000263543 001__ 263543
000263543 005__ 20190619220159.0
000263543 022__ $$a0278-3649
000263543 022__ $$a1741-3176
000263543 02470 $$a000454319900001$$2isi
000263543 0247_ $$a10.1177/0278364918816374$$2doi
000263543 037__ $$aARTICLE
000263543 245__ $$aSmall-variance asymptotics for non-parametric online robot learning
000263543 260__ $$c2019$$aLondon$$bSAGE PUBLICATIONS LTD
000263543 269__ $$a2019-01-01
000263543 336__ $$aJournal Articles
000263543 520__ $$aSmall-variance asymptotics is emerging as a useful technique for inference in large-scale Bayesian non-parametric mixture models. This paper analyzes the online learning of robot manipulation tasks with Bayesian non-parametric mixture models under small-variance asymptotics. The analysis yields a scalable online sequence clustering (SOSC) algorithm that is non-parametric in the number of clusters and the subspace dimension of each cluster. SOSC groups the new datapoint in low-dimensional subspaces by online inference in a non-parametric mixture of probabilistic principal component analyzers (MPPCA) based on a Dirichlet process, and captures the state transition and state duration information online in a hidden semi-Markov model (HSMM) based on a hierarchical Dirichlet process. A task-parameterized formulation of our approach autonomously adapts the model to changing environmental situations during manipulation. We apply the algorithm in a teleoperation setting to recognize the intention of the operator and remotely adjust the movement of the robot using the learned model. The generative model is used to synthesize both time-independent and time-dependent behaviors by relying on the principles of shared and autonomous control. Experiments with the Baxter robot yield parsimonious clusters that adapt online with new demonstrations and assist the operator in performing remote manipulation tasks.
000263543 650__ $$aRobotics
000263543 650__ $$aRobotics
000263543 6531_ $$alearning and adaptive systems
000263543 6531_ $$abayesian non-parametrics
000263543 6531_ $$aonline learning
000263543 6531_ $$ahidden semi-markov model
000263543 6531_ $$asubspace clustering
000263543 6531_ $$ateleoperation
000263543 6531_ $$ahigh-dimensional data
000263543 6531_ $$ahidden markov-models
000263543 6531_ $$amanipulation tasks
000263543 6531_ $$amixture
000263543 6531_ $$adirichlet
000263543 6531_ $$atutorial
000263543 700__ $$g216104$$0246728$$aTanwani, Ajay Kumar
000263543 700__ $$aCalinon, Sylvain$$0240592$$g119190
000263543 773__ $$tInternational Journal of Robotics Research$$q3-22$$j38$$k1
000263543 8560_ $$faude.billard@epfl.ch
000263543 909C0 $$pIMT$$xU10343$$0252447
000263543 909CO $$pSTI$$particle$$ooai:infoscience.epfl.ch:263543
000263543 910C0 $$yDeclined$$pLASA$$xU10660$$maude.billard@epfl.ch$$zMarselli, Béatrice$$0252119
000263543 961__ $$afantin.reichler@epfl.ch
000263543 973__ $$aEPFL$$sPUBLISHED$$rREVIEWED
000263543 980__ $$aARTICLE
000263543 980__ $$aWoS
000263543 981__ $$aoverwrite