Differentiable Factor Graph Optimization for Learning Smoothers

Brent Yi ¹, Michelle A. Lee ¹, Alina Kloss ², Roberto Martín-Martín ¹, Jeannette Bohg ¹

¹ Stanford University
² Max Planck Institute for Intelligent Systems

Paper

A recent line of work has shown that end-to-end optimization of Bayesian filters can be used to learn state estimators for systems whose underlying models are difficult to hand-design or tune, while retaining the core advantages of probabilistic state estimation. As an alternative approach for state estimation in these settings, we present an end-to-end approach for learning state estimators modeled as factor graph-based smoothers. By unrolling the optimizer we use for maximum a posteriori inference in these probabilistic graphical models, we can learn probabilistic system models in the full context of an overall state estimator, while also taking advantage of the distinct accuracy and runtime advantages that smoothers offer over recursive filters. We study this approach using two fundamental state estimation problems, object tracking and visual odometry, where we demonstrate a significant improvement over existing baselines.

Our work comes with an extensive code release, which includes training and evaluation scripts, as well as Python libraries for Lie theory and factor graph optimization.

Link: http://arxiv.org/abs/2105.08257

Code Release

Data & experiments: https://github.com/brentyi/dfgo

Factor graph optimization library: https://github.com/brentyi/jaxfg

Lie theory library: https://github.com/brentyi/jaxlie

Technical Overview

Bibtex

@inproceedings{yi2021iros,
author={\textbf{Brent Yi} and \textbf{Michelle Lee} and \textbf{Alina Kloss} and \textit{Roberto Mart\'in-Mart\'in} and Jeannette Bohg},
title = {Differentiable Factor Graph Optimization for Learning Smoothers},
year = 2021,
BOOKTITLE = {2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}
}

Page updated

Google Sites

Report abuse