Deep Model Reference Adaptive Control

Joshi, Girish; Chowdhary, Girish

doi:10.1109/cdc40024.2019.9029173

Cited by 52 publications

(31 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Stable adaptive control of nonlinear systems often relies on linearly parameterizable dynamics with known nonlinear basis functions, i.e., features, and the ability to cancel these nonlinearities stably with the control input when the parameters are known exactly [69,70,71,44]. When such features cannot be derived a priori, function approximators such as neural networks [65,33,34] and Gaussian processes [25,23] can be used and updated online in the adaptive control loop. However, fast closed-loop adaptive control with complex function approximators is hindered by the computational effort required to train them; this issue is exacerbated by the practical need for controller gain tuning.…”

Section: B Adaptive Controlmentioning

confidence: 99%

Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems

Richards

Azizan

Slotine

et al. 2021

Robotics: Science and Systems XVII

View full text Add to dashboard Cite

Real-time adaptation is imperative to the control of robots operating in complex, dynamic environments. Adaptive control laws can endow even nonlinear systems with good trajectory tracking performance, provided that any uncertain dynamics terms are linearly parameterizable with known nonlinear features. However, it is often difficult to specify such features a priori, such as for aerodynamic disturbances on rotorcraft or interaction forces between a manipulator arm and various objects. In this paper, we turn to data-driven modeling with neural networks to learn, offline from past data, an adaptive controller with an internal parametric model of these nonlinear features.Our key insight is that we can better prepare the controller for deployment with control-oriented meta-learning of features in closed-loop simulation, rather than regression-oriented metalearning of features to fit input-output data. Specifically, we metalearn the adaptive controller with closed-loop tracking simulation as the base-learner and the average tracking error as the metaobjective. With a nonlinear planar rotorcraft subject to wind, we demonstrate that our adaptive controller outperforms other controllers trained with regression-oriented meta-learning when deployed in closed-loop for trajectory tracking control.

show abstract

Section: B Adaptive Controlmentioning

confidence: 99%

Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems

Richards

Azizan

Slotine

et al. 2021

Robotics: Science and Systems XVII

View full text Add to dashboard Cite

show abstract

“…However, earlier studies often use radial basis function (RBF) NNs, which require a sufficient preallocation of basis functions over the operating domain; the desired theoretical guarantees do not hold outside of the targeted operating domain. Recently, an asynchronous DNN MRAC framework was proposed to mitigate the limitation of RBF NNs by learning "features" at a slower timescale [19]; but, the approach only considers systems with additive input uncertainties.…”

Section: Related Workmentioning

confidence: 99%

Bridging the Model-Reality Gap with Lipschitz Network Adaptation

Zhou¹,

Perez²,

Zhao³

et al. 2021

Preprint

View full text Add to dashboard Cite

“…In [4], the disturbance experienced by the robot is parametrized through a neural network; the inner features parameters are meta-learned offline in closed-loop simulations of model ensembles under adaptive control. A deep network is used in [5] for quadrotor control; adaptation to different flight regimes is achieved using an MRAC law for the last layer weights. Research has also been conducted to add adaptive control stability guarantees in Quadratic Programs (QPs).…”

Section: Introductionmentioning

confidence: 99%