Self-organization of dynamic object features based on bidirectional training

Shun Nishide, Tetsuya Ogata, Jun Tani, Kazunori Komatani, Hiroshi G. Okuno

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

This paper presents a method to self-organize object features that describe object dynamics using bidirectional training. The model is composed of a dynamics learning module and a feature extraction module. Recurrent Neural Network with Parametric Bias (RNNPB) is utilized for the dynamics learning module, learning and self-organizing the sequences of robot and object motions. A hierarchical neural network is linked to the input of RNNPB as the feature extraction module for self-organizing object features that describe the object motions. The two modules are simultaneously trained through bidirectional training using image and motion sequences acquired from the robot's active sensing with objects. Experiments are performed with the robot's pushing motion with a variety of objects to generate sliding, falling over, bouncing and rolling motions. The results have shown that the model is capable of self-organizing object dynamics based on the self-organized features.

Original languageEnglish
Pages (from-to)2035-2057
Number of pages23
JournalAdvanced Robotics
Volume23
Issue number15
DOIs
Publication statusPublished - 2009 Oct 1
Externally publishedYes

Fingerprint

Recurrent neural networks
Robots
Feature extraction
Neural networks
Experiments

Keywords

  • Active sensing
  • Affordance
  • Bidirectional training
  • Humanoid robots
  • Neural networks

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Human-Computer Interaction
  • Computer Science Applications
  • Hardware and Architecture
  • Software

Cite this

Self-organization of dynamic object features based on bidirectional training. / Nishide, Shun; Ogata, Tetsuya; Tani, Jun; Komatani, Kazunori; Okuno, Hiroshi G.

In: Advanced Robotics, Vol. 23, No. 15, 01.10.2009, p. 2035-2057.

Research output: Contribution to journalArticle

Nishide, Shun ; Ogata, Tetsuya ; Tani, Jun ; Komatani, Kazunori ; Okuno, Hiroshi G. / Self-organization of dynamic object features based on bidirectional training. In: Advanced Robotics. 2009 ; Vol. 23, No. 15. pp. 2035-2057.
@article{f3362021487f4c8798a54e2b48691d41,
title = "Self-organization of dynamic object features based on bidirectional training",
abstract = "This paper presents a method to self-organize object features that describe object dynamics using bidirectional training. The model is composed of a dynamics learning module and a feature extraction module. Recurrent Neural Network with Parametric Bias (RNNPB) is utilized for the dynamics learning module, learning and self-organizing the sequences of robot and object motions. A hierarchical neural network is linked to the input of RNNPB as the feature extraction module for self-organizing object features that describe the object motions. The two modules are simultaneously trained through bidirectional training using image and motion sequences acquired from the robot's active sensing with objects. Experiments are performed with the robot's pushing motion with a variety of objects to generate sliding, falling over, bouncing and rolling motions. The results have shown that the model is capable of self-organizing object dynamics based on the self-organized features.",
keywords = "Active sensing, Affordance, Bidirectional training, Humanoid robots, Neural networks",
author = "Shun Nishide and Tetsuya Ogata and Jun Tani and Kazunori Komatani and Okuno, {Hiroshi G.}",
year = "2009",
month = "10",
day = "1",
doi = "10.1163/016918609X12529289797027",
language = "English",
volume = "23",
pages = "2035--2057",
journal = "Advanced Robotics",
issn = "0169-1864",
publisher = "Taylor and Francis Ltd.",
number = "15",

}

TY - JOUR

T1 - Self-organization of dynamic object features based on bidirectional training

AU - Nishide, Shun

AU - Ogata, Tetsuya

AU - Tani, Jun

AU - Komatani, Kazunori

AU - Okuno, Hiroshi G.

PY - 2009/10/1

Y1 - 2009/10/1

N2 - This paper presents a method to self-organize object features that describe object dynamics using bidirectional training. The model is composed of a dynamics learning module and a feature extraction module. Recurrent Neural Network with Parametric Bias (RNNPB) is utilized for the dynamics learning module, learning and self-organizing the sequences of robot and object motions. A hierarchical neural network is linked to the input of RNNPB as the feature extraction module for self-organizing object features that describe the object motions. The two modules are simultaneously trained through bidirectional training using image and motion sequences acquired from the robot's active sensing with objects. Experiments are performed with the robot's pushing motion with a variety of objects to generate sliding, falling over, bouncing and rolling motions. The results have shown that the model is capable of self-organizing object dynamics based on the self-organized features.

AB - This paper presents a method to self-organize object features that describe object dynamics using bidirectional training. The model is composed of a dynamics learning module and a feature extraction module. Recurrent Neural Network with Parametric Bias (RNNPB) is utilized for the dynamics learning module, learning and self-organizing the sequences of robot and object motions. A hierarchical neural network is linked to the input of RNNPB as the feature extraction module for self-organizing object features that describe the object motions. The two modules are simultaneously trained through bidirectional training using image and motion sequences acquired from the robot's active sensing with objects. Experiments are performed with the robot's pushing motion with a variety of objects to generate sliding, falling over, bouncing and rolling motions. The results have shown that the model is capable of self-organizing object dynamics based on the self-organized features.

KW - Active sensing

KW - Affordance

KW - Bidirectional training

KW - Humanoid robots

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=70449589606&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449589606&partnerID=8YFLogxK

U2 - 10.1163/016918609X12529289797027

DO - 10.1163/016918609X12529289797027

M3 - Article

VL - 23

SP - 2035

EP - 2057

JO - Advanced Robotics

JF - Advanced Robotics

SN - 0169-1864

IS - 15

ER -