methylDragon/ros-sensor-fusion-tutorial
methylDragon/ros-sensor-fusion-tutorial has 719 GitHub stars and 169 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-15 18:32 UTC. Last push 2019-03-15.
Measured star growth
- in 24h
- 0
- in 7 days
- Update delayed
- in 15 days
- Update delayed
- in 1 month
- Update delayed
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
About
An in-depth step-by-step tutorial for implementing sensor fusion with robot_localization! 🛰
LearningREADME.md
OriginalSensor Fusion in ROS
An in-depth step-by-step tutorial for implementing sensor fusion with extended Kalman filter nodes from robot_localization! Basic concepts like covariance and Kalman filters are explained here!
This tutorial is especially useful because there hasn't been a full end-to-end implementation tutorial for sensor fusion with the robot_localization package yet.
You can find the implementation in the Example Implementation folder!
Why fuse sensor data
A lot of times, the individual navigation stack components in a robot application can fail more often than not, but together, they form a more robust whole than not.
One way to do this is with the extended Kalman filter from the robot_localization package. The package features a relatively simple ROS interface to help you fuse and configure your sensors, so that's what we'll be using!
How to use this tutorial
- Make sure you're caught up on ROS
- It'll be good to read the Marvelmind Indoor 'GPS' beacon tutorial alongside this if you want to understand the example implementation
- Likewise for the Linorobot stack
- And AMCL
- Then go ahead and follow the tutorial in order!
.png)