000198846 001__ 198846
000198846 005__ 20190416220316.0
000198846 037__ $$aCONF
000198846 245__ $$aLearning from demonstrations with partially observable task parameters
000198846 269__ $$a2014
000198846 260__ $$c2014
000198846 336__ $$aConference Papers
000198846 520__ $$aRobot learning from demonstrations requires the robot to learn and adapt movements to new situations, often characterized by position and orientation of objects or landmarks in the robot’s environment. In the task-parameterized Gaussian mixture model framework, the movements are considered to be modulated with respect to a set of candidate frames of reference (coordinate systems) attached to a set of objects in the robot workspace. Following a similar approach, this paper addresses the problem of having missing candidate frames during the demonstrations and reproductions, which can happen in various situations such as visual occlusion, sensor unavailability, or tasks with a variable number of descriptive features. We study this problem with a dust sweeping task in which the robot requires to consider a variable amount of dust areas to clean for each reproduction trial.
000198846 700__ $$aAlizadeh, T.
000198846 700__ $$aCalinon, S.
000198846 700__ $$aCaldwell, D. G.
000198846 7112_ $$aProc. IEEE Intl Conf. on Robotics and Automation (ICRA)
000198846 8564_ $$uhttps://infoscience.epfl.ch/record/198846/files/Alizadeh_ICRA_2014.pdf$$zn/a$$s1187820$$yn/a
000198846 909C0 $$xU10381$$0252189$$pLIDIAP
000198846 909CO $$ooai:infoscience.tind.io:198846$$qGLOBAL_SET$$pconf$$pSTI
000198846 937__ $$aEPFL-CONF-198846
000198846 970__ $$aAlizadeh_ICRA_2014/LIDIAP
000198846 973__ $$aEPFL
000198846 980__ $$aCONF