Advanced

Real-time deep learning of robotic manipulator inverse dynamics

Polydoros, A.S.; Nalpantidis, L. and Kruger, V. LU (2015) IEEE/RSJ International Conference on Intelligent Robots and Systems , 2015 p.3442-3448
Abstract
In certain cases analytical derivation of physics-based models of robots is difficult or even impossible. A potential workaround is the approximation of robot models from sensor data-streams employing machine learning approaches. In this paper, the inverse dynamics models are learned by employing a novel real-time deep learning algorithm. The algorithm exploits the methods of self-organized learning, reservoir computing and Bayesian inference. It is evaluated and compared to other state of the art algorithms in terms of generalization ability, convergence and adaptability using five datasets gathered from four robots. Results show that the proposed algorithm can adapt to real-time changes of the inverse dynamics model significantly better... (More)
In certain cases analytical derivation of physics-based models of robots is difficult or even impossible. A potential workaround is the approximation of robot models from sensor data-streams employing machine learning approaches. In this paper, the inverse dynamics models are learned by employing a novel real-time deep learning algorithm. The algorithm exploits the methods of self-organized learning, reservoir computing and Bayesian inference. It is evaluated and compared to other state of the art algorithms in terms of generalization ability, convergence and adaptability using five datasets gathered from four robots. Results show that the proposed algorithm can adapt to real-time changes of the inverse dynamics model significantly better than the other state of the art algorithms. (Less)
Please use this url to cite or link to this publication:
author
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
keywords
approximation theory, belief networks, inference mechanisms, learning (artificial intelligence), real-time systems, Bayesian inference, machine learning, physics-based models, real-time deep learning, reservoir computing, robotic manipulator, inverse dynamics, self-organized learning, sensor data-streams, Adaptation models, computational modeling, Heuristic algorithms, Manipulator dynamics, Robot sensing systems
host publication
2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS),
pages
7 pages
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
conference name
IEEE/RSJ International Conference on Intelligent Robots and Systems , 2015
conference location
Hamburg, Germany
conference dates
2015-09-28 - 2015-10-02
external identifiers
  • scopus:84958184203
ISBN
978-1-4799-9994-1
DOI
10.1109/IROS.2015.7353857
language
English
LU publication?
no
id
2dcf04e9-f812-42d8-b14c-7a804a0dd187
date added to LUP
2019-05-16 21:22:33
date last changed
2019-09-17 04:53:59
@inproceedings{2dcf04e9-f812-42d8-b14c-7a804a0dd187,
  abstract     = {In certain cases analytical derivation of physics-based models of robots is difficult or even impossible. A potential workaround is the approximation of robot models from sensor data-streams employing machine learning approaches. In this paper, the inverse dynamics models are learned by employing a novel real-time deep learning algorithm. The algorithm exploits the methods of self-organized learning, reservoir computing and Bayesian inference. It is evaluated and compared to other state of the art algorithms in terms of generalization ability, convergence and adaptability using five datasets gathered from four robots. Results show that the proposed algorithm can adapt to real-time changes of the inverse dynamics model significantly better than the other state of the art algorithms.},
  author       = {Polydoros, A.S. and Nalpantidis, L. and Kruger, V.},
  isbn         = {978-1-4799-9994-1},
  keyword      = {approximation theory,belief networks,inference mechanisms,learning (artificial intelligence),real-time systems,Bayesian inference,machine learning,physics-based models,real-time deep learning,reservoir computing,robotic manipulator,inverse dynamics,self-organized learning,sensor data-streams,Adaptation models,computational modeling,Heuristic algorithms,Manipulator dynamics,Robot sensing systems},
  language     = {eng},
  location     = {Hamburg, Germany},
  month        = {09},
  pages        = {3442--3448},
  publisher    = {IEEE--Institute of Electrical and Electronics Engineers Inc.},
  title        = {Real-time deep learning of robotic manipulator inverse dynamics},
  url          = {http://dx.doi.org/10.1109/IROS.2015.7353857},
  year         = {2015},
}