Click on badges to follow links:
|Stable Release||Dev branch||Coverage||Documentation|
This package implements a few different non-Gaussian factor graph inference algorithms, primarily
- Multi-Modal iSAM (MM-iSAM) (see references) which does hybrid non-parametric and parametric inference/state-estimation over large factor graphs.
- Batch Parametric (akin to conventional "non-linear least squares"),
- Max-mixtures parametric,
- Other multiparametric and non-Gaussian algorithms are in the works and will be announced in due course.
Fundamentally, inference is performed via the Bayes (junction) tree where Chapman-Kolmogorov transit integral solutions are based on marginal-joint belief estimation (a sum-product / belief-propagation approximation algorithm). Many benefits such as clique recycling are also available. See the common Caesar.jl documenation for more details.
This package 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 (RoME.jl) package extends the available variables, factors, and utilities for use in robotic navigation.
Note, that IncrementalInference.jl does not have to be used with RoME.jl / Caesar.jl -- IncrementalInference.jl only implements the algebraic inference operations against mathematical abstractions such as Manifolds.jl.
Install the package from inside Julia
(v1.6) pkg> add IncrementalInference
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 # optional
Cite and 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 using the common reference at Caesar.jl Citation with IncrementalInference.jl DOI
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.