Bootstrap conditions for interaction-based multimodal learning in cognitive robotics: development of an emotional module for a cognitive architecture

• Grant number: 19/09675-7
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: June 01, 2019
• End date: March 31, 2020
• Field of knowledge: Engineering - Electrical Engineering
• Agreement: IBM Brasil
• Principal Investigator: Eric ROHMER
• Grantee: André Barros de Medeiros
• Host Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Company: Universidade Estadual de Campinas (UNICAMP). Faculdade de Engenharia Elétrica e de Computação (FEEC)
• Associated research grant: 16/18819-4 - Bootstrap conditions for interaction-based multimodal learning in cognitive robotics, AP.PITE

Abstract

With recent technological advances in computing and robotics, as well as new discoveries in the area of neuroscience, we are now more capable than ever before to attempt at simulating human life in a robotic environment. But it is very important to remember that the construction and design of a humanoid robot is not limited to the mechanical or to the sensors the robot possesses. One of the key pieces of this goal is the "brain" of the robot. How to program a robot so that it can process and emulate emotions, as well as learn from its surroundings is a very difficult task. In order to solve this problem, and bring us a bit closer to creating a "perfect humanoid", we will take affective neuroscience and recent developments in affective computing into strong consideration. We aim to design an emotional model based on inputs processed by an emotional module and expected behavior (output). On top of that, integrate the emotional module into the proposed cognitive architecture. In sum, the project's goal is to observe and quantify the influence of the expression of a robots motivational state, through emotions, when considering a robot's initial training (or learning) phase.