基于风险筛选高价值驾驶场景，提升自动驾驶测试数据质量。
Risk-Based Filtering of Valuable Driving Situations in the Waymo Open Motion Dataset
- 用概率风险模型识别直接与间接影响的高危驾驶情境
- 相比基线方法，筛选出更复杂且互补的交互场景
- 适合自动驾驶测试数据构建与评估的研究者使用
提升自动驾驶软件性能需要富含有价值道路使用者交互的驾驶数据。本文提出一种基于风险的过滤方法，从大规模数据集中识别此类高价值驾驶情境。具体而言，采用概率风险模型检测高风险情况，创新性地考虑两类情境：一阶情境（一辆车直接影响另一辆车并引发风险）和二阶情境（影响通过中间车辆传播）。实验表明，该方法在Waymo Open Motion Dataset中有效筛选出高价值驾驶场景。相较于卡尔曼滤波难度和待预测轨迹数（Tracks-To-Predict）两个基线交互度量，本方法识别出更复杂且互补的情境，显著提升了自动驾驶测试数据的质量。风险数据已开源：https://github.com/HRI-EU/RiskBasedFiltering。
原文摘要 · Abstract (English)
Improving automated vehicle software requires driving data rich in valuable road user interactions. In this paper, we propose a risk-based filtering approach that helps identify such valuable driving situations from large datasets. Specifically, we use a probabilistic risk model to detect high-risk situations. Our method stands out by considering a) first-order situations (where one vehicle directly influences another and induces risk) and b) second-order situations (where influence propagates through an intermediary vehicle). In experiments, we show that our approach effectively selects valuable driving situations in the Waymo Open Motion Dataset. Compared to the two baseline interaction metrics of Kalman difficulty and Tracks-To-Predict (TTP), our filtering approach identifies complex and complementary situations, enriching the quality in automated vehicle testing. The risk data is made open-source: https://github.com/HRI-EU/RiskBasedFiltering.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。