Paper Info
Title
Prediction and imitation of other's motions by reusing own forward-inverse model in robots
Abstract
This paper proposes a model that enables a robot to predict and imitate the motions of another by reusing its body forward-inverse model. Our model includes three approaches: (i) projection of a self-forward model for predicting phenomena in the external environment (other individuals), (ii) "triadic relation" that is mediation by a physical object between self and others, (iii) introduction of infant imitation by a parent. The Recurrent Neural Network with Parametric Bias (RNNPB) model is used as the robot's self forward-inverse model. A group of hierarchical neural networks are attached to the RNNPB model as "conversion modules". Experiments demonstrated that a robot with our model could imitate a human's motions by translating the viewpoint. It could also discriminate known/unknown motions appropriately, and associate whole motion dynamics from only one motion snap image.
Year
DOI
Venue
2009
10.1109/ROBOT.2009.5152363
ICRA
Keywords
Field
DocType
motion snap image,self forward-inverse model,own forward-inverse model,self-forward model,parametric bias,rnnpb model,unknown motion,conversion module,body forward-inverse model,recurrent neural network,associate whole motion dynamic,cognitive robotics,neural networks,predictive models,recurrent neural networks,visualization,motion control,inverse modeling,mobile robots,predictive control,pediatrics,mediation,mobile robot
Cognitive robotics,Motion control,Computer science,Recurrent neural network,Parametric statistics,Artificial intelligence,Imitation,Robot,Artificial neural network,Mobile robot
Conference
Volume
Issue
ISSN
2009
1
1050-4729
Citations 
PageRank 
References 
2
0.39
4
Authors
5
Name
Order
Citations
PageRank
Tetsuya Ogata11158135.73
Ryunosuke Yokoya2111.96
Jun Tani31508139.42
Kazunori Komatani479087.95
Hiroshi G. Okuno52092233.19