Multi-task Gaussian Process Learning of Robot Inverse Dynamics

By Kian Ming Adam Chai, Christopher K. I. Williams, Stefan Klanke, Sethu Vijayakumar. 2008

126 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.

Citations in the corpus

Vector Field Learning via Spectral Filtering (2010, background): “Starting from the work of [7], related ideas have been developed in the context of regularization methods [8], Gaussian processes [9,10].”
Online Sparse Multi-Output Gaussian Process Regression and Learning (2019, background): “The robot inverse dynamics problem considered in [17] and [23] is a typical multi-output regression problem in robotics, where the mapping from a 21-dimensional input space to a 7-dimensional output space needs to be modeled.”
On-line regression algorithms for learning mechanical models of robots: A survey (2011, background): “More interestingly, since the inverse dynamics model is unique but may be involved in the realization of diverse tasks at the kinematic level, one can see the problem of learning this inverse dynamics model through a first task and using it for other tasks as a transfer learning problem [22, 120].”
Remarks on multi-output Gaussian process regression (2018, background): “, environmental sensor networks [11], robot inverse dynamics [12], multivariate physiological time-series analysis [13], structural design [14], and aircraft design [15].”
Graphical Multi-Task Learning (2008, background): “These arise frequently in multi-task learning: see [8–10], and nearly all examples from [4].”
Feature-based transfer learning with real-world applications (2010, methodology): “[32] studied how to apply a GP based multi-task learning method to solve the inverse dynamics problem for a robotic manipulator [32].”