CorrRisk-WM：用于安全关键轨迹规划的走廊条件风险世界建模
CorrRisk-WM: Corridor-Conditioned Risk World Modeling for Safety-Critical Trajectory Planning
浏览论文内容
中文总结 AI 辅助
本文提出CorrRisk-WM，一种面向规划的局部世界模型，通过耦合环境演化与候选走廊监督预测，在Waymo数据集上实现高精度入侵与近失风险预测，并降低开环碰撞率。
中文摘要 AI 辅助
安全局部规划需要预测周围智能体的运动并评估特定于候选轨迹的风险，因为相同的智能体运动可能对不同的自我轨迹构成不同的风险。我们提出了CorrRisk-WM，一种面向规划的局部世界模型，它将环境演化与对有界候选轨迹走廊的监督入侵和近失预测相结合。一个潜在环境模型递归地预测智能体状态，并更新智能体-智能体和智能体-地图交互。每个候选轨迹通过足迹感知几何和学习的智能体-走廊表示来查询演化中的环境。一个轻量级循环风险模块利用时间上下文来估计每个切片的危险；生存聚合产生首次进入和水平层面的事件概率。在来自100个Waymo验证分片的29,176个场景上，CorrRisk-WM实现了入侵平均精度（AP）为0.8567，1米近失首次进入AP为0.8671。在基线比较中，它在所有三个距离阈值下取得了最高的近失AP，并实现了最低的观测开环碰撞率（4.88%），路线进展为15.35米。在三个种子上，移除动态环境建模或候选条件几何交互将平均入侵AP分别从0.8590降至0.7624和0.7252。这些结果支持将环境演化与候选条件几何推理相结合，用于风险预测和面向安全的候选选择。
英文摘要
Safe local planning requires forecasting surrounding-agent motion and evaluating candidate-specific risks, since identical agent motion can pose different risks to different ego trajectories. We present CorrRisk-WM, a planning-oriented partial world model coupling environment evolution with supervised intrusion and near-miss prediction over bounded candidate-trajectory corridors. A latent environment model recursively predicts agent states and updates agent-agent and agent-map interactions. Each candidate queries the evolving environment through footprint- aware geometry and learned agent-corridor representations. A lightweight recurrent risk module uses temporal context to estimate per-slice hazards; survival aggregation yields first-entry and horizon-level event probabilities. On 29,176 scenarios from 100 Waymo validation shards, CorrRisk-WM achieves intrusion average precision (AP) of 0.8567 and 1-m near-miss first-entry AP of 0.8671. In baseline comparisons, it attains the highest near-miss AP at all three distance thresholds and the lowest observed open-loop collision rate (4.88%), with route progress of 15.35 m. Across three seeds, removing dynamic environment modeling or candidate-conditioned geometric interaction reduces mean intrusion AP from 0.8590 to 0.7624 and 0.7252, respectively. These results support coupling environment evolution with candidate-conditioned geometric reasoning for risk prediction and safety-oriented candidate selection.
发表机构
- Texas A&M University（德克萨斯A&M大学）
机构由 AI 辅助整理，请以论文原文为准。
