GISNet: Graph-Based Information Sharing Network For Vehicle Trajectory Prediction
This addresses the critical problem of accurate trajectory prediction for autonomous driving systems, offering a significant performance gain over existing models.
The paper tackles vehicle trajectory prediction by proposing GISNet, a graph-based information sharing network that encodes historical trajectories and enables information sharing between vehicles, achieving up to 50.00% improvement in accuracy measured by RMSE on public datasets.
The trajectory prediction is a critical and challenging problem in the design of an autonomous driving system. Many AI-oriented companies, such as Google Waymo, Uber and DiDi, are investigating more accurate vehicle trajectory prediction algorithms. However, the prediction performance is governed by lots of entangled factors, such as the stochastic behaviors of surrounding vehicles, historical information of self-trajectory, and relative positions of neighbors, etc. In this paper, we propose a novel graph-based information sharing network (GISNet) that allows the information sharing between the target vehicle and its surrounding vehicles. Meanwhile, the model encodes the historical trajectory information of all the vehicles in the scene. Experiments are carried out on the public NGSIM US-101 and I-80 Dataset and the prediction performance is measured by the Root Mean Square Error (RMSE). The quantitative and qualitative experimental results show that our model significantly improves the trajectory prediction accuracy, by up to 50.00%, compared to existing models.