Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems
Preprint
Abstract
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 meta-learning of features to fit input-output data. Specifically, we meta-learn the adaptive controller with closed-loop tracking simulation as the base-learner and the average tracking error as the meta-objective. 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.Keywords
All Related Versions
This publication has 29 references indexed in Scilit:
- Array programming with NumPyNature, 2020
- A robust adaptive model predictive control framework for nonlinear uncertain systemsInternational Journal of Robust and Nonlinear Control, 2020
- CasADi: a software framework for nonlinear optimization and optimal controlMathematical Programming Computation, 2018
- Robust adaptive MPC for constrained uncertain nonlinear systemsInternational Journal of Adaptive Control and Signal Processing, 2010
- For model-based control design, closed-loop identification gives better performanceAutomatica, 1996
- Unconstrained parametrizations for variance-covariance matricesStatistics and Computing, 1996
- Nonlinear control design for slightly non-minimum phase systems: Application to V/STOL aircraftAutomatica, 1992
- Composite adaptive control of robot manipulatorsAutomatica, 1989
- Necessary and sufficient conditions for parameter convergence in adaptive controlAutomatica, 1986
- Exponential Convergence of Adaptive Identification and Control AlgorithmsIFAC Proceedings Volumes, 1981