On improving the extrapolation capability of task-parameterized movement models

104 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Geometrical Invariance and Smoothness Maximization for Task-Space Movement Generation (2016, methodology): “1) A task-parameterized Gaussian mixture model (TpGMM) [49], which implements a virtual spring damper system.”
A tutorial on task-parameterized movement learning and retrieval (2015, methodology): “The proposed task-parameterized model is not new: preliminary versions were investigated in [14,16,20] for the special case of frames of reference representing rotations and translations in Cartesian space.”
Neural learning of vector fields for encoding stable dynamical systems (2014, methodology): “An alternative approach to the standard DMP approach is the task-parameterized Gaussian mixture model (TpGMM [16]), where the parameterization of the motion is variable.”
Learning bimanual end-effector poses from demonstrations using task-parameterized dynamical systems (2015, background): “We showed in [12] that treating task adaptation as standard regression (with GP implementation as example) has limited generalization capabilities.”