A biologically constrained architecture for developmental learning of eye–head gaze control on a humanoid robot

James Alexander Law, Patricia Hazel Shaw, Mark Howard Lee

Research output: Contribution to journalArticlepeer-review

33 Citations (SciVal)

Abstract

In this paper we describe a biologically constrained architecture for developmental learning of eye–head gaze control on an iCub robot. In contrast to other computational implementations, the developmental approach aims to
acquire sensorimotor competence through growth processes modelled on data and theory from infant psychology. Constraints help shape learning in infancy by limiting the complexity of interactions between the body and environment,
and we use this idea to produce efficient, effective learning in autonomous robots. Our architecture is based on current thinking surrounding the gaze mechanism, and experimentally derived models of stereotypical eye–head gaze contributions. It is built using our proven constraint-based fieldmapping
approach. We identify stages in the development of infant gaze control, and propose a framework of artificial constraints to shape learning on the robot in a similar manner. We demonstrate the impact these constraints have on learning,
and the resulting ability of the robot to make controlled gaze shifts.
Original languageEnglish
Pages (from-to)77-92
Number of pages16
JournalAutonomous Robots
Volume35
Issue number1
Early online date19 Apr 2013
DOIs
Publication statusPublished - 01 Jul 2013

Keywords

  • Developmental robotics
  • Gaze control
  • Sensorimotor learning
  • Eye-head coordination
  • Humanoid robotics

Fingerprint

Dive into the research topics of 'A biologically constrained architecture for developmental learning of eye–head gaze control on a humanoid robot'. Together they form a unique fingerprint.

Cite this