PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Adaptive Optimal Feedback Control with Learned Internal Dynamics Models
Djordje Mitrovic, Sethu Vijayakumar and Stefan Klanke
In: From Motor Learning to Interaction Learning in Robots Studies in Computational Intelligence , 264 . (2010) Springer Verlag , pp. 65-84. ISBN 978-3-642-05180-7

Abstract

Optimal Feedback Control (OFC) has been proposed as an attractive movement generation strategy in goal reaching tasks for anthropomorphic manipulator systems. Recent developments, such as the Iterative Linear Quadratic Gaussian (ILQG) algorithm, have focused on the case of non-linear, but still analytically available, dynamics. For realistic control systems, however, the dynamics may often be unknown, difficult to estimate, or subject to frequent systematic changes. In this chapter, we combine the ILQG framework with learning the forward dynamics for simulated arms, which exhibit large redundancies, both, in kinematics and in the actuation. We demonstrate how our approach can compensate for complex dynamic perturbations in an online fashion. The specific adaptive framework introduced lends itself to a computationally more efficient implementation of the ILQG optimisation without sacrificing control accuracy – allowing the method to scale to large DoF systems.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Book Section
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
Theory & Algorithms
ID Code:5901
Deposited By:Stefan Klanke
Deposited On:08 March 2010