Full text
| |
| Author(s): |
Rodrigo Elias Bianchi
Total Authors: 1
|
| Document type: | Master's Dissertation |
| Press: | São Carlos. |
| Institution: | Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC/SB) |
| Defense date: | 2003-07-07 |
| Examining board members: |
Roseli Aparecida Francelin Romero;
Dante Augusto Couto Barone;
Orides Morandin Junior
|
| Advisor: | Roseli Aparecida Francelin Romero |
| Abstract | |
In this work, we investigate the use of probabilistic methods for autonomous mobile robots navigation. The main goal is to devolop a navigation software for a mobile robot, which must be able to transport documents autonomously between distant places. This must be dono without any modification on the robot environment. The environments that this robot can act on could be, for example, the laboratories building of the Instituto of Mathematics and Computer Sciences (ICMC) at the University of São Paulo (USP). In order to achieve this, the software must be able to: (l)estimate the robot, position without using artificial landmarks, (2)build and maintain environment maps, (3)avoid static and dynamical obstados, and (4)calculate the path between the places where the robot is expected to get and deliver documents. A navigation system that uses the probabilistic methods called Occupancy Grid Mapping and Monto Carlo Localization was implemented. In order to show the adequacy of such a system to the documents delivery task, several experiments have been performed. These methods have been tested in a real environment at ICMC-USP, by using the Pioneer 1 mobile robot. (AU) | |