# cra-ros-pkg/robot_localization

robot_localization is a package of nonlinear state estimation nodes. The package was developed by Charles River Analytics, Inc. Please ask questions on answers.ros.org.

Repository: https://github.com/cra-ros-pkg/robot_localization
Canonical: https://ross.abutalabs.com/products/robot_localization
Homepage: http://www.cra.com
Language: C++
License: NOASSERTION
License Family: other
Last push: 2026-07-16T11:41:06+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 8, longevity 100
- inputs: {"age_days": 4538, "days_push": 48, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1947, forks 1033 (observed 2026-08-28T04:05:57.927553+00:00)

## What it is
robot_localization is a ROS package of nonlinear state estimation nodes (EKF, UKF, and navsat_transform) for fusing IMU, odometry, and other sensor data into a robot's pose estimate. It was developed by Charles River Analytics and is widely used in ROS/ROS 2 navigation stacks.

## Use cases
- fuse imu and wheel odometry into a robot pose estimate
- estimate robot localization with an extended kalman filter
- transform gps data into the robot's odometry frame
- get a smooth tf transform for ros navigation
- dead reckoning for a mobile robot
- sensor fusion for autonomous robot navigation

## When to choose
- you are building a ROS or ROS 2 mobile robot and need robust state estimation from multiple sensors
- you need to fuse IMU, odometry, and GPS data into a continuous pose estimate
- you want a battle-tested, community-standard localization package for the ROS navigation stack

## When to avoid
- you are not using ROS or ROS 2
- you need SLAM or map-based localization rather than odometry-based state estimation
- you need a standalone estimator outside the ROS ecosystem

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, simulation
- domain: robotics, autonomous-vehicles
- platform: cpp
- tags: ros, state-estimation, sensor-fusion, kalman-filter, ekf, ukf, nav2, odometry, linux

## Member repositories
- cra-ros-pkg/robot_localization (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:57.927553+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 2026-08-30T03:07:06.284018+00:00, confidence not recorded.
  - readme: https://github.com/cra-ros-pkg/robot_localization (fetched 2026-08-28T04:05:57.927553+00:00, sha 9f01c81bc435)
  - homepage: http://www.cra.com (fetched 2026-08-29T10:46:51.989989+00:00, sha 067497b19378)
- Data as of 2026-08-30T08:39:29.467469+00:00.