Scalable nonparametric Bayesian learning for heterogeneous and dynamic velocity fields

TL;DR

This paper introduces a scalable nonparametric Bayesian model for learning complex, heterogeneous, and dynamic velocity fields in spatio-temporal data, with applications to autonomous vehicle navigation.

Contribution

It combines hierarchical Dirichlet processes, infinite hidden Markov models, and Gaussian processes with an efficient inference method for complex velocity data.

Findings

Effective on simulated datasets

Demonstrated on NGSIM vehicle interaction data

Scalable inference approach works well

Abstract

Analysis of heterogeneous patterns in complex spatio-temporal data finds usage across various domains in applied science and engineering, including training autonomous vehicles to navigate in complex traffic scenarios. Motivated by applications arising in the transportation domain, in this paper we develop a model for learning heterogeneous and dynamic patterns of velocity field data. We draw from basic nonparameric Bayesian modeling elements such as hierarchical Dirichlet process and infinite hidden Markov model, while the smoothness of each homogeneous velocity field element is captured with a Gaussian process prior. Of particular focus is a scalable approximate inference method for the proposed model; this is achieved by employing sequential MAP estimates from the infinite HMM model and an efficient sequential GP posterior computation technique, which is shown to work effectively on simulated data sets. Finally, we demonstrate the effectiveness of our techniques to the NGSIM dataset of complex multi-vehicle interactions.