FloMo: Tractable Motion Prediction with Normalizing Flows

TL;DR

FloMo is a novel normalizing flow-based model for traffic motion prediction that reliably estimates trajectory likelihoods, enabling safer planning for autonomous systems.

Contribution

It introduces FloMo, a normalizing flow model for motion prediction that allows direct likelihood computation and improved training stability and generalization.

Findings

Achieves state-of-the-art results on three prediction datasets.

Provides reliable likelihood estimates for predicted trajectories.

Demonstrates improved performance with new data augmentation techniques.

Abstract

The future motion of traffic participants is inherently uncertain. To plan safely, therefore, an autonomous agent must take into account multiple possible trajectory outcomes and prioritize them. Recently, this problem has been addressed with generative neural networks. However, most generative models either do not learn the true underlying trajectory distribution reliably, or do not allow predictions to be associated with likelihoods. In our work, we model motion prediction directly as a density estimation problem with a normalizing flow between a noise distribution and the future motion distribution. Our model, named FloMo, allows likelihoods to be computed in a single network pass and can be trained directly with maximum likelihood estimation. Furthermore, we propose a method to stabilize training flows on trajectory datasets and a new data augmentation transformation that improves the performance and generalization of our model. Our method achieves state-of-the-art performance on three popular prediction datasets, with a significant gap to most competing models.