PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

A study of Morphological Computation by using Probabilistic Inference for Motor Planning
Elmar Rückert and Gerhard Neumann
In: International Conference on Morphological Computation ICMC 2011, 12-14 Sep 2011, Venice, Italy.

Abstract

One key idea behind morphological computation is that many difficulties of a control problem can be absorbed by the morphology of the robot. The performance of the controlled system naturally depends on the control architecture and on the morphology of the robot. Ideally, adapting the morphology of the plant and optimizing the control law interact such that finally, optimal physical properties of the system and optimal control laws emerge. As a first step towards this vision we propose to use optimal control methods for investigating the power of morphological computation. We use probabilistic inference for motor control to acquire optimal control laws given the current morphology. By changing the morphology of our robot, control problems can be simplified, resulting in controllers with higher performance and reduced complexity.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Talk)
Additional Information:This paper was selected by the conference committee members to be submitted to the Special Issue on Morphological Computation in the journal Artificial Life.
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:8757
Deposited By:Elmar Rückert
Deposited On:21 February 2012