Haar Wavelet based Block Autoregressive Flows for Trajectories

09/21/2020
by   Apratim Bhattacharyya, et al.
4

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.

READ FULL TEXT

Authors

page 10

page 11

page 17

page 18

04/08/2020

Normalizing Flows with Multi-Scale Autoregressive Priors

Flow-based generative models are an important class of exact inference m...
03/12/2017

Prediction and Control with Temporal Segment Models

We introduce a method for learning the dynamics of complex nonlinear sys...
10/26/2020

Wavelet Flow: Fast Training of High Resolution Normalizing Flows

Normalizing flows are a class of probabilistic generative models which a...
05/24/2019

Discrete Flows: Invertible Generative Models of Discrete Data

While normalizing flows have led to significant advances in modeling hig...
12/17/2019

HCNAF: Hyper-Conditioned Neural Autoregressive Flow and its Application for Probabilistic Occupancy Map Forecasting

We introduce Hyper-Conditioned Neural Autoregressive Flow (HCNAF); a pow...
12/14/2021

Deep Generative Models for Vehicle Speed Trajectories

Generating realistic vehicle speed trajectories is a crucial component i...
06/26/2022

Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One

Autoregressive generative models are commonly used, especially for those...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.