Dehann Fourie
Dehann Fourie
https://juliarobotics.org/Caesar.jl/latest/concepts/dataassociation/#Various-SamplableBelief-Distribution-Types
Something like: `ppe.mean` `ppe.covariance` all sorts of issues for multimodal, non-Gaussian cases, etc. The value "Covariance" is still perfectly valid, but then we would also need a way to support...
Use IIF v0.27 distribution packing types instead of legacy duplicates: https://github.com/JuliaRobotics/Caesar.jl/blob/master/src/zmq/models/distributions.jl New IIF v0.27 ones here: https://github.com/JuliaRobotics/IncrementalInference.jl/tree/master/src/Serialization/entities
Which format to publish first: - Occupancy Grid, - Signed Distance Functions - TSDF, - ESDF, ---- Quick references: - Distributed 3D Manifold TSDF https://hal.archives-ouvertes.fr/hal-02335904/document - Kintinuous' TSDF: https://www.ri.cmu.edu/pub_files/2012/7/Whelan12rssw.pdf -...
Predict this within a few seconds to help size hardware for solve.
Lets just start a common location in docs for this is how we work with image axes and robot axes together with example camera calibration matrix for reference
go from one plane to another, using AprilTags or similar.
Initial example, see here: https://github.com/JuliaRobotics/Caesar.jl/blob/1f7d8438a129b28a1c310c634c6af3deffd7b0b3/examples/marine/asv/philos/IngestROSbag.jl#L137-L186