Modeling tool-body assimilation using second-order recurrent neural network

Shun Nishide, Tatsuhiro Nakagawa, Tetsuya Ogata, Jun Tani, Toru Takahashi, Hiroshi G. Okuno

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

10 Citations (Scopus)

Abstract

Tool-body assimilation is one of the intelligent human abilities. Through trial and experience, humans are capable of using tools as if they are part of their own bodies. This paper presents a method to apply a robot's active sensing experience for creating the tool-body assimilation model. The model is composed of a feature extraction module, dynamics learning module, and a tool recognition module. Self-Organizing Map (SOM) is used for the feature extraction module to extract object features from raw images. Multiple Time-scales Recurrent Neural Network (MTRNN) is used as the dynamics learning module. Parametric Bias (PB) nodes are attached to the weights of MTRNN as second-order network to modulate the behavior of MTRNN based on the tool. The generalization capability of neural networks provide the model the ability to deal with unknown tools. Experiments are performed with HRP-2 using no tool, I-shaped, T-shaped, and L-shaped tools. The distribution of PB values have shown that the model has learned that the robot's dynamic properties change when holding a tool. The results of the experiment show that the tool-body assimilation model is capable of applying to unknown objects to generate goal-oriented motions.

Original languageEnglish
Title of host publication2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009
Pages5376-5381
Number of pages6
DOIs
Publication statusPublished - 2009 Dec 11
Externally publishedYes
Event2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009 - St. Louis, MO
Duration: 2009 Oct 112009 Oct 15

Other

Other2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009
CitySt. Louis, MO
Period09/10/1109/10/15

Fingerprint

Recurrent neural networks
Feature extraction
Robots
Self organizing maps
Experiments
Neural networks

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Control and Systems Engineering

Cite this

Nishide, S., Nakagawa, T., Ogata, T., Tani, J., Takahashi, T., & Okuno, H. G. (2009). Modeling tool-body assimilation using second-order recurrent neural network. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009 (pp. 5376-5381). [5354655] https://doi.org/10.1109/IROS.2009.5354655

Modeling tool-body assimilation using second-order recurrent neural network. / Nishide, Shun; Nakagawa, Tatsuhiro; Ogata, Tetsuya; Tani, Jun; Takahashi, Toru; Okuno, Hiroshi G.

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009. 2009. p. 5376-5381 5354655.

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

Nishide, S, Nakagawa, T, Ogata, T, Tani, J, Takahashi, T & Okuno, HG 2009, Modeling tool-body assimilation using second-order recurrent neural network. in 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009., 5354655, pp. 5376-5381, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009, St. Louis, MO, 09/10/11. https://doi.org/10.1109/IROS.2009.5354655
Nishide S, Nakagawa T, Ogata T, Tani J, Takahashi T, Okuno HG. Modeling tool-body assimilation using second-order recurrent neural network. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009. 2009. p. 5376-5381. 5354655 https://doi.org/10.1109/IROS.2009.5354655
Nishide, Shun ; Nakagawa, Tatsuhiro ; Ogata, Tetsuya ; Tani, Jun ; Takahashi, Toru ; Okuno, Hiroshi G. / Modeling tool-body assimilation using second-order recurrent neural network. 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009. 2009. pp. 5376-5381
@inproceedings{a3cf9afaba70465b8a34c6c6da26d464,
title = "Modeling tool-body assimilation using second-order recurrent neural network",
abstract = "Tool-body assimilation is one of the intelligent human abilities. Through trial and experience, humans are capable of using tools as if they are part of their own bodies. This paper presents a method to apply a robot's active sensing experience for creating the tool-body assimilation model. The model is composed of a feature extraction module, dynamics learning module, and a tool recognition module. Self-Organizing Map (SOM) is used for the feature extraction module to extract object features from raw images. Multiple Time-scales Recurrent Neural Network (MTRNN) is used as the dynamics learning module. Parametric Bias (PB) nodes are attached to the weights of MTRNN as second-order network to modulate the behavior of MTRNN based on the tool. The generalization capability of neural networks provide the model the ability to deal with unknown tools. Experiments are performed with HRP-2 using no tool, I-shaped, T-shaped, and L-shaped tools. The distribution of PB values have shown that the model has learned that the robot's dynamic properties change when holding a tool. The results of the experiment show that the tool-body assimilation model is capable of applying to unknown objects to generate goal-oriented motions.",
author = "Shun Nishide and Tatsuhiro Nakagawa and Tetsuya Ogata and Jun Tani and Toru Takahashi and Okuno, {Hiroshi G.}",
year = "2009",
month = "12",
day = "11",
doi = "10.1109/IROS.2009.5354655",
language = "English",
isbn = "9781424438044",
pages = "5376--5381",
booktitle = "2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009",

}

TY - GEN

T1 - Modeling tool-body assimilation using second-order recurrent neural network

AU - Nishide, Shun

AU - Nakagawa, Tatsuhiro

AU - Ogata, Tetsuya

AU - Tani, Jun

AU - Takahashi, Toru

AU - Okuno, Hiroshi G.

PY - 2009/12/11

Y1 - 2009/12/11

N2 - Tool-body assimilation is one of the intelligent human abilities. Through trial and experience, humans are capable of using tools as if they are part of their own bodies. This paper presents a method to apply a robot's active sensing experience for creating the tool-body assimilation model. The model is composed of a feature extraction module, dynamics learning module, and a tool recognition module. Self-Organizing Map (SOM) is used for the feature extraction module to extract object features from raw images. Multiple Time-scales Recurrent Neural Network (MTRNN) is used as the dynamics learning module. Parametric Bias (PB) nodes are attached to the weights of MTRNN as second-order network to modulate the behavior of MTRNN based on the tool. The generalization capability of neural networks provide the model the ability to deal with unknown tools. Experiments are performed with HRP-2 using no tool, I-shaped, T-shaped, and L-shaped tools. The distribution of PB values have shown that the model has learned that the robot's dynamic properties change when holding a tool. The results of the experiment show that the tool-body assimilation model is capable of applying to unknown objects to generate goal-oriented motions.

AB - Tool-body assimilation is one of the intelligent human abilities. Through trial and experience, humans are capable of using tools as if they are part of their own bodies. This paper presents a method to apply a robot's active sensing experience for creating the tool-body assimilation model. The model is composed of a feature extraction module, dynamics learning module, and a tool recognition module. Self-Organizing Map (SOM) is used for the feature extraction module to extract object features from raw images. Multiple Time-scales Recurrent Neural Network (MTRNN) is used as the dynamics learning module. Parametric Bias (PB) nodes are attached to the weights of MTRNN as second-order network to modulate the behavior of MTRNN based on the tool. The generalization capability of neural networks provide the model the ability to deal with unknown tools. Experiments are performed with HRP-2 using no tool, I-shaped, T-shaped, and L-shaped tools. The distribution of PB values have shown that the model has learned that the robot's dynamic properties change when holding a tool. The results of the experiment show that the tool-body assimilation model is capable of applying to unknown objects to generate goal-oriented motions.

UR - http://www.scopus.com/inward/record.url?scp=76249109830&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=76249109830&partnerID=8YFLogxK

U2 - 10.1109/IROS.2009.5354655

DO - 10.1109/IROS.2009.5354655

M3 - Conference contribution

SN - 9781424438044

SP - 5376

EP - 5381

BT - 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009

ER -