A modern robotic toolkit for localization and mapping -- reducing the barrier of entry for Simultaneous Localization and Mapping (SLAM).
Towards non-parametric / parametric state estimation and navigation solutions [1]. Implemented in Julia (and JuliaPro) for a fast, flexible, dynamic and productive robot designer experience. This framework maintains good interoperability with other languages like C/C++ or Python, as listed in features below. Multi-modal (quasi-multi-hypothesis) navigation and mapping solutions, using various sensor data, is a corner stone of this package. Multi-sensor fusion is made possible via vertically integrated Multi-modal iSAM.
Critically, this package can operate in the conventional SLAM manner, using local dictionaries, or centralize around the FactorGraph
through a graph database using CloudGraphs.jl, as discussed here[2]. A variety of plotting, 3D visualization, serialization, LCM middleware, and analysis tools come standard. Please see internal packages, Robot Motion Estimate RoME.jl and back-end solver IncrementalInference.jl.
Comments, questions and issues welcome.
Please see the documentation:
Please see the Arena.jl package for the concentration of all 2D and 3D visualization utilities of the Caesar.jl robot navigation packages.
Caesar can be installed with:
julia> Pkg.add("Caesar")
Major Dependencies | Status | Test Coverage |
---|---|---|
Caesar.jl | ||
RoME.jl | ||
IncrementalInference.jl | ||
KernelDensityEstimate.jl | ||
TransformUtils.jl | ||
Graphs.jl | ||
CloudGraphs.jl |
Authors directly involved with this package are:
D. Fourie, S. Claassens, P. Vaz Teixeira, N. Rypkema, S. Pillai, R. Mata, M. Kaess, J. Leonard
We are grateful for many, many contributions within the Julia package ecosystem -- see the REQUIRE
files of Caesar, Arena, RoME, RoMEPlotting, KernelDensityEstimate, IncrementalInference, NLsolve, DrakeVisualizer, Graphs, CloudGraphs
and others for a far reaching list of contributions.
Consider citing our work:
@misc{caesarjl,
author = "Dehann Fourie, John Leonard, Micheal Kaess, and contributors",
title = "Caesar.jl",
year = 2017,
url = "https://github.com/dehann/Caesar.jl"
}