Navigation under uncertainty: Trajectory prediction and occlusion reasoning with switching dynamical systems

TL;DR

This paper introduces a unified probabilistic framework using switching dynamical systems for trajectory prediction and occlusion reasoning in autonomous navigation, aiming to improve safety and generalization in complex scenarios.

Contribution

It proposes a novel structured probabilistic model that combines trajectory prediction and occlusion reasoning, addressing limitations of existing high-capacity models.

Findings

Initial experiments on Waymo dataset demonstrate the model's potential.

The framework effectively unifies trajectory prediction and occlusion reasoning.

Results suggest improved handling of occluded objects in navigation tasks.

Abstract

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.