TY - GEN
T1 - Learning-based Adaptive Control using Contraction Theory
AU - Tsukamoto, Hiroyasu
AU - Chung, Soon Jo
AU - Slotine, Jean Jacques
N1 - ∗ Graduate Aerospace Laboratories, Caltech, Pasadena, CA, {htsukamoto, sjchung}@caltech.edu. † Nonlinear Systems Laboratory, MIT, Cambridge, MA, [email protected]. This work was in part funded by the Jet Propulsion Laboratory, California Institute of Technology. Code: https://github.com/astrohiro/ancm.
PY - 2021
Y1 - 2021
N2 - Adaptive control is subject to stability and performance issues when a learned model is used to enhance its performance. This paper thus presents a deep learning-based adaptive control framework for nonlinear systems with multiplicatively-separable parametrization, called adaptive Neural Contraction Metric (aNCM). The aNCM approximates real-time optimization for computing a differential Lyapunov function and a corresponding stabilizing adaptive control law by using a Deep Neural Network (DNN). The use of DNNs permits real-time implementation of the control law and broad applicability to a variety of nonlinear systems with parametric and nonparametric uncertainties. We show using contraction theory that the aNCM ensures exponential boundedness of the distance between the target and controlled trajectories in the presence of parametric uncertainties of the model, learning errors caused by aNCM approximation, and external disturbances. Its superiority to the existing robust and adaptive control methods is demonstrated using a cart-pole balancing model.
AB - Adaptive control is subject to stability and performance issues when a learned model is used to enhance its performance. This paper thus presents a deep learning-based adaptive control framework for nonlinear systems with multiplicatively-separable parametrization, called adaptive Neural Contraction Metric (aNCM). The aNCM approximates real-time optimization for computing a differential Lyapunov function and a corresponding stabilizing adaptive control law by using a Deep Neural Network (DNN). The use of DNNs permits real-time implementation of the control law and broad applicability to a variety of nonlinear systems with parametric and nonparametric uncertainties. We show using contraction theory that the aNCM ensures exponential boundedness of the distance between the target and controlled trajectories in the presence of parametric uncertainties of the model, learning errors caused by aNCM approximation, and external disturbances. Its superiority to the existing robust and adaptive control methods is demonstrated using a cart-pole balancing model.
UR - https://www.scopus.com/pages/publications/85119166309
UR - https://www.scopus.com/pages/publications/85119166309#tab=citedBy
U2 - 10.1109/CDC45484.2021.9683435
DO - 10.1109/CDC45484.2021.9683435
M3 - Conference contribution
AN - SCOPUS:85119166309
T3 - Proceedings of the IEEE Conference on Decision and Control
SP - 2533
EP - 2538
BT - 60th IEEE Conference on Decision and Control, CDC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 60th IEEE Conference on Decision and Control, CDC 2021
Y2 - 13 December 2021 through 17 December 2021
ER -