A Sensitivity-based Data Augmentation Framework for Model Predictive Control Policy Approximation

TL;DR

This paper introduces a sensitivity-based data augmentation method to efficiently generate training data for approximating MPC policies, reducing the computational burden of sampling the state-space.

Contribution

It proposes a novel sensitivity-based augmentation scheme that exploits parametric sensitivities to generate additional training samples near existing ones.

Findings

Reduces the need for extensive sampling of the state-space.

Enables more efficient training data generation for MPC policy approximation.

Potentially lowers computational costs in MPC implementation.

Abstract

Approximating model predictive control (MPC) policy using expert-based supervised learning techniques requires labeled training data sets sampled from the MPC policy. This is typically obtained by sampling the feasible state-space and evaluating the control law by solving the numerical optimization problem offline for each sample. Although the resulting approximate policy can be cheaply evaluated online, generating large training samples to learn the MPC policy can be time consuming and prohibitively expensive. This is one of the fundamental bottlenecks that limit the design and implementation of MPC policy approximation. This technical note aims to address this challenge, and proposes a novel sensitivity-based data augmentation scheme for direct policy approximation. The proposed approach is based on exploiting the parametric sensitivities to cheaply generate additional training samples in the neighborhood of the existing samples.