Learning flatness-based controller using neural networks

被引：0

作者：

Ren, Hailin ^{[1
]}

Qi, Jingyuan ^{[2
]}

Ben-Tzvi, Pinhas ^{[1
]}

机构：

[1] Robotics and Mechatronics Lab, Department of Mechanical Engineering, Virginia Tech, Blacksburg, 24060, VA

[2] Department of Physics, Virginia Tech, Blacksburg, 24060, VA

来源：

ASME Letters in Dynamic Systems and Control | 2021年 / 1卷 / 02期

关键词：

Dynamics and control; Machine learning; Neural networks; Nonlinear systems; Robotics;

D O I：

10.1115/1.4046776

中图分类号：

学科分类号：

摘要：

This paper presents a method to imitate flatness-based controllers for mobile robots using neural networks. Sample case studies for a unicycle mobile robot and an unmanned aerial vehicle (UAV) quadcopter are presented. The goals of this paper are to (1) train a neural network to approximate a previously designed flatness-based controller, which takes in the desired trajectories previously planned in the flatness space and robot states in a general state space, and (2) present a dynamic training approach to learn models with high-dimensional inputs. It is shown that a simple feedforward neural network could adequately compute the highly nonlinear state variables transformation from general state space to flatness space and replace the complicated designed heuristic to avoid singularities in the control law. This paper also presents a new dynamic training method for models with high-dimensional independent inputs, serving as a reference for learning models with a multitude of inputs. Training procedures and simulations are presented to show both the effectiveness of this novel training approach and the performance of the welltrained neural network. Copyright © 2021 by ASME.

引用

共 23 条

[1]

Sira-Ramirez H., Agrawal S., Differentially Flat Systems, 5, (2004)

[2]

Francisco S., Murray R. M., Rathinam M., Sluis W., Differential Flatness of Mechanical Control Systems: A Catalog of Prototype Systems, Proceedings of the 1995 ASME International Congress and Exposition, (1995)

[3]

Soheil-Hamedani M., Zandi M., Gavagsaz-Ghoachani R., Nahid-Mobarakeh B., Pierfederici S., Flatness-Based Control Method: A Review of Its Applications to Power Systems, 2016 7th Power Electronics and Drive Systems Technologies Conference (PEDSTC), pp. 547-552, (2016)

[4]

Tang C. P., Differential Flatness-Based Kinematic and Dynamic Control of a Differentially Driven Wheeled Mobile Robot, 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 2267-2272, (2009)

[5]

De Luca A., Oriolo G., Samson C., Feedback Control of a Nonholonomic Car-Like Robot, Robot Motion Planning and Control, pp. 171-253, (1998)

[6]

Poultney A., Kennedy C., Clayton G., Ashrafiuon H., Robust Tracking Control of Quadrotors Based on Differential Flatness: Simulations and Experiments, IEEE/ASME Trans. Mechatronics, 23, 3, pp. 1126-1137, (2018)

[7]

Cowling I. D., Yakimenko O. A., Whidborne J. F., Cooke A. K., A Prototype of An Autonomous Controller for a Quadrotor UAV, 2007 European Control Conference (ECC), pp. 4001-4008, (2007)

[8]

Agrawal S., Sangwan V., Differentially Flat Designs of Underactuated Open-Chain Planar Robots, IEEE Trans. Rob, 24, 6, pp. 1445-1451, (2008)

[9]

Ren H., Kumar A., Wang X., Ben-Tzvi P., Parallel Deep Learning Ensembles for Human Pose Estimation, Dynamic Systems and Control Conference, (2018)

[10]

Young T., Hazarika D., Poria S., Cambria E., Recent Trends in Deep Learning Based Natural Language Processing [Review Article], IEEE Comput. Intell. Mag, 13, 3, pp. 55-75, (2018)

← 1 2 3 →