Learning soft task priorities for control of redundant robots

Modugno, V. and Neumann, Gerhard and Rueckert, E. and Oriolo, G. and Peters, J. and Ivaldi, S. (2016) Learning soft task priorities for control of redundant robots. In: IEEE International Conference on Robotics and Automation (ICRA) 2016, 16-21 May 2016, Stockholm, Sweden.

Documents
main_revised.pdf
[img]
[Download]
[img]
Preview
PDF
main_revised.pdf - Whole Document

3MB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

Movement primitives (MPs) provide a powerful
framework for data driven movement generation that has been
successfully applied for learning from demonstrations and robot
reinforcement learning. In robotics we often want to solve a
multitude of different, but related tasks. As the parameters
of the primitives are typically high dimensional, a common
practice for the generalization of movement primitives to new
tasks is to adapt only a small set of control variables, also
called meta parameters, of the primitive. Yet, for most MP
representations, the encoding of these control variables is precoded
in the representation and can not be adapted to the
considered tasks. In this paper, we want to learn the encoding of
task-specific control variables also from data instead of relying
on fixed meta-parameter representations. We use hierarchical
Bayesian models (HBMs) to estimate a low dimensional latent
variable model for probabilistic movement primitives (ProMPs),
which is a recent movement primitive representation. We show
on two real robot datasets that ProMPs based on HBMs
outperform standard ProMPs in terms of generalization and
learning from a small amount of data and also allows for an
intuitive analysis of the movement. We also extend our HBM by
a mixture model, such that we can model different movement
types in the same dataset.

Keywords:Movement Primitives, Robotics, Movement Skill Learning
Subjects:H Engineering > H671 Robotics
G Mathematical and Computer Sciences > G760 Machine Learning
Divisions:College of Science > School of Computer Science
ID Code:25639
Deposited On:21 Jul 2017 11:05

Repository Staff Only: item control page