Discovery of other individuals by projecting a self-model through imitation

Ryunosuke Yokoya, Tetsuya Ogata, Jun Tani, Kazunori Komatani, Hiroshi G. Okuno

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

This paper proposes a novel model which enables a humanoid robot infant to discover other individual (e.g. human parent). In this work, the authors define "other individual" as an actor which can be predicted by a self-model. For modeling the developmental process of discovering ability, the following three approaches are employed. (i) Projection of a self-model for predicting other individual's actions. (ii) Mediation by a physical object between self and other individual. (iii) Introduction of infant imitation by parent. For creating the self-model of a robot, we apply Recurrent Neural Network with Parametric Bias (RNNPB) model which can learn the robot's body dynamics. For the other-model of a human, conventional hierarchical neural networks are attached to the RNNPB model as "conversion modules". Our target task is a moving an object. For evaluation of our model, human discovery experiments by the robot projecting its self-model were conducted. The results demonstrated that our method enabled the robot to predict the human's motions, and to estimate the human's position fairly accurately, which proved its adequacy.

Original languageEnglish
Title of host publicationIEEE International Conference on Intelligent Robots and Systems
Pages1009-1014
Number of pages6
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007 - San Diego, CA
Duration: 2007 Oct 292007 Nov 2

Other

Other2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007
CitySan Diego, CA
Period07/10/2907/11/2

Fingerprint

Robots
Recurrent neural networks
Neural networks
Experiments

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Yokoya, R., Ogata, T., Tani, J., Komatani, K., & Okuno, H. G. (2007). Discovery of other individuals by projecting a self-model through imitation. In IEEE International Conference on Intelligent Robots and Systems (pp. 1009-1014). [4399153] https://doi.org/10.1109/IROS.2007.4399153

Discovery of other individuals by projecting a self-model through imitation. / Yokoya, Ryunosuke; Ogata, Tetsuya; Tani, Jun; Komatani, Kazunori; Okuno, Hiroshi G.

IEEE International Conference on Intelligent Robots and Systems. 2007. p. 1009-1014 4399153.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yokoya, R, Ogata, T, Tani, J, Komatani, K & Okuno, HG 2007, Discovery of other individuals by projecting a self-model through imitation. in IEEE International Conference on Intelligent Robots and Systems., 4399153, pp. 1009-1014, 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2007, San Diego, CA, 07/10/29. https://doi.org/10.1109/IROS.2007.4399153
Yokoya R, Ogata T, Tani J, Komatani K, Okuno HG. Discovery of other individuals by projecting a self-model through imitation. In IEEE International Conference on Intelligent Robots and Systems. 2007. p. 1009-1014. 4399153 https://doi.org/10.1109/IROS.2007.4399153
Yokoya, Ryunosuke ; Ogata, Tetsuya ; Tani, Jun ; Komatani, Kazunori ; Okuno, Hiroshi G. / Discovery of other individuals by projecting a self-model through imitation. IEEE International Conference on Intelligent Robots and Systems. 2007. pp. 1009-1014
@inproceedings{6502918b1e8549708f56525055feab31,
title = "Discovery of other individuals by projecting a self-model through imitation",
abstract = "This paper proposes a novel model which enables a humanoid robot infant to discover other individual (e.g. human parent). In this work, the authors define {"}other individual{"} as an actor which can be predicted by a self-model. For modeling the developmental process of discovering ability, the following three approaches are employed. (i) Projection of a self-model for predicting other individual's actions. (ii) Mediation by a physical object between self and other individual. (iii) Introduction of infant imitation by parent. For creating the self-model of a robot, we apply Recurrent Neural Network with Parametric Bias (RNNPB) model which can learn the robot's body dynamics. For the other-model of a human, conventional hierarchical neural networks are attached to the RNNPB model as {"}conversion modules{"}. Our target task is a moving an object. For evaluation of our model, human discovery experiments by the robot projecting its self-model were conducted. The results demonstrated that our method enabled the robot to predict the human's motions, and to estimate the human's position fairly accurately, which proved its adequacy.",
author = "Ryunosuke Yokoya and Tetsuya Ogata and Jun Tani and Kazunori Komatani and Okuno, {Hiroshi G.}",
year = "2007",
doi = "10.1109/IROS.2007.4399153",
language = "English",
isbn = "1424409128",
pages = "1009--1014",
booktitle = "IEEE International Conference on Intelligent Robots and Systems",

}

TY - GEN

T1 - Discovery of other individuals by projecting a self-model through imitation

AU - Yokoya, Ryunosuke

AU - Ogata, Tetsuya

AU - Tani, Jun

AU - Komatani, Kazunori

AU - Okuno, Hiroshi G.

PY - 2007

Y1 - 2007

N2 - This paper proposes a novel model which enables a humanoid robot infant to discover other individual (e.g. human parent). In this work, the authors define "other individual" as an actor which can be predicted by a self-model. For modeling the developmental process of discovering ability, the following three approaches are employed. (i) Projection of a self-model for predicting other individual's actions. (ii) Mediation by a physical object between self and other individual. (iii) Introduction of infant imitation by parent. For creating the self-model of a robot, we apply Recurrent Neural Network with Parametric Bias (RNNPB) model which can learn the robot's body dynamics. For the other-model of a human, conventional hierarchical neural networks are attached to the RNNPB model as "conversion modules". Our target task is a moving an object. For evaluation of our model, human discovery experiments by the robot projecting its self-model were conducted. The results demonstrated that our method enabled the robot to predict the human's motions, and to estimate the human's position fairly accurately, which proved its adequacy.

AB - This paper proposes a novel model which enables a humanoid robot infant to discover other individual (e.g. human parent). In this work, the authors define "other individual" as an actor which can be predicted by a self-model. For modeling the developmental process of discovering ability, the following three approaches are employed. (i) Projection of a self-model for predicting other individual's actions. (ii) Mediation by a physical object between self and other individual. (iii) Introduction of infant imitation by parent. For creating the self-model of a robot, we apply Recurrent Neural Network with Parametric Bias (RNNPB) model which can learn the robot's body dynamics. For the other-model of a human, conventional hierarchical neural networks are attached to the RNNPB model as "conversion modules". Our target task is a moving an object. For evaluation of our model, human discovery experiments by the robot projecting its self-model were conducted. The results demonstrated that our method enabled the robot to predict the human's motions, and to estimate the human's position fairly accurately, which proved its adequacy.

UR - http://www.scopus.com/inward/record.url?scp=51349116581&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51349116581&partnerID=8YFLogxK

U2 - 10.1109/IROS.2007.4399153

DO - 10.1109/IROS.2007.4399153

M3 - Conference contribution

AN - SCOPUS:51349116581

SN - 1424409128

SN - 9781424409129

SP - 1009

EP - 1014

BT - IEEE International Conference on Intelligent Robots and Systems

ER -