Online Learning of Industrial Manipulators' Dynamics Models

Research output: Book/ReportPh.D. thesisResearch

Abstract

The robotics industry has introduced light-weight compliant manipulators to increase the safety during human-robot interaction. This characteristic is achieved by replacing the stiff actuators of the traditional robots with compliant ones which creates challenges in the analytical derivation of the dynamics models. Those mainly derive from physics-based methods and thus they are based on physical properties which are hard to be calculated. 
In this thesis, is presented, a novel online machine learning approach  which is able to model both inverse and forward dynamics models of industrial manipulators. The proposed method belongs to the class of deep learning and exploits the concepts of self-organization, recurrent neural networks and iterative multivariate Bayesian regression. It has been evaluated on multiple datasets captured from industrial robots while they were performing various tasks. Also, it was compared with multiple other state-of-the-art machine learning algorithms. Moreover, the thesis presents the application of the proposed learning method on robot control for achieving trajectory execution while learning the inverse dynamics models  on-the-fly . Also it is presented the application of the forward dynamics models on a model-based reinforcement learning scheme.
Original languageEnglish
Number of pages183
Publication statusPublished - 2017
SeriesPh.d.-serien for Det Ingeniør- og Naturvidenskabelige Fakultet, Aalborg Universitet
ISSN2446-1636

Fingerprint

Industrial manipulators
Dynamic models
Learning systems
Robots
Human robot interaction
Recurrent neural networks
Industrial robots
Reinforcement learning
Learning algorithms
Manipulators
Robotics
Actuators
Physics
Physical properties
Trajectories
Industry

Bibliographical note

Dissertation not published.

Keywords

  • Robot Learning
  • Model Learning
  • Recurrent Neural Networks
  • Bayesian Inference
  • Reinforcement Learning
  • Industrial Robotics

Cite this

Polydoros, A. (2017). Online Learning of Industrial Manipulators' Dynamics Models. Ph.d.-serien for Det Ingeniør- og Naturvidenskabelige Fakultet, Aalborg Universitet
Polydoros, Athanasios. / Online Learning of Industrial Manipulators' Dynamics Models. 2017. 183 p. (Ph.d.-serien for Det Ingeniør- og Naturvidenskabelige Fakultet, Aalborg Universitet).
@phdthesis{cdade308701e4e73865a5d3eec4e4af2,
title = "Online Learning of Industrial Manipulators' Dynamics Models",
abstract = "The robotics industry has introduced light-weight compliant manipulators to increase the safety during human-robot interaction. This characteristic is achieved by replacing the stiff actuators of the traditional robots with compliant ones which creates challenges in the analytical derivation of the dynamics models. Those mainly derive from physics-based methods and thus they are based on physical properties which are hard to be calculated. In this thesis, is presented, a novel online machine learning approach  which is able to model both inverse and forward dynamics models of industrial manipulators. The proposed method belongs to the class of deep learning and exploits the concepts of self-organization, recurrent neural networks and iterative multivariate Bayesian regression. It has been evaluated on multiple datasets captured from industrial robots while they were performing various tasks. Also, it was compared with multiple other state-of-the-art machine learning algorithms. Moreover, the thesis presents the application of the proposed learning method on robot control for achieving trajectory execution while learning the inverse dynamics models  on-the-fly . Also it is presented the application of the forward dynamics models on a model-based reinforcement learning scheme.",
keywords = "Robot Learning, Model Learning, Recurrent Neural Networks , Bayesian Inference, Reinforcement Learning, Industrial Robotics",
author = "Athanasios Polydoros",
note = "Dissertation not published.",
year = "2017",
language = "English",

}

Polydoros, A 2017, Online Learning of Industrial Manipulators' Dynamics Models. Ph.d.-serien for Det Ingeniør- og Naturvidenskabelige Fakultet, Aalborg Universitet.

Online Learning of Industrial Manipulators' Dynamics Models. / Polydoros, Athanasios.

2017. 183 p.

Research output: Book/ReportPh.D. thesisResearch

TY - BOOK

T1 - Online Learning of Industrial Manipulators' Dynamics Models

AU - Polydoros, Athanasios

N1 - Dissertation not published.

PY - 2017

Y1 - 2017

N2 - The robotics industry has introduced light-weight compliant manipulators to increase the safety during human-robot interaction. This characteristic is achieved by replacing the stiff actuators of the traditional robots with compliant ones which creates challenges in the analytical derivation of the dynamics models. Those mainly derive from physics-based methods and thus they are based on physical properties which are hard to be calculated. In this thesis, is presented, a novel online machine learning approach  which is able to model both inverse and forward dynamics models of industrial manipulators. The proposed method belongs to the class of deep learning and exploits the concepts of self-organization, recurrent neural networks and iterative multivariate Bayesian regression. It has been evaluated on multiple datasets captured from industrial robots while they were performing various tasks. Also, it was compared with multiple other state-of-the-art machine learning algorithms. Moreover, the thesis presents the application of the proposed learning method on robot control for achieving trajectory execution while learning the inverse dynamics models  on-the-fly . Also it is presented the application of the forward dynamics models on a model-based reinforcement learning scheme.

AB - The robotics industry has introduced light-weight compliant manipulators to increase the safety during human-robot interaction. This characteristic is achieved by replacing the stiff actuators of the traditional robots with compliant ones which creates challenges in the analytical derivation of the dynamics models. Those mainly derive from physics-based methods and thus they are based on physical properties which are hard to be calculated. In this thesis, is presented, a novel online machine learning approach  which is able to model both inverse and forward dynamics models of industrial manipulators. The proposed method belongs to the class of deep learning and exploits the concepts of self-organization, recurrent neural networks and iterative multivariate Bayesian regression. It has been evaluated on multiple datasets captured from industrial robots while they were performing various tasks. Also, it was compared with multiple other state-of-the-art machine learning algorithms. Moreover, the thesis presents the application of the proposed learning method on robot control for achieving trajectory execution while learning the inverse dynamics models  on-the-fly . Also it is presented the application of the forward dynamics models on a model-based reinforcement learning scheme.

KW - Robot Learning

KW - Model Learning

KW - Recurrent Neural Networks

KW - Bayesian Inference

KW - Reinforcement Learning

KW - Industrial Robotics

M3 - Ph.D. thesis

BT - Online Learning of Industrial Manipulators' Dynamics Models

ER -

Polydoros A. Online Learning of Industrial Manipulators' Dynamics Models. 2017. 183 p. (Ph.d.-serien for Det Ingeniør- og Naturvidenskabelige Fakultet, Aalborg Universitet).