Heterogeneous trajectory forecasting is critical for intelligent transportation systems, while it is challenging because of the difficulty for modeling the complex interaction relations among the heterogeneous road agents as well as their agent-environment constraint. In this work, we propose a risk and scene graph learning method for trajectory forecasting of heterogeneous road agents, which consists of a Heterogeneous Risk Graph (HRG) and a Hierarchical Scene Graph (HSG) from the aspects of agent category and their movable semantic regions. HRG groups each kind of road agents and calculates their interaction adjacency matrix based on an effective collision risk metric. HSG of driving scene is modeled by inferring the relationship between road agents and road semantic layout aligned by the road scene grammar. Based on this formulation, we can obtain an effective trajectory forecasting in driving situations, and superior performance to other state-of-the-art approaches is demonstrated by exhaustive experiments on the nuScenes, ApolloScape, and Argoverse datasets.

翻译：在这项工作中,我们提出了一种风险图和场景图学学习方法,用于不同道路物剂的轨迹预测,其中包括来自物剂类别及其可移动语系区域各个方面的异质风险图(HRG)和高层次场景图(HSG),各种类型的道路物剂组,并根据有效的碰撞风险指标计算出其相互作用的相邻矩阵。驾驶场HSG的模型是推断道路物剂与公路场景语义布局之间的关系。根据这一公式,我们可以在驾驶情况中取得有效的轨迹预测,其他最先进的方法的优异性表现表现表现表现表现表现表现表现表现在对核Scenes、阿波罗斯卡佩和Argoverse数据集的详尽实验中。