Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems

03/07/2021
by   Spencer M. Richards, et al.
0

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.

READ FULL TEXT
research
04/14/2022

Control-oriented meta-learning

Real-time adaptation is imperative to the control of robots operating in...
research
03/02/2021

Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions

Realtime model learning proves challenging for complex dynamical systems...
research
04/05/2023

Convex Optimization-based Policy Adaptation to Compensate for Distributional Shifts

Many real-world systems often involve physical components or operating e...
research
07/04/2022

Bayesian Optimization-based Nonlinear Adaptive PID Controller Design for Robust Mobile Manipulation

In this paper, we propose to use a nonlinear adaptive PID controller to ...
research
12/25/2022

Temporally Layered Architecture for Adaptive, Distributed and Continuous Control

We present temporally layered architecture (TLA), a biologically inspire...
research
07/21/2021

Online-Learning Deep Neuro-Adaptive Dynamic Inversion Controller for Model Free Control

Adaptive methods are popular within the control literature due to the fl...
research
09/07/2022

Adaptive Passivity-Based Pose Tracking Control of Cable-Driven Parallel Robots for Multiple Attitude Parameterizations

The proposed control method uses an adaptive feedforward-based controlle...

Please sign up or login with your details

Forgot password? Click here to reset