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

Standard

A biologically constrained architecture for developmental learning of eye–head gaze control on a humanoid robot. / Law, James Alexander; Shaw, Patricia Hazel; Lee, Mark Howard.

In: Autonomous Robots, Vol. 35, No. 1, 01.07.2013, p. 77-92.

Research output: Contribution to journalArticlepeer-review

Bibtex - Download

@article{807d37c60ad348ba8d4ffa1d66157790,
title = "A biologically constrained architecture for developmental learning of eye–head gaze control on a humanoid robot",
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.",
keywords = "Developmental robotics, Gaze control, Sensorimotor learning, Eye-head coordination, Humanoid robotics",
author = "Law, {James Alexander} and Shaw, {Patricia Hazel} and Lee, {Mark Howard}",
note = "Law, J. A., Shaw, P. H., Lee, M. H. (2013). A biologically constrained architecture for developmental learning of eye–head gaze control on a humanoid robot. Autonomous Robots, 35 (1), 77-92.",
year = "2013",
month = jul,
day = "1",
doi = "10.1007/s10514-013-9335-2",
language = "English",
volume = "35",
pages = "77--92",
journal = "Autonomous Robots",
issn = "0929-5593",
publisher = "Springer Nature",
number = "1",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - A biologically constrained architecture for developmental learning of eye–head gaze control on a humanoid robot

AU - Law, James Alexander

AU - Shaw, Patricia Hazel

AU - Lee, Mark Howard

N1 - Law, J. A., Shaw, P. H., Lee, M. H. (2013). A biologically constrained architecture for developmental learning of eye–head gaze control on a humanoid robot. Autonomous Robots, 35 (1), 77-92.

PY - 2013/7/1

Y1 - 2013/7/1

N2 - 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.

AB - 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.

KW - Developmental robotics

KW - Gaze control

KW - Sensorimotor learning

KW - Eye-head coordination

KW - Humanoid robotics

UR - http://hdl.handle.net/2160/9280

U2 - 10.1007/s10514-013-9335-2

DO - 10.1007/s10514-013-9335-2

M3 - Article

VL - 35

SP - 77

EP - 92

JO - Autonomous Robots

JF - Autonomous Robots

SN - 0929-5593

IS - 1

ER -

View graph of relations
Citation formats