道路交通网络金字塔模型车道级特征层构建

Constructing lane-level feature layer of road network pyramid model

车道级道路网络模型在自动驾驶中具有非常重要的作用,文中依据车道及相邻车道之间的通行规则,以车道组、车道段作为建模基本元素,基于道路交通网络金字塔模型,设计了车道级特征层的表达结构,提出基于实际车道分隔线特性的自动构建方法,通过实例实现了模型的建立。文中所设计的车道特征层可优化车道的描述与组织,减少数据存储冗余,能为自动驾驶提供车道级微观路径规划。

The lane-level model of road network plays an important role in autonomous driving. In this paper, according to the traffic rules between lanes and adjacent lanes, lane groups and lane segments are taken as basic elements of modeling, and the expression structure of lane-level feature layer is designed based on the pyramid model of road network. An automatic construction method based on the characteristics of lane divider is proposed, and the model is tested with examples. The lane-level feature layer designed in this paper can optimize the description and organization of lanes, and reduce the redundancy of data storage. It can be used for lane-level micro path planning in autonomous driving.