Trajectory prediction plays a vital role in automotive radar systems, facilitating precise tracking and decision-making in autonomous driving. Generative adversarial networks with the ability to learn a distribution over future trajectories tend to predict out-of-distribution samples, which typically occurs when the distribution of forthcoming paths comprises a blend of various manifolds that may be disconnected. To address this issue, we propose a trajectory prediction framework, which can capture the social interaction variations and model disconnected manifolds of pedestrian trajectories. Our framework is based on a fused spatiotemporal graph to better model the complex interactions of pedestrians in a scene, and a multi-generator architecture that incorporates a flexible generator selector network on generated trajectories to learn a distribution over multiple generators. We show that our framework achieves state-of-the-art performance compared with several baselines on different challenging datasets.
@article{arxiv.2311.02835,
title = {Flexible Multi-Generator Model with Fused Spatiotemporal Graph for Trajectory Prediction},
author = {Peiyuan Zhu and Fengxia Han and Hao Deng},
journal= {arXiv preprint arXiv:2311.02835},
year = {2023}
}