Interactive Behavior Prediction for Heterogeneous Traffic Participants in the Urban Road: A Graph-Neural-Network-Based Multitask Learning Framework

Effectively predicting interactive behaviors of traffic participants in the urban road is the key to successful decision-making and motion planning of intelligent vehicles. In this article, based on the data collected from vehicle on-board sensors, a graph-neural-network-based multitask learning framework (GNN-MTLF) is proposed to accurately predict trajectories of traffic participants with interactive behaviors. The interactive behavior considered in this research includes interactive events and trajectories that are modeled as spatial-temporal graphs using the GNN. Under the GNN-MTLF, the prediction process contains two main parts: recognition of interactive events and prediction of interactive trajectories. An integrated loss function is designed for multitask learning with the purpose of prediction and recognition. The proposed framework is verified using naturalistic driving data in the urban road. Experimental results show a superior performance of the GNN-MTLF compared to baseline methods and the potential for improving the road mobility.