Alberto-visualloc
- Project Name: Localization algorithm for the Pioneer robot based on a visual beacons 2D-map and camera images.
- Authors: Alberto López and Jose María Cañas Plaza (jmplaza [at] gsyc [dot] es)
- Academic Year: 2004-2005
- Degree: Undergrad
- Jde Version: jde-4.2.1
- SVN Repository: source code
- Tags: robot, visual-localization, cameras, map
- Technology: c, c++, jde suite, xforms
- State: Finished
- Source License: GPLv3
- Document License: Creative Commons Attribution-Share Alike 3.0 Unported License
- Documentation:
Master Thesis: PDF (latex code)
- Presentation:
This project tries to solve localization problem in mobile robots. To solve this problem in this project we use two diferents algorithms: probability grid and Monte Carlo's particles filter. Also we use a algorithm that compare the real image, gets from a camera, with a virtual image gets from map.
The picture below shows the GUI of the probability grid algorithm.
Here is a picture of a typical execution of the probability grid algorithm with his steps.
The next picture is the GUI to use the particles filter algorithm.
This picture shows a typical execution of the Monter Carlo's algorithm.
- Videos:
This video is an example of particle's filter algorithm running over the real robot, in the first video the robot is moving around the corridor and finds a trash, that allow it to estimate the position.
In the second video, the robot estimates his position with two extinguisher.
