TORQUE CONTROL WITH RECURRENT NEURAL NETWORKS

Guillaume Jouffroy

2008

Abstract

In the robotics field, a lot of attention is given to the complexity of the mechanics and particularly to the number of degrees of freedom. Also, the oscillatory recurrent neural network architecture is only considered as a black box, which prevents from carefully studying the interesting features of the network’s dynamics. In this paper we describe a generalized teacher forcing algorithm, and we build a default oscillatory recurrent neural network controller for a vehicle of one degree of freedom. We then build a feedback system as a constraint method for the joint. We show that with the default oscillatory controller the vehicle can however behave correctly, even in its transient time from standing to moving, and is robust to the oscillatory controller’s own transient period and its initial conditions. We finally discuss how the default oscillator can be modified, thus reducing the local feedback adaptation amplitude.

Paper Citation

in Harvard Style

Jouffroy G. (2008). TORQUE CONTROL WITH RECURRENT NEURAL NETWORKS . In Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-8111-31-9, pages 109-114. DOI: 10.5220/0001501401090114

in Bibtex Style

@conference{icinco08,
author={Guillaume Jouffroy},
title={TORQUE CONTROL WITH RECURRENT NEURAL NETWORKS},
booktitle={Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2008},
pages={109-114},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001501401090114},
isbn={978-989-8111-31-9},
}

in EndNote Style

TY - CONF
JO - Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - TORQUE CONTROL WITH RECURRENT NEURAL NETWORKS
SN - 978-989-8111-31-9
AU - Jouffroy G.
PY - 2008
SP - 109
EP - 114
DO - 10.5220/0001501401090114