Title:
Low-Dimensional Learning for Complex Robots
Low-Dimensional Learning for Complex Robots
Files
Authors
O’Flaherty, Rowland
Egerstedt, Magnus B.
Egerstedt, Magnus B.
Authors
Advisors
Advisors
Associated Organizations
Organizational Unit
Organizational Unit
Series
Collections
Supplementary to
Permanent Link
Abstract
This paper presents an algorithm for learning the
switching policy and the boundaries conditions between primitive
controllers that maximize the translational movements of a
complex locomoting system. The algorithm learns an optimal
action for each boundary condition instead of one for each
discretized state-action pair of the system, as is typically done
in machine learning. The system is model as a hybrid system
because it contains both discrete and continuous dynamics. With
this hybridification of the system and with this abstraction of
learning boundary-action pairs, the “curse of dimensionality”
is mitigated. The effectiveness of this learning algorithm is
demonstrated on both a simulated system and on a physical
robotic system. In both cases, the algorithm is able to learn the
hybrid control strategy that maximizes the forward translational
movement of the system without the need for human involvement.
Sponsor
Date Issued
2015-01
Extent
Resource Type
Text
Resource Subtype
Post-print
Proceedings
Proceedings