VABO: Violation-Aware Bayesian Optimization for Closed-Loop Control Performance Optimization with Unmodeled Constraints

10/14/2021

∙

We study the problem of performance optimization of closed-loop control systems with unmodeled dynamics. Bayesian optimization (BO) has been demonstrated effective for improving closed-loop performance by automatically tuning controller gains or reference setpoints in a model-free manner. However, BO methods have rarely been tested on dynamical systems with unmodeled constraints. In this paper, we propose a violation-aware BO algorithm (VABO) that optimizes closed-loop performance while simultaneously learning constraint-feasible solutions. Unlike classical constrained BO methods which allow an unlimited constraint violations, or safe BO algorithms that are conservative and try to operate with near-zero violations, we allow budgeted constraint violations to improve constraint learning and accelerate optimization. We demonstrate the effectiveness of our proposed VABO method for energy minimization of industrial vapor compression systems.

READ FULL TEXT

VABO: Violation-Aware Bayesian Optimization for Closed-Loop Control Performance Optimization with Unmodeled Constraints

Violation-Aware Contextual Bayesian Optimization for Controller Performance Optimization with Unmodeled Constraints

CONFIG: Constrained Efficient Global Optimization for Closed-Loop Control System Optimization with Unmodeled Constraints

Closed-loop Model Selection for Kernel-based Models using Bayesian Optimization

Generative Adversarial Network based Autoencoder: Application to fault detection problem for closed loop dynamical systems

Robot Learning with Crash Constraints

Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures

Model Learning and Contextual Controller Tuning for Autonomous Racing

VABO: Violation-Aware Bayesian Optimization for Closed-Loop Control Performance Optimization with Unmodeled Constraints

Related Research

Violation-Aware Contextual Bayesian Optimization for Controller Performance Optimization with Unmodeled Constraints

CONFIG: Constrained Efficient Global Optimization for Closed-Loop Control System Optimization with Unmodeled Constraints

Closed-loop Model Selection for Kernel-based Models using Bayesian Optimization

Generative Adversarial Network based Autoencoder: Application to fault detection problem for closed loop dynamical systems

Robot Learning with Crash Constraints

Excursion Search for Constrained Bayesian Optimization under a Limited Budget of Failures

Model Learning and Contextual Controller Tuning for Autonomous Racing