000102395 001__ 102395
000102395 005__ 20180317093214.0
000102395 02470 $$2DAR$$a8674
000102395 037__ $$aARTICLE
000102395 245__ $$aDiscriminative and Adaptive Imitation in Uni-Manual and Bi-Manual Tasks
000102395 269__ $$a2006
000102395 260__ $$c2006
000102395 336__ $$aJournal Articles
000102395 520__ $$aThis paper addresses the problems of what to imitate and how to imitate in simple uni- and bi-manual manipulatory tasks. To solve the what to imitate issue, we use a probabilistic method, based on Hidden Markov Models, for extracting the relative importance of reproducing either the gesture or the specific hand path in a given task. This allows us to determine a metric of imitation performance. To solve the how to imitate issue, we compute the trajectory that optimizes the metric, given a set of robot's body constraints. We validate the methods in a series of experiments, where a human demonstrator teaches through kinesthetic a humanoid robot how to manipulate simple objects.
000102395 6531_ $$aRobot Programming by Demonstration (RbD)
000102395 6531_ $$aLearning by Imitation
000102395 6531_ $$aHuman-Robot Interaction (HRI)
000102395 6531_ $$aHidden Markov Model (HMM)
000102395 700__ $$0240594$$aBillard, A.$$g115671
000102395 700__ $$0240592$$aCalinon, S.$$g119190
000102395 700__ $$0240591$$aGuenter, F.$$g127923
000102395 773__ $$j54$$k5$$q370-384$$tRobotics and Autonomous Systems
000102395 8564_ $$s1841562$$uhttps://infoscience.epfl.ch/record/102395/files/ras05.pdf$$zn/a
000102395 909CO $$ooai:infoscience.tind.io:102395$$particle$$pSTI
000102395 909C0 $$0252119$$pLASA$$xU10660
000102395 937__ $$aLASA-ARTICLE-2007-003
000102395 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000102395 980__ $$aARTICLE