Ego‐planning‐guided multi‐graph convolutional network for heterogeneous agent trajectory prediction
Zihao Sheng, Zilin Huang, Sikai Chen
Abstract
Accurate prediction of the future trajectories of traffic agents is a critical aspect of autonomous vehicle navigation. However, most existing approaches focus on predicting trajectories from a static roadside perspective, ignoring the influence of autonomous vehicles’ future plans on neighboring traffic agents. To address this challenge, this paper introduces EPG-MGCN, an ego-planning-guided multi-graph convolutional network. EPG-MGCN leverages graph convolutional networks and ego-planning guidance to predict the trajectories of heterogeneous traffic agents near the ego vehicle. The model captures interactions through multiple graph topologies from four distinct perspectives: distance, visibility, ego planning, and category. Additionally, it encodes the ego vehicle's planning information via the planning graph and a planning-guided prediction module. The model is evaluated on three challenging trajectory datasets: ApolloScape, nuScenes, and next generation simulation (NGSIM). Comparative evaluations against mainstream methods demonstrate its superior predictive capabilities and inference speed.