Abstract | ||
---|---|---|
A system for mapping between different sensory modalities was developed for a robot system to enable it to generate motions expressing auditory signals and sounds generated by object movement. A recurrent neural network model with parametric bias, which has good generalization ability, is used as a learning model. Since the correspondences between auditory signals and visual signals are too numerous to memorize, the ability to generalize is indispensable. This system was implemented in the ''Keepon'' robot, and the robot was shown horizontal reciprocating or rotating motions with the sound of friction and falling or overturning motion with the sound of collision by manipulating a box object. Keepon behaved appropriately not only from learned events but also from unknown events and generated various sounds in accordance with observed motions. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1016/j.patrec.2010.05.002 | Pattern Recognition Letters |
Keywords | Field | DocType |
recurrent neural network with parametric bias,box object,generalization,auditory signal,different sensory modality,good generalization ability,inter-modality mapping,inter-modal mapping,observed motion,dynamical systems,object movement,various sound,horizontal reciprocating,robot system,recurrent neural network model,dynamic system,recurrent neural network | Audio signal,Computer vision,Computer science,Recurrent neural network,Dynamical systems theory,Parametric statistics,Artificial intelligence,Robot,Reciprocating motion,Stimulus modality,Robotics | Journal |
Volume | Issue | ISSN |
31 | 12 | Pattern Recognition Letters |
Citations | PageRank | References |
11 | 0.74 | 7 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tetsuya Ogata | 1 | 1158 | 135.73 |
Shun Nishide | 2 | 60 | 13.47 |
Hideki Kozima | 3 | 297 | 32.71 |
Kazunori Komatani | 4 | 790 | 87.95 |
Hiroshi G. Okuno | 5 | 2092 | 233.19 |