Two-way translation of compound sentences and arm motions by recurrent neural networks

Tetsuya Ogata, Masamitsu Murase, Jim Tani, Kazunori Komatani, Hiroshi G. Okuno

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

35 Citations (Scopus)

Abstract

We present a connectionist model that combines motions and language based on the behavioral experiences of a real robot. Two models of recurrent neural network with parametric bias (RNNPB) were trained using motion sequences and linguistic sequences. These sequences were combined using their respective parameters so that the robot could handle many-to-many relationships between motion sequences and linguistic sequences. Motion sequences were articulated into some primitives corresponding to given linguistic sequences using the prediction error of the RNNPB model. The experimental task in which a humanoid robot moved its arm on a table demonstrated that the robot could generate a motion sequence corresponding to given linguistic sequence even if the motions or sequences were not included in the training data, and vice versa.

Original languageEnglish
Title of host publicationIEEE International Conference on Intelligent Robots and Systems
Pages1858-1863
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

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Ogata, T., Murase, M., Tani, J., Komatani, K., & Okuno, H. G. (2007). Two-way translation of compound sentences and arm motions by recurrent neural networks. In IEEE International Conference on Intelligent Robots and Systems (pp. 1858-1863). [4399265] https://doi.org/10.1109/IROS.2007.4399265