Sciweavers

Share
IROS
2007
IEEE

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

9 years 7 months ago
Two-way translation of compound sentences and arm motions by recurrent neural networks
- 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.
Tetsuya Ogata, Masamitsu Murase, Jun Tani, Kazunor
Added 03 Jun 2010
Updated 03 Jun 2010
Type Conference
Year 2007
Where IROS
Authors Tetsuya Ogata, Masamitsu Murase, Jun Tani, Kazunori Komatani, Hiroshi G. Okuno
Comments (0)
books