# MichaelGrupp/evo

Python package for the evaluation of odometry and SLAM

Repository: https://github.com/MichaelGrupp/evo
Canonical: https://ross.abutalabs.com/products/evo
Homepage: https://michaelgrupp.github.io/evo/
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: slam, odometry, evaluation, metrics, robotics, trajectory, benchmark, ros, kitti, tum, mapping, euroc, ros2, trajectory-analysis, trajectory-evaluation
Last push: 2026-08-14T16:14:03+00:00

## Health v2 (maintenance only)
Score: 76/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 35, longevity 100
- inputs: {"age_days": 3276, "days_push": 19, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4309, forks 795 (observed 2026-08-28T04:08:41.747615+00:00)

## What it is
evo is a Python package with CLI executables and a small library for evaluating, comparing, and plotting trajectory output from odometry and SLAM algorithms. It supports TUM, KITTI, EuRoC, and ROS/ROS2 bagfile trajectory formats with alignment, scale adjustment, and metric computation.

## Use cases
- evaluate SLAM trajectory accuracy against ground truth
- compare odometry outputs from multiple algorithms
- compute APE and RPE metrics on TUM or KITTI trajectories
- plot and export trajectory error plots for papers
- align and scale monocular SLAM trajectories
- analyze trajectories from ROS or ROS2 bag files

## When to choose
- you need to benchmark or evaluate odometry/SLAM trajectories in standard formats
- you want a configurable CLI plus a Python library for custom trajectory analysis
- you work with ROS/ROS2, KITTI, TUM, or EuRoC data

## When to avoid
- you need a 1-to-1 reimplementation of a dataset-specific evaluation protocol
- you need real-time SLAM or odometry itself rather than offline evaluation
- you require a non-GPL license for redistribution

## Facets
- artifact type: library
- maturity: stable
- function: benchmarking, data-visualization, cli, math
- domain: robotics, simulation, developer-tools, data-visualization
- platform: windows, python, cli, cross-platform
- tags: slam, odometry, trajectory-evaluation, ros, ros2, kitti, tum, euroc, metrics, linux, macos

## Member repositories
- MichaelGrupp/evo (main) score 76

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:41.747615+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:21:47.895935+00:00, confidence not recorded.
  - readme: https://github.com/MichaelGrupp/evo (fetched 2026-08-28T04:08:41.747615+00:00, sha cc92e3fe9e6b)
  - homepage: https://michaelgrupp.github.io/evo/ (fetched 2026-08-29T09:10:56.012719+00:00, sha 9f5eea10546a)
  - registry_pypi: https://pypi.org/pypi/evo/json (fetched 2026-08-29T09:10:56.089995+00:00, sha 8c3a0b4fe66b)
- Data as of 2026-08-30T08:39:29.467469+00:00.