论文标题
轻量级的机器学习管道，用于激光镜像
A Lightweight Machine Learning Pipeline for LiDAR-simulation
论文作者
论文摘要
虚拟测试是确保自动驾驶安全性的至关重要的任务，而传感器模拟是该领域的重要任务。当前大多数LiDAR模拟非常简单，主要用于执行初始测试，而大多数见解是在路上收集的。在本文中，我们提出了一种轻巧的方法，以实现更现实的激光雷达模拟，该方法从测试驱动器数据中学习了真实传感器的行为，并将其转换为虚拟域。核心思想是将仿真施加到图像到图像翻译问题中。我们将基于PIX2PIX的架构训练两个现实世界数据集，即流行的Kitti数据集和提供RGB和LIDAR图像的Audi自动驾驶数据集。我们将该网络应用于合成渲染，并表明它从真实图像到模拟图像充分概括。该策略使我们可以在我们的合成世界中跳过传感器特异性，昂贵且复杂的LiDAR物理学模拟，并避免过度简化和通过干净的合成环境较大的域间隙。
Virtual testing is a crucial task to ensure safety in autonomous driving, and sensor simulation is an important task in this domain. Most current LiDAR simulations are very simplistic and are mainly used to perform initial tests, while the majority of insights are gathered on the road. In this paper, we propose a lightweight approach for more realistic LiDAR simulation that learns a real sensor's behavior from test drive data and transforms this to the virtual domain. The central idea is to cast the simulation into an image-to-image translation problem. We train our pix2pix based architecture on two real world data sets, namely the popular KITTI data set and the Audi Autonomous Driving Dataset which provide both, RGB and LiDAR images. We apply this network on synthetic renderings and show that it generalizes sufficiently from real images to simulated images. This strategy enables to skip the sensor-specific, expensive and complex LiDAR physics simulation in our synthetic world and avoids oversimplification and a large domain-gap through the clean synthetic environment.
