SevDiff：用于长尾冲突轨迹生成的严重程度条件扩散
SevDiff: Severity-Conditioned Diffusion for Long-Tail Conflict Trajectory Generation
浏览论文内容
中文总结 AI 辅助
研究针对ADAS评估中冲突轨迹罕见及现有方法不足的问题，提出SevDiff严重程度条件扩散模型，以TTC值为调节信号生成配对轨迹，经训练在不同TTC目标下有高命中率，生成特征物理合理，命中率下降模式可精确表征生成器。
中文摘要 AI 辅助
用于ADAS评估的轨迹数据集严重偏向常规驾驶；真正的车对车冲突事件很少见，事件越罕见，ADAS系统处理失败时成本越高。现有生成方法通过场景级属性进行调节来解决这种不平衡，但无法接受目标碰撞时间（TTC）值作为输入并在可测量误差内生成。本文介绍了SevDiff，一种严重程度条件去噪扩散概率模型（DDPM），它接受请求的最小TTC值作为标量调节信号，并生成配对的车辆交互轨迹，其实现的冲突严重程度与请求匹配，通过命中率指标进行评估。在从UTE SQM-W-1高速公路交织段数据集提取的468个交互窗口上进行训练，SevDiff在TTC目标为0.5-1.5秒时，在+/-0.5秒内达到100%的命中率，在2.0-2.5秒时达到97-99%，在TTC=5.0秒时降至39%。生成的运动学特征在物理上是合理的，最大超范围率为4.7%，超过96.5%的样本中没有负速度或间隙值。命中率下降模式在物理上可解释为调节信号相对于训练先验的强度，使其成为生成器的精确表征而非通过/失败结果。
英文摘要
Trajectory datasets used in ADAS evaluation are heavily biased toward routine driving; genuine vehicle-to-vehicle conflict events are rare, and the rarer the event, the higher the cost when an ADAS system fails to handle it. Existing generative approaches address this imbalance by conditioning on scene-level properties - spatial goals, agent structure, or natural-language adversarial objectives - but none can accept a target Time-to-Collision (TTC) value as input and be held to producing it within a measurable error. This paper introduces SevDiff, a severity-conditioned denoising diffusion probabilistic model (DDPM) that accepts a requested minimum TTC value as a scalar conditioning signal and generates paired vehicle interaction trajectories whose realized conflict severity matches the request, evaluated through a hit-rate metric. Trained on 468 interaction windows extracted from the UTE SQM-W-1 expressway weaving-section dataset (1,041 vehicles, 822,691 observations after smoothing), SevDiff achieves 100% hit-rate within +/-0.5 s for TTC targets of 0.5-1.5 s and 97-99% at 2.0-2.5 s, with graceful degradation to 39% at TTC = 5.0 s. Generated kinematic features are physically plausible, with a maximum out-of-range rate of 4.7% across 12 features and no negative speed or gap values in more than 96.5% of samples. The hit-rate degradation pattern is physically interpretable as the strength of the conditioning signal relative to the training prior, making it a precision characterization of the generator rather than a pass/fail result.
