Developmental model of sensorimotor map acquisition for a humanoid robot

Cognitive developmental robotics unites machine learning and neuroscience with the aim of creating robots which display the robustness and efficiency of human cognition. This document proposes a novel method for acquiring a visuomotor mapping for hand-eye coordination. This model is trained on the iCub humanoid robot and used for smooth control of reaching. Applications of this model to sensorimotor associative learning are examined. In addition, a derivation of the self-organizing map from neural dynamics is presented. This dissertation is part of an overarching goal of developing a platform-independent model of intelligent systems.

Name thesis:degree_name

Ph.D.

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2013

Author dc:creator

• Majure, Lydia

Contributors dc:contributor

• Levinson, Stephen E.
• Coleman, Todd P.
• Hasegawa-Johnson, Mark A.
• Huang, Thomas S.

• Cognitive Developmental Robotics
• Artificial Intelligence
• Humanoid Robotics
• Machine Learning
• Neural Dynamics

Statement dc:rights

• Copyright 2013 Lydia Majure

Language dc:language

en

Handle dc:identifier

http://hdl.handle.net/2142/45648

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/45648