usdot-fhwa-stol / carma-analytics-fotda

CARMA Analytics is a secure, scalable and cloud agnostic data architecture to enable research analysis on big data sets by defining repeatable and scalable processes for ingesting data, creation of a data repository to fuse, process and perform quality assurance.
Apache License 2.0
3 stars 3 forks source link

Added plots that visualize localization performance #72

Closed john-chrosniak closed 4 months ago

john-chrosniak commented 5 months ago

PR Details

Description

This PR adds plots to visualize the standard deviation of our localization estimates, the standard deviation of the particles in our localization particle filters, and velcocity as a function of downtrack distance. The average and maximum standard deviations are also logged to the terminal.

Related Jira Key

CF-854

Motivation and Context

When testing in the PVL and in other environments, establishing benchmarks for localization performance is important to track improvements and define the limitations of the system.

How Has This Been Tested?

Plots were generated using bags from a run in the main Saxton lab and the PVL.

Types of changes

Checklist:

john-chrosniak commented 5 months ago

localization_std_dev

john-chrosniak commented 5 months ago

localization_deviation

john-chrosniak commented 5 months ago

localization_std_dev pf_std_dev

Most recent plots of testing in the PVL lab

john-chrosniak commented 5 months ago

pvl_route_driven speed_vs_downtrack

john-chrosniak commented 4 months ago

speed_vs_downtrack Updated speed vs. downtrack using the commanded velocity

john-chrosniak commented 4 months ago

05_ms_route

Updated route driven plot that includes std deviation