000102365 001__ 102365
000102365 005__ 20190316233944.0
000102365 02470 $$2DAR$$a10260
000102365 02470 $$2ISI$$a000245109300004
000102365 037__ $$aARTICLE
000102365 245__ $$aOn Learning, Representing and Generalizing a Task in a Humanoid Robot
000102365 269__ $$a2007
000102365 260__ $$c2007
000102365 336__ $$aJournal Articles
000102365 520__ $$aWe present a Programming by Demonstration (PbD) framework for generically extracting the relevant features of a given task and for addressing the problem of generalizing the acquired knowledge to different contexts. We validate the architecture through a series of experiments in which a human demonstrator teaches a humanoid robot some simple manipulatory tasks. A probability based estimation of the relevance is suggested, by first projecting the joint angles, hand paths, and object-hand trajectories onto a generic latent space using Principal Component Analysis (PCA). The resulting signals were then encoded using a mixture of Gaussian/Bernoulli distributions (GMM/BMM). This provides a measure of the spatio-temporal correlations across the different modalities collected from the robot which can be used to determine a metric of the imitation performance. The trajectories are then generalized using Gaussian Mixture Regression (GMR). Finally, we analytically compute the trajectory which optimizes the imitation metric and use this to generalize the skill to different contexts and to the robot's specific bodily constraints.
000102365 6531_ $$aRobot Programming by Demonstration (RbD)
000102365 6531_ $$aLearning by Imitation
000102365 6531_ $$aHuman-Robot Interaction (HRI)
000102365 6531_ $$aGaussian Mixture Model (GMM)
000102365 6531_ $$aGaussian Mixture Regression (GMR)
000102365 700__ $$0240592$$aCalinon, S.$$g119190
000102365 700__ $$0240591$$aGuenter, F.$$g127923
000102365 700__ $$0240594$$aBillard, A.$$g115671
000102365 773__ $$j37$$k2$$q286-298$$tIEEE transactions on systems, man and cybernetics, Part B. Special issue on robot learning by observation, demonstration and imitation
000102365 8564_ $$zURL
000102365 8564_ $$s2219093$$uhttps://infoscience.epfl.ch/record/102365/files/Calinon-JSMC2006.pdf$$zn/a
000102365 909C0 $$0252119$$pLASA$$xU10660
000102365 909CO $$ooai:infoscience.tind.io:102365$$pSTI$$particle$$qGLOBAL_SET
000102365 937__ $$aLASA-ARTICLE-2007-001
000102365 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000102365 980__ $$aARTICLE