Abstract: To accurately perceive the environment and predict the trajectory of the surrounding traffic participants for autonomous driving,we propose a real-time end-to-end trajectory prediction framework based on bird eye view(BEV) to learn both interaction and scene information simultaneously.The framework consists of two essential modules:graph interaction network and pyramid perception network.The former encodes the interaction patterns among traffic participants through a spatiotemporal graph convolutional network,and the latter adopts a spatiotemporal pyramid network to model the surrounding information and obtain the scene features.Next,interactive features and scene features are fused at a unified scale to perform classification and trajectory prediction tasks.Experiments and analysis on Nuscenes,a large open-source dataset,indicate that the proposed framework achieves a higher classification accuracy of 3.1% and 1.43% less predicted trajectory loss than MotionNet.Hence,our framework outperforms state-of-the-art algorithms in terms of generalization and robustness,and is more in line with perception requirements in actual autonomous driving scenes.

Key words: Trajectory prediction, Spatiotemporal graph convolutional, Spatiotemporal pyramid, Graph interaction encoding, Feature fusion