Learning for Goal-Directed Actions Using RNNPB: Developmental Change of "What to Imitate"

Cited 8 time in webofscience Cited 0 time in scopus
  • Hit : 594
  • Download : 109
What to imitate" is one of the most important and difficult issues in robot imitation learning. A possible solution from an engineering approach involves focusing on the salient properties of actions. We investigate the developmental change of what to imitate in robot action learning in this paper. Our robot is equipped with a recurrent neural network with parametric bias (RNNPB), and learned to imitate multiple goal-directed actions in two different environments (i.e., simulation and real humanoid robot). Our close analysis of the error measures and the internal representation of the RNNPB revealed that actions' most salient properties (i.e., reaching the desired end of motor trajectories) were learned first, while the less salient properties (i.e., matching the shape of motor trajectories) were learned later. Interestingly, this result was analogous to the developmental process of human infant's action imitation. We discuss the importance of our results in terms of understanding the underlying mechanisms of human development.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2018-09
Language
English
Article Type
Article
Citation

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, v.10, no.3, pp.545 - 556

ISSN
2379-8920
DOI
10.1109/TCDS.2017.2679765
URI
http://hdl.handle.net/10203/245890
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 8 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0