Neuroevolution with CMA-ES for Real-time Gain Tuning of a Car-like Robot Controller

Ashley Hill, Eric Lucet, Roland Lenain

2019

Abstract

This paper proposes a method for dynamically varying the gains of a mobile robot controller that takes into account, not only errors to the reference trajectory but also the uncertainty in the localisation. To do this, the covariance matrix of a state observer is used to indicate the precision of the perception. CMA-ES, an evolutionary algorithm is used to train a neural network that is capable of adapting the robot’s behaviour in real-time. Using a car-like vehicle model in simulation. Promising results show significant trajectory following performances improvements thanks to control gains fluctuations by using this new method. Simulations demonstrate the capability of the system to control the robot in complex environments, in which classical static controllers could not guarantee a stable behaviour.

Download


Paper Citation


in Harvard Style

Hill A., Lucet E. and Lenain R. (2019). Neuroevolution with CMA-ES for Real-time Gain Tuning of a Car-like Robot Controller.In Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-758-380-3, pages 311-319. DOI: 10.5220/0007927103110319


in Bibtex Style

@conference{icinco19,
author={Ashley Hill and Eric Lucet and Roland Lenain},
title={Neuroevolution with CMA-ES for Real-time Gain Tuning of a Car-like Robot Controller},
booktitle={Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2019},
pages={311-319},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007927103110319},
isbn={978-989-758-380-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - Neuroevolution with CMA-ES for Real-time Gain Tuning of a Car-like Robot Controller
SN - 978-989-758-380-3
AU - Hill A.
AU - Lucet E.
AU - Lenain R.
PY - 2019
SP - 311
EP - 319
DO - 10.5220/0007927103110319