TY - GEN
T1 - Data-Driven Deep Learning Based Feedback Linearization of Systems with Unknown Dynamics
AU - Goswami, Raktim Gautam
AU - Krishnamurthy, Prashanth
AU - Khorrami, Farshad
N1 - Funding Information:
1Control/Robotics Research Laboratory, Elec. & Comp. Engg. Dept., Tandon School of Engineering (Polytechnic Institute), New York University, Brooklyn, NY, 11201 {rgg9769,pk929,khorrami}@nyu.edu This work was supported in part by ARO grant W911NF-22-1-0028 and in part by the New York University Abu Dhabi (NYUAD) Center for Artificial Intelligence and Robotics, funded by Tamkeen under the NYUAD Research Institute Award CG010.
Publisher Copyright:
© 2023 American Automatic Control Council.
PY - 2023
Y1 - 2023
N2 - A methodology is developed to learn a feedback linearization (i.e., nonlinear change of coordinates and input transformation) using a data-driven approach for a single input control-affine nonlinear system with unknown dynamics. We employ deep neural networks to learn the feedback law (input transformation) in conjunction with an extension of invertible neural networks to learn the nonlinear change of coordinates (state transformation). We also learn the matrices A and B of the transformed linear system and define loss terms to ensure controllability of the pair (A, B). The efficacy of our approach is demonstrated by simulations on a nonlinear system. Furthermore, we show that state feedback controllers designed using the feedback linearized system yield expected closed-loop behavior when applied to the original nonlinear system, further demonstrating validity of the learned feedback linearization.
AB - A methodology is developed to learn a feedback linearization (i.e., nonlinear change of coordinates and input transformation) using a data-driven approach for a single input control-affine nonlinear system with unknown dynamics. We employ deep neural networks to learn the feedback law (input transformation) in conjunction with an extension of invertible neural networks to learn the nonlinear change of coordinates (state transformation). We also learn the matrices A and B of the transformed linear system and define loss terms to ensure controllability of the pair (A, B). The efficacy of our approach is demonstrated by simulations on a nonlinear system. Furthermore, we show that state feedback controllers designed using the feedback linearized system yield expected closed-loop behavior when applied to the original nonlinear system, further demonstrating validity of the learned feedback linearization.
UR - http://www.scopus.com/inward/record.url?scp=85167805910&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85167805910&partnerID=8YFLogxK
U2 - 10.23919/ACC55779.2023.10156140
DO - 10.23919/ACC55779.2023.10156140
M3 - Conference contribution
AN - SCOPUS:85167805910
T3 - Proceedings of the American Control Conference
SP - 66
EP - 71
BT - 2023 American Control Conference, ACC 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 American Control Conference, ACC 2023
Y2 - 31 May 2023 through 2 June 2023
ER -