English(EN) Robust Fusion of Object-Level V2X for Learned 3D Object Detection

研究人员开发用于通过V2X数据进行鲁棒3D目标检测的噪声感知训练

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-01 12:06

研究人员开发了一种将车联网（V2X）通信数据集成到自动驾驶3D目标检测系统中的新方法。该方法旨在克服车载传感器（如摄像头和雷达）的局限性，这些传感器在遮挡和能见度差的情况下表现不佳。该研究引入了一种噪声感知训练策略，以确保系统即使在V2X数据不完美（如延迟和低渗透率）的情况下也能保持鲁棒性。 AI

影响通过有效集成不完美的V2X数据，增强了自动驾驶感知系统的鲁棒性。

排序理由这是一篇研究论文，详细介绍了一种改进自动驾驶汽车3D目标检测的新方法。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Lukas Ostendorf, Lennart Reiher, Onn Haran, Lutz Eckstein · 2026-05-04 04:00

Robust Fusion of Object-Level V2X for Learned 3D Object Detection

arXiv:2605.00595v1 Announce Type: new Abstract: Perception for automated driving is largely based on onboard environmental sensors, such as cameras and radar, which are cost-effective but limited by line-of-sight and field-of-view constraints. These inherent limitations may cause…
arXiv cs.CV TIER_1 English(EN) · Lutz Eckstein · 2026-05-01 12:06

Robust Fusion of Object-Level V2X for Learned 3D Object Detection

Perception for automated driving is largely based on onboard environmental sensors, such as cameras and radar, which are cost-effective but limited by line-of-sight and field-of-view constraints. These inherent limitations may cause onboard perception to fail under occlusions or …