JaywalkerVR：一种用于采集安全关键型行人-车辆交互数据的VR系统
JaywalkerVR: A VR System for Collecting Safety-Critical Pedestrian-Vehicle Interactions
AI总结：
本文提出VR人在环模拟器JaywalkerVR，用于安全高效地采集罕见行人-车辆交互数据，并构建CARLA-VR数据集，使训练模型在位移误差和碰撞率上分别改善10.7%和4.9%。
摘要：
开发能够与行人安全交互的自动驾驶汽车，需要大量的行人与车辆数据，以学习准确的行人-车辆交互模型。然而，采集包含关键但罕见场景的数据——例如行人乱穿马路进入繁忙车流——可能成本高昂且不安全。我们提出了一种虚拟现实人在环模拟器JaywalkerVR，用于获取车辆-行人交互数据以应对这些挑战。我们的系统能够高效、低成本且安全地采集长尾行人-车辆交互数据。利用所提出的模拟器，我们创建了一个高质量数据集，包含来自安全关键场景的车辆-行人交互数据，称为CARLA-VR。CARLA-VR数据集弥补了常用真实世界自动驾驶数据集中长尾数据样本的不足。我们证明，使用CARLA-VR训练的模型将位移误差和碰撞率分别降低了10.7%和4.9%，并且在罕见车辆-行人场景中更具鲁棒性。
英文摘要：
Developing autonomous vehicles that can safely interact with pedestrians requires large amounts of pedestrian and vehicle data in order to learn accurate pedestrian-vehicle interaction models. However, gathering data that include crucial but rare scenarios - such as pedestrians jaywalking into heavy traffic - can be costly and unsafe to collect. We propose a virtual reality human-in-the-loop simulator, JaywalkerVR, to obtain vehicle-pedestrian interaction data to address these challenges. Our system enables efficient, affordable, and safe collection of long-tail pedestrian-vehicle interaction data. Using our proposed simulator, we create a high-quality dataset with vehicle-pedestrian interaction data from safety critical scenarios called CARLA-VR. The CARLA-VR dataset addresses the lack of long-tail data samples in commonly used real world autonomous driving datasets. We demonstrate that models trained with CARLA-VR improve displacement error and collision rate by 10.7% and 4.9%, respectively, and are more robust in rare vehicle-pedestrian scenarios.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
