Differentiable Factor Graph Optimization for Learning Smoothers
2021
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, this method is able to 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 our 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 the evaluated models and libraries for
differentiable Lie theory and factor graph optimization:
https://sites.google.com/view/diffsmoothing/
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
45
References
2
Citations
NaN
KQI