Social Force Embedded Mixed Graph Convolutional Network for Multi-Class Trajectory Prediction

Accurate prediction of agent motion trajectories is crucial for ensuring the safety and reliability of autonomous driving systems. Current research predominantly focuses on traditional deep learning methods, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs), which use relative distances to predict the trajectories of a single class of agents. However, in complex traffic scenarios, the motion behaviors of diverse traffic participants exhibit highly stochastic. Sole reliance on relative distances may not sufficiently capture nuanced interaction patterns between different classes of road users. To address this challenge, we propose a novel multi-class trajectory prediction method named the social force embedded mixed graph convolutional network (SFEM-GCN). SFEM-GCN comprises three graph topologies: the semantic graph (SG), position graph (PG), and velocity graph (VG). These graphs encode various social force relationships among different classes of agents in complex scenes. Specifically, SG utilizes one-hot encoding of agent-class information to guide the construction of graph adjacency matrices based on semantic information. PG and VG create adjacency matrices to capture motion interaction relationships between different classes of agents. These graph structures are then integrated into a mixed graph, where learning is conducted using a spatio-temporal graph convolutional neural network (ST-GCNN). To further enhance prediction performance, we adopt temporal convolutional networks (TCNs) to generate the predicted trajectory with fewer parameters. Extensive experiments on the widely recognized open-source dataset demonstrate that SFEM-GCN surpasses state-of-the-art methods in terms of accuracy and robustness.