On the Convergence of DEM’s Linear Parameter Estimator

Conference paper (2022)

Authors

A. Anil Meera Robot Dynamics - Mechanical, Maritime and Materials Engineering

M. Wisse Robot Dynamics - Mechanical, Maritime and Materials Engineering

Research Group

Robot Dynamics (Mechanical, Maritime and Materials Engineering) (TU Delft)

DOI: https://doi.org/10.1007/978-3-030-93736-2_49

Parameter estimation Dynamic expectation maximization Free energy principle Linear state space systems

To reference this document use:

http://resolver.tudelft.nl/uuid:43f969df-969f-4c8f-9a0e-eeeedc62aa61

More Info

expand_more

Published Date

2022

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical, Maritime and Materials Engineering

Department

Cognitive Robotics

Research Group

Robot Dynamics

Abstract

The free energy principle from neuroscience provides an efficient data-driven framework called the Dynamic Expectation Maximization (DEM), to learn the generative model in the environment. DEM’s growing potential to be the brain-inspired learning algorithm for robots demands a mathematically rigorous analysis using the standard control system tools. Therefore, this paper derives the mathematical proof of convergence for its parameter estimator for linear state space systems, subjected to colored noise. We show that the free energy based parameter learning converges to a stable solution for linear systems. The paper concludes by providing a proof of concept through simulation for a wide range of spring damper systems.

Files

978_3_030_93736_2_49.pdf

(.pdf | 0.35 Mb)

- Embargo expired in 01-07-2023