top of page

Robot Localization using the Adaptive Monte Carlo Localization (AMCL)

Github: 

Overview

This project utilizes the ROS AMCL package to accurately localize a mobile robot inside a map in the Gazebo simulation environment. The project aims to achieve the following:

​

  • Create a ROS package that launches a custom robot model in a custom Gazebo world.

  • Utilize the ROS AMCL package and the Tele-Operation/Navigation stack to localize the robot.

  • Explore, add and tune specific parameters corresponding to each package to achieve the best possible localization results.

​

​

The localization is tested using two methods: 

​

1. Sending a 2D Navigation Goal: The first option would be sending a 2D Navigation Goal from RViz. The move_base will try to navigate your robot based on the localization. Based on the new observation and the odometry, the robot further performs localization. 

​

2. Using the teleop Node: The teleop node can be used to control the robot and observe it localize itself in the environment. In order to use this the teleop package needs to be set up

 

 

All setup instructions as well as source codes can be found on my GitHub page  

 

 

​

bottom of page