IncrementalInference.jl
Click on badges to follow links:
| Stable v0.23 | Stable v0.24 | Dev | Coverage | Documentation |
|---|---|---|---|---|
 |
 |
   |
  |
   |
Optimization routines for incremental non-parametric and parametric solutions based on factor graphs and the Bayes (Junction) tree implemented in the Julia language (and JuliaPro).
This package furthermore forms a cardinal piece of the Caesar.jl robotics toolkit, including 3D visualization and database interaction, which can serve as a base station for a robotic platform. A standalone Robot Motion Estimate package is also available.
Introduction
This package implements Multi-modal iSAM [1], a descendant of the iSAM2 [3] algorithm. The main algorithm is focused towards hybrid non-parametric and parametric inference over large factor graphs. Inference is performed via the Bayes tree (similar to Junction tree) where non-parametric and parametric solutions are based on belief propagation -- also known as the sum-product algorithm. Immediate benefits such as branch recycling is carried over as well. Also see related research work here [2].
Installation
Pre-install the following packages system wide packages[, and easily draw factor graph and Bayes tree]:
sudo apt-get install hdf5-tools
sudo apt-get install graphviz xdot # optionalInstall the package from inside Julia
(v1.5) pkg> add IncrementalInferenceExamples
This library is built as a back-end solver which is closer to the mathetical operations can be easily modified and extended for a variety of uses. Specific emphasis is placed on allowing outside user defined variables and factor definitions to be used. The current major use case is through RoME.jl and Caesar.jl which introduces various sensor measurement and motion manifold functions for use in Robot Motion Estimate (a.k.a SLAM). See these and related packages for documentation and examples.
Contributors
We are grateful for many, many contributions within the Julia package ecosystem -- see the Project.toml files for a far reaching list of upstream packages and contributions.
Consider citing our work:
@misc{caesarjl,
author = "Contributors and Dependencies",
title = "Caesar.jl",
year = 2020,
url = "https://github.com/JuliaRobotics/Caesar.jl"
}
Get Involved, and Code of Conduct
This project adheres to the JuliaRobotics code of conduct, and we invite contributions or comments from the community. Use the slack channel, Julia Discourse, or Github issues to get in touch.