Advanced search
Start date
Betweenand

Construction of a simulation environment for the Marta Humanoid robot

Grant number: 18/09439-9
Support type:Scholarships in Brazil - Scientific Initiation
Effective date (Start): June 01, 2018
Effective date (End): May 31, 2019
Field of knowledge:Physical Sciences and Mathematics - Computer Science
Cooperation agreement: IBM Brasil
Principal Investigator:Eric Rohmer
Grantee:Samuel Felipe Chenatti
Home 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

The objective of this scientific initiation is the development of an experimental simulation platform that will support the project "Bootstrap Conditions for Interaction-Based Multimodal Learning in Cognitive Robots". In this project, the humanoid robot Marta will be observing and interacting with objects of the world around her, and will feel, learn and grow just like a baby does until the age of about 6 months, with the support of a cognitive architecture. The research aims at defining what the minimal bootstrap conditions are, for a cognitive robot system, to be able to learn about the world it actuates in. To do so, a real robot Marta is planned to be build with a set of sensors and objects that define its world. However, in order to define the necessary sensory hardware as well as to run a plethora of experiments, having a simulated version of the robot and its environment is of a great help. At first the simulation allow the testing of different kind of sensors to specify the final hardware, then the simulation can serve as an automated experimentation platform for repeated learning protocols. This last feature of the simulation environment will greatly catalyze the process of teaching and self learning of the cognitive system, as the experiments will be able to be scripted and run in parallel. (AU)