FutuTP: Future-based trajectory prediction for autonomous driving

Qingchao Xu, Yandong Liu, Shixi Wen, Xin Yang, Dongsheng Zhou

Abstract: Trajectory prediction is an essential aspect of autonomous driving technology. Based on the historical trajectories and environmental information, trajectory prediction methods predict the future trajectory of a vehicle. Goal-based methods have been successful because of their excellent interpretability. However, these methods ignore future lane information and interactions in future trajectories, which leads to prediction failures in some scenes. In this paper, we propose an encoder-decoder model called future-based trajectory prediction (FutuTP). The encoder fuses the interactions of future trajectories through a transformer module. The decoder predicts the future lane area and applies the results to generate a trajectory. The experimental results show that FutuTP achieves more accurate predictions than does the SOTA method on Argoverse 1. Especially in terms of the \(\text {minFDE}_6\) metric, FutuTP outperforms the SOTA method by approximately 6%. The code can be accessed via the following link: https://github.com/Qingchao-Xu/FutuTP.