Robotic Architecture for Control of Socially Intelligent Robots

• Grant number: 08/10554-5
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: December 01, 2009
• End date: June 30, 2010
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Roseli Aparecida Francelin Romero
• Grantee: Giampaolo Luiz Libralon
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

Sociable robots should be able to interact, to communicate, to understand and to relate with human beings in a natural way. Although many sociable robots have been developed with success, several limitations still need to be surpassed. It is demanded important advances in development of mechanisms to allow more realistic interactions and able to regulate the relationship among robots and human beings. The majority of existent sociable robots has limited perception, cognition and behavior abilities wether compared with humans. Many researchers argue that there is a set of basic emotions which was preserved during the evolutive process because these emotions allow the adaption of organisms behavior for distinct daily situations. Among these, it can be cited rage, aversion, fear, happiness, sadness and surprise. These emotions serve to specific purposes and emerge in certain environment contexts to prepare the organism to respond appropriately. In this sense, this project proposes the improvement of an existent robotic architecture, which learns from social interactions, with the addition of the ability for expressing a set of basic emotions, as well as the improvement of existent learning and computational vision system, in order to allow more realistic and long lasting interactions with humans beings.

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

LIBRALON, Giampaolo Luiz. Computational modeling for emotion recognition based on facial analysis. 2014. Doctoral Thesis - Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC/SB) São Carlos.