Full text
| |
| Author(s): |
Antonio Henrique Pinto Selvatici
Total Authors: 1
|
| Document type: | Master's Dissertation |
| Press: | São Paulo. , gráficos, ilustrações, tabelas. |
| Institution: | Universidade de São Paulo (USP). Escola Politécnica (EP/BC) |
| Defense date: | 2005-02-04 |
| Examining board members: |
Anna Helena Reali Costa;
Jun Okamoto Junior;
Mário Sarcinelli Filho
|
| Advisor: | Anna Helena Reali Costa |
| Field of knowledge: | Physical Sciences and Mathematics - Computer Science |
| Indexed in: | Banco de Dados Bibliográficos da USP-DEDALUS; Biblioteca Digital de Teses e Dissertações - USP |
| Location: | Universidade de São Paulo. Biblioteca Central da Escola Politécnica; EPBC/FD-3900; Universidade de São Paulo. Escola Politécnica. Biblioteca de Engenharia Elétrica; EPEL/FD-3900 |
| Abstract | |
It is desirable that mobile robots applied to real world applications perform their operations in previously unknown environments. Thus, a mobile robot architecture capable of adaptation is very suitable. This work presents an adaptive architecture for mobile robots called AAREACT, that has the ability of learning how to coordinate primitive behaviors codified by the Potential Fields method through reinforcement learning. Each behavior uses the information of a single sensor (vision, sonar or odometer). This work also brings details about the vision sensor\'s development, which uses time-to-crash information in order to detect distances to frontal obstacles. The proposed architecture\'s actuation is compared to that showed by an architecture that performs a fixed coordination of its behaviors, and shows a better performance. The obtained results also suggest that AAREACT has good adaptation skills. (AU) | |