Emergence of evolutionary interaction with voice and motion between two robots using RNN

Wataru Hinoshita, Tetsuya Ogata, Hideki Kozima, Hisashi Kanda, Toru Takahashi, Hiroshi G. Okuno

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

3 Citations (Scopus)

Abstract

We propose a model of evolutionary interaction between two robots where signs used for communication emerge through mutual adaptation. Signs used in human interaction, e.g., language, gestures and eye contact change and evolve in form and meaning through repeated use. To create flexible human-like interaction systems, it is necessary to deal with signs as a dynamic property and to construct a framework in which signs emerge from mutual adaptation by agents. Our target is multi-modal interaction using voice and motion between two robots where a voice/motion pattern is used as a sign referring to a motion/voice pattern. To enable evolutionary signs (voice and motion patterns) to be recognized and generated, we utilized a dynamics model: Multiple Timescale Recurrent Neural Network (MTRNN). To enable the robots to interpret signs, we utilized hierarchical neural networks, which transform dynamics model parameters of voice/motion into those of motion/voice. In our experiment, two robots modified their own interpretation of signs constantly through mutual adaptation in interaction where they responded to the other's voice with motion one after the other. As a result of the experiment, we found that the interaction kept evolving through the robots' repeated and alternate miscommunications and readaptations, and this induced the emergence of diverse new signs that depended on the robots' body dynamics through the generalization capability of MTRNN.

Original languageEnglish
Title of host publication2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009
Pages4186-4192
Number of pages7
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

Robots
Recurrent neural networks
Dynamic models
Experiments
Neural networks
Communication

ASJC Scopus subject areas

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

Cite this

Hinoshita, W., Ogata, T., Kozima, H., Kanda, H., Takahashi, T., & Okuno, H. G. (2009). Emergence of evolutionary interaction with voice and motion between two robots using RNN. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009 (pp. 4186-4192). [5353887] https://doi.org/10.1109/IROS.2009.5353887

Emergence of evolutionary interaction with voice and motion between two robots using RNN. / Hinoshita, Wataru; Ogata, Tetsuya; Kozima, Hideki; Kanda, Hisashi; Takahashi, Toru; Okuno, Hiroshi G.

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009. 2009. p. 4186-4192 5353887.

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

Hinoshita, W, Ogata, T, Kozima, H, Kanda, H, Takahashi, T & Okuno, HG 2009, Emergence of evolutionary interaction with voice and motion between two robots using RNN. in 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009., 5353887, pp. 4186-4192, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009, St. Louis, MO, 09/10/11. https://doi.org/10.1109/IROS.2009.5353887
Hinoshita W, Ogata T, Kozima H, Kanda H, Takahashi T, Okuno HG. Emergence of evolutionary interaction with voice and motion between two robots using RNN. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009. 2009. p. 4186-4192. 5353887 https://doi.org/10.1109/IROS.2009.5353887
Hinoshita, Wataru ; Ogata, Tetsuya ; Kozima, Hideki ; Kanda, Hisashi ; Takahashi, Toru ; Okuno, Hiroshi G. / Emergence of evolutionary interaction with voice and motion between two robots using RNN. 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009. 2009. pp. 4186-4192
@inproceedings{a3a3e5dae5e0413b85ba1300db55cbf5,
title = "Emergence of evolutionary interaction with voice and motion between two robots using RNN",
abstract = "We propose a model of evolutionary interaction between two robots where signs used for communication emerge through mutual adaptation. Signs used in human interaction, e.g., language, gestures and eye contact change and evolve in form and meaning through repeated use. To create flexible human-like interaction systems, it is necessary to deal with signs as a dynamic property and to construct a framework in which signs emerge from mutual adaptation by agents. Our target is multi-modal interaction using voice and motion between two robots where a voice/motion pattern is used as a sign referring to a motion/voice pattern. To enable evolutionary signs (voice and motion patterns) to be recognized and generated, we utilized a dynamics model: Multiple Timescale Recurrent Neural Network (MTRNN). To enable the robots to interpret signs, we utilized hierarchical neural networks, which transform dynamics model parameters of voice/motion into those of motion/voice. In our experiment, two robots modified their own interpretation of signs constantly through mutual adaptation in interaction where they responded to the other's voice with motion one after the other. As a result of the experiment, we found that the interaction kept evolving through the robots' repeated and alternate miscommunications and readaptations, and this induced the emergence of diverse new signs that depended on the robots' body dynamics through the generalization capability of MTRNN.",
author = "Wataru Hinoshita and Tetsuya Ogata and Hideki Kozima and Hisashi Kanda and Toru Takahashi and Okuno, {Hiroshi G.}",
year = "2009",
month = "12",
day = "11",
doi = "10.1109/IROS.2009.5353887",
language = "English",
isbn = "9781424438044",
pages = "4186--4192",
booktitle = "2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009",

}

TY - GEN

T1 - Emergence of evolutionary interaction with voice and motion between two robots using RNN

AU - Hinoshita, Wataru

AU - Ogata, Tetsuya

AU - Kozima, Hideki

AU - Kanda, Hisashi

AU - Takahashi, Toru

AU - Okuno, Hiroshi G.

PY - 2009/12/11

Y1 - 2009/12/11

N2 - We propose a model of evolutionary interaction between two robots where signs used for communication emerge through mutual adaptation. Signs used in human interaction, e.g., language, gestures and eye contact change and evolve in form and meaning through repeated use. To create flexible human-like interaction systems, it is necessary to deal with signs as a dynamic property and to construct a framework in which signs emerge from mutual adaptation by agents. Our target is multi-modal interaction using voice and motion between two robots where a voice/motion pattern is used as a sign referring to a motion/voice pattern. To enable evolutionary signs (voice and motion patterns) to be recognized and generated, we utilized a dynamics model: Multiple Timescale Recurrent Neural Network (MTRNN). To enable the robots to interpret signs, we utilized hierarchical neural networks, which transform dynamics model parameters of voice/motion into those of motion/voice. In our experiment, two robots modified their own interpretation of signs constantly through mutual adaptation in interaction where they responded to the other's voice with motion one after the other. As a result of the experiment, we found that the interaction kept evolving through the robots' repeated and alternate miscommunications and readaptations, and this induced the emergence of diverse new signs that depended on the robots' body dynamics through the generalization capability of MTRNN.

AB - We propose a model of evolutionary interaction between two robots where signs used for communication emerge through mutual adaptation. Signs used in human interaction, e.g., language, gestures and eye contact change and evolve in form and meaning through repeated use. To create flexible human-like interaction systems, it is necessary to deal with signs as a dynamic property and to construct a framework in which signs emerge from mutual adaptation by agents. Our target is multi-modal interaction using voice and motion between two robots where a voice/motion pattern is used as a sign referring to a motion/voice pattern. To enable evolutionary signs (voice and motion patterns) to be recognized and generated, we utilized a dynamics model: Multiple Timescale Recurrent Neural Network (MTRNN). To enable the robots to interpret signs, we utilized hierarchical neural networks, which transform dynamics model parameters of voice/motion into those of motion/voice. In our experiment, two robots modified their own interpretation of signs constantly through mutual adaptation in interaction where they responded to the other's voice with motion one after the other. As a result of the experiment, we found that the interaction kept evolving through the robots' repeated and alternate miscommunications and readaptations, and this induced the emergence of diverse new signs that depended on the robots' body dynamics through the generalization capability of MTRNN.

UR - http://www.scopus.com/inward/record.url?scp=76249104738&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=76249104738&partnerID=8YFLogxK

U2 - 10.1109/IROS.2009.5353887

DO - 10.1109/IROS.2009.5353887

M3 - Conference contribution

AN - SCOPUS:76249104738

SN - 9781424438044

SP - 4186

EP - 4192

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

ER -