Michel Hidalgo comments

Results 403 comments of


                                            Michel Hidalgo

[AMCL] pf_z's default value seems wrong and is assigned directly into pop_z

It's 2.33 for 99% and 3.0 for 99.7%. The difference in practice is likely negligible, as @mikeferguson says.

Extending likelihood field to model unexplored spaces

@DPR00 we should update the PR title.

Extending likelihood field to model unexplored spaces

This is no draft anymore, it's solid PR material.

Extending likelihood field to model unexplored spaces

This PR needs a rebase after #433.

ROS Noetic EOL: beluga doesn't build on buildfarm

@sloretz we are aware, see #389. It's unlikely we'll fix and re-release before Noetic goes EOL. `armhf` is exotic enough these days to not have received much attention.

ROS Noetic EOL: beluga doesn't build on buildfarm

Cleaning up now that Noetic is officially EOL'd

Missing compatibility notes Beluga/Nav2

@glpuga I think you are looking for https://ekumen-os.github.io/beluga/packages/beluga_amcl/docs/ros2-reference.html#compatibility-notes. This now lives in https://github.com/Ekumen-OS/beluga/blob/main/beluga_amcl/docs/ros2-reference.md.

Add option to remove the adaptiveness to the core filter pipeline

Coming back to this, is adaptiveness the problem or is it the use of random state samples to fight sample impoverishment? Good ol' AMCL does both, but it need not,...

Add option to remove the adaptiveness to the core filter pipeline

I think we can discuss if a class is the best incarnation of a complete particle filtering algorithm with state, also if the core library is the best place for...

Implement low-variance sampling algorithm

@larodriguez22 may I take this to completion or are you still working on it?