Control of a two-dimensional magnetic positioning system with deep reinforcement learning and feedback linearization

Eduardo Bejar; Antonio Moran Cardenas

Control of a two-dimensional magnetic positioning system with deep reinforcement learning and feedback linearization

Eduardo Bejar
, Antonio Moran Cardenas

Pontificia Universidad Católica del Perú

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

This paper presents a neuro-controller based on deep reinforcement learning to control the nonlinear dynamics of a two-dimensional magnetic positioning system. The feedback-linearized model of the magnetic positioning system is used to generate training data for the neuro-controller. The neuro-controller is trained using the Deep Deterministic Policy Gradient (DDPG) algorithm. The effectiveness of the proposed control strategy is verified with different desired setpoints and trajectories, and diverse working conditions.

Original language	Spanish
Title of host publication	Midwest Symposium on Circuits and Systems
Pages	909-912
Number of pages	4
Volume	2018-August
State	Published - 22 Jan 2019
Externally published	Yes

Cite this

@inproceedings{146dd8978fdb4d8188a9ba2d21a533f0,

title = "Control of a two-dimensional magnetic positioning system with deep reinforcement learning and feedback linearization",

abstract = "This paper presents a neuro-controller based on deep reinforcement learning to control the nonlinear dynamics of a two-dimensional magnetic positioning system. The feedback-linearized model of the magnetic positioning system is used to generate training data for the neuro-controller. The neuro-controller is trained using the Deep Deterministic Policy Gradient (DDPG) algorithm. The effectiveness of the proposed control strategy is verified with different desired setpoints and trajectories, and diverse working conditions.",

author = "Eduardo Bejar and Cardenas, \{Antonio Moran\}",

year = "2019",

month = jan,

day = "22",

language = "Espa{\~n}ol",

volume = "2018-August",

pages = "909--912",

booktitle = "Midwest Symposium on Circuits and Systems",

}

TY - GEN

T1 - Control of a two-dimensional magnetic positioning system with deep reinforcement learning and feedback linearization

AU - Bejar, Eduardo

AU - Cardenas, Antonio Moran

PY - 2019/1/22

Y1 - 2019/1/22

N2 - This paper presents a neuro-controller based on deep reinforcement learning to control the nonlinear dynamics of a two-dimensional magnetic positioning system. The feedback-linearized model of the magnetic positioning system is used to generate training data for the neuro-controller. The neuro-controller is trained using the Deep Deterministic Policy Gradient (DDPG) algorithm. The effectiveness of the proposed control strategy is verified with different desired setpoints and trajectories, and diverse working conditions.

AB - This paper presents a neuro-controller based on deep reinforcement learning to control the nonlinear dynamics of a two-dimensional magnetic positioning system. The feedback-linearized model of the magnetic positioning system is used to generate training data for the neuro-controller. The neuro-controller is trained using the Deep Deterministic Policy Gradient (DDPG) algorithm. The effectiveness of the proposed control strategy is verified with different desired setpoints and trajectories, and diverse working conditions.

M3 - Contribución a la conferencia

VL - 2018-August

SP - 909

EP - 912

BT - Midwest Symposium on Circuits and Systems

ER -