#9 Add likelihood calculation for use with IMM

[Adrian Figueroa]

Hello again!

I would like to use IMM (see for example https://secwww.jhuapl.edu/techdigest/Content/techdigest/pdf/V22-N04/22-04-Genovese.pdf) in combination with your library. However, some intermediate results from the observe step may be required in order to do that.

I am currently implementing an additional observe function that gives back some internals from the UKF, so that IMM can use them (likelihood, innovation, innovation covariance). Therefore, original observe functionality will remain unchanged. If you agree, I would like to contribute the changes upstream, when they are finished.

During editing, I noticed that formatting can be inconsistent and that my automatic formatting introduces additional changes, which is not great for reviewing. How do you currently format, do you have some rustfmt.toml that you can share?

I currently use the following at the moment:

group_imports = "StdExternalCrate"
imports_granularity = "Module"
edition = "2024"
max_width = 120

This requires running with cargo +nightly fmt. This creates consistent import ordering as well.

Best regards,
Adrian

[Adrian Figueroa]

I made my changes public here: https://gitlab.com/mic_public/bayes-estimate/-/merge_requests/1
Sorry for the formatting clutter.

[Michael Stevens]

Cool I take a look. Thanks. Formatting was done mostly by the RustRover IDE. Maybe I need to do a reformat at some point.