Haar Wavelet based Block Autoregressive Flows for Trajectories

TL;DR

This paper introduces a Haar wavelet based block autoregressive flow model that captures hierarchical, multiscale trajectory dependencies for improved prediction of pedestrian paths, enabling exact inference and diverse, accurate results.

Contribution

It proposes a novel Haar wavelet based block autoregressive model with split couplings for hierarchical trajectory modeling, improving over existing generative approaches.

Findings

Effective in generating diverse trajectories

Achieves accurate predictions on real-world datasets

Models multiscale dependencies hierarchically

Abstract

Prediction of trajectories such as that of pedestrians is crucial to the performance of autonomous agents. While previous works have leveraged conditional generative models like GANs and VAEs for learning the likely future trajectories, accurately modeling the dependency structure of these multimodal distributions, particularly over long time horizons remains challenging. Normalizing flow based generative models can model complex distributions admitting exact inference. These include variants with split coupling invertible transformations that are easier to parallelize compared to their autoregressive counterparts. To this end, we introduce a novel Haar wavelet based block autoregressive model leveraging split couplings, conditioned on coarse trajectories obtained from Haar wavelet based transformations at different levels of granularity. This yields an exact inference method that models trajectories at different spatio-temporal resolutions in a hierarchical manner. We illustrate the advantages of our approach for generating diverse and accurate trajectories on two real-world datasets - Stanford Drone and Intersection Drone.