Heterogeneous Trajectory Forecasting via Risk and Scene Graph Learning

TL;DR

This paper introduces a novel risk and scene graph learning approach for heterogeneous trajectory forecasting, effectively modeling complex interactions among diverse road agents and their environment to improve prediction accuracy.

Contribution

It proposes a combined risk and scene graph framework, including HRG and HSG, to better capture agent interactions and scene semantics for trajectory forecasting.

Findings

Outperforms state-of-the-art methods on nuScenes, ApolloScape, and Argoverse datasets.

Effectively models agent interactions using collision risk metrics.

Incorporates scene semantics through hierarchical scene graph modeling.

Abstract

Heterogeneous trajectory forecasting is critical for intelligent transportation systems, but it is challenging because of the difficulty of modeling the complex interaction relations among the heterogeneous road agents as well as their agent-environment constraints. 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 agent and calculates their interaction adjacency matrix based on an effective collision risk metric. HSG of the 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 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.