Analysis of learning and performance of classifying systems models applied to autonomous robot navigation

• Grant number: 05/03519-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: January 01, 2006
• End date: December 31, 2006
• Field of knowledge: Engineering - Electrical Engineering
• Principal Investigator: Fernando José von Zuben
• Grantee: Renan Cipriano Moioli
• Host Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

This project purposes a comparative study of three learning classifiers systems models applied to the robot autonomous navigation problem. Specific extensions to each autonomous control proposal are also foreseen. With the objective of analysing the learning process and the performance of the tools, computational simulations in a virtual environment are going to be performed, and also real experiments with the Khepera II robot. The student already works for one year together with the research group, allowing him to aquire a good level of experience in handling with autonomous robots and virtual environments for computational simulations, so that the efforts can be focused on sintesis, implementation and performance analysis of the controllers based on learning classifier systems models.