasoning about what risk factors are being tracked and how risk evolves over time. Existing methods fall short in this regard: feature-driven models are opaque, post-hoc explanations often lack fidelity, and concept-based methods are mostly designed for static recognition rather than dynamic driving scenes. We propose CARA (Concept-Aware Risk Attention), an intrinsically interpretable spatio-temporal framework for collision anticipation. CARA derives domain-grounded risk concepts from accident narratives, aligns them with video frames via vision-language similarity, and organizes them into evolving concept trajectories. These trajectories provide explicit risk evidence that guides spatial attention, temporal attention, and anticipation, allowing semantic concepts to directly influence both where the model attends and how it predicts risk over time. By treating semantic risk factors as dynamic intermediate evidence rather than auxiliary post-hoc explanations, CARA tightly couples interpretability with the predictive process. Extensive experiments on three benchmarks show that CARA consistently improves anticipation accuracy and warning earliness over strong baselines, while providing sparse and semantically grounded concept evidence.
