?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Collaboration+Development+through+Interactive+Learning+between+Human+and+Robot&rft.creator=Ogata%2C+Tetsuya&rft.creator=Masago%2C+Noritaka&rft.creator=Sugano%2C+Shigeki&rft.creator=Tani%2C+Jun&rft.subject=Dynamical+Systems&rft.subject=Neural+Nets&rft.subject=Robotics&rft.description=In+this+paper%2C+we+investigated+interactive+learning+between+human+subjects+and+robot+experimentally%2C+and+its+essential+characteristics+are+examined+using+the+dynamical+systems+approach.+Our+research+concentrated+on+the+navigation+system+of+a+specially+developed+humanoid+robot+called+Robovie+and+seven+human+subjects+whose+eyes+were+covered%2C+making+them+dependent+on+the+robot+for+directions.+We+compared+the+usual+feed-forward+neural+network+(FFNN)+without+recursive+connections+and+the+recurrent+neural+network+(RNN).+Although+the+performances+obtained+with+both+the+RNN+and+the+FFNN+improved+in+the+early+stages+of+learning%2C+as+the+subject+changed+the+operation+by+learning+on+its+own%2C+all+performances+gradually+became+unstable+and+failed.+Results+of+a+questionnaire+given+to+the+subjects+confirmed+that+the+FFNN+gives+better+mental+impressions%2C+especially+from+the+aspect+of+operability.+When+the+robot+used+a+consolidation-learning+algorithm+using+the+rehearsal+outputs+of+the+RNN%2C+the+performance+improved+even+when+interactive+learning+continued+for+a+long+time.+The+questionnaire+results+then+also+confirmed+that+the+subject's+mental+impressions+of+the+RNN+improved+significantly.+The+dynamical+systems+analysis+of+RNNs+support+these+differences+and+also+showed+that+the+collaboration+scheme+was+developed+dynamically+along+with+succeeding+phase+transitions.&rft.publisher=Lund+University+Cognitive+Studies&rft.contributor=Prince%2C+Christopher+G.&rft.contributor=Berthouze%2C+Luc&rft.contributor=Kozima%2C+Hideki&rft.contributor=Bullock%2C+Daniel&rft.contributor=Stojanov%2C+Georgi&rft.contributor=Balkenius%2C+Christian&rft.date=2003&rft.type=Conference+Paper&rft.type=PeerReviewed&rft.format=application%2Fpdf&rft.identifier=http%3A%2F%2Fcogprints.org%2F3336%2F1%2FOgata.pdf&rft.identifier=++Ogata%2C+Tetsuya+and+Masago%2C+Noritaka+and+Sugano%2C+Shigeki+and+Tani%2C+Jun++(2003)+Collaboration+Development+through+Interactive+Learning+between+Human+and+Robot.++%5BConference+Paper%5D+++++&rft.relation=http%3A%2F%2Fcogprints.org%2F3336%2F