Title :
Prediction and imitation of other´s motions by reusing own forward-inverse model in robots
Author :
Ogata, Tetsuya ; Yokoya, Ryunosuke ; Tani, Jun ; Komatani, Kazunori ; Okuno, Hiroshi G.
Author_Institution :
Dept. of Intell. Sci. & Technol., Kyoto Univ., Kyoto, Japan
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) ldquotriadic relationrdquo 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 ldquoconversion modulesrdquo. 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.
Keywords :
mobile robots; motion control; neurocontrollers; predictive control; recurrent neural nets; robot dynamics; RNNPB model; conversion module; dynamic object; forward-inverse model; mobile robot; motion control; predicting phenomena; recurrent neural network-with-parametric bias model; self-forward model; triadic relation; Biological neural networks; Cognitive robotics; Humans; Image converters; Intelligent robots; Mediation; Neural networks; Predictive models; Recurrent neural networks; Robotics and automation;
Conference_Titel :
Robotics and Automation, 2009. ICRA '09. IEEE International Conference on
Conference_Location :
Kobe
Print_ISBN :
978-1-4244-2788-8
Electronic_ISBN :
1050-4729
DOI :
10.1109/ROBOT.2009.5152363