Predicting future trajectories of nearby objects, especially under occlusion, is a crucial task in autonomous driving and safe robot navigation. Prior works typically neglect to maintain uncertainty about occluded objects and only predict trajectories of observed objects using high-capacity models such as Transformers trained on large datasets. While these approaches are effective in standard scenarios, they can struggle to generalize to the long-tail, safety-critical scenarios. In this work, we explore a conceptual framework unifying trajectory prediction and occlusion reasoning under the same class of structured probabilistic generative model, namely, switching dynamical systems. We then present some initial experiments illustrating its capabilities using the Waymo open dataset.
@article{arxiv.2410.10653,
title = {Navigation under uncertainty: Trajectory prediction and occlusion reasoning with switching dynamical systems},
author = {Ran Wei and Joseph Lee and Shohei Wakayama and Alexander Tschantz and Conor Heins and Christopher Buckley and John Carenbauer and Hari Thiruvengada and Mahault Albarracin and Miguel de Prado and Petter Horling and Peter Winzell and Renjith Rajagopal},
journal= {arXiv preprint arXiv:2410.10653},
year = {2024}
}