Through constant improvements in recent years radar sensors have become a viable alternative to lidar as the main distancing sensor of an autonomous vehicle. Although robust and with the possibility to directly measure the radial velocity, it brings it's own set of challenges, for which existing algorithms need to be adapted. One core algorithm of a perception system is dynamic occupancy grid mapping, which has traditionally relied on lidar. In this paper we present a dual-weight particle filter as an extension for a Bayesian occupancy grid mapping framework to allow to operate it with radar as its main sensors. It uses two separate particle weights that are computed differently to compensate that a radial velocity measurement in many situations is not able to capture the actual velocity of an object. We evaluate the method extensively with simulated data and show the advantages over existing single weight solutions.
翻译:在今年以来的不断改进的过程中,雷达传感器已成为自动驾驶汽车的主要距离传感器,成为了激光雷达的可行替代品。尽管其鲁棒性和直接测量径向速度的能力,但其带来了自己的一系列挑战,需要适应现有算法。感知系统的核心算法之一是动态占用格网图绘制,传统上依赖于激光雷达。在本文中,我们提出了双重权重粒子滤波器作为贝叶斯占用格网绘制框架的扩展,以便将其作为主要传感器使用雷达来操作。它使用两个不同计算的分别计算的粒子权重,以补偿径向速度测量在许多情况下无法捕捉物体的实际速度的限制。我们使用模拟数据对该方法进行了广泛评估,并展示了相对于现有的单重解决方案的优势。