Domain Adaptation of Drag Reduction Policy to Partial Measurements

TL;DR

This paper introduces a method to adapt fluid flow control policies trained on full measurements to real-world scenarios with partial sensor data, using a domain-specific feature transfer map in a simulated vehicle drag reduction task.

Contribution

It proposes a novel domain-specific feature transfer approach to reconstruct full measurements from partial data, enabling effective control policy transfer from simulation to real-world conditions.

Findings

The method successfully reconstructs full measurements from partial data in simulations.

It enables the derivation of optimal control policies using limited sensor information.

The approach provides insights into the architecture and history length needed for effective control.

Abstract

Feedback control of fluid-based systems poses significant challenges due to their high-dimensional, nonlinear, and multiscale dynamics, which demand real-time, three-dimensional, multi-component measurements for sensing. While such measurements are feasible in digital simulations, they are often only partially accessible in the real world. In this paper, we propose a method to adapt feedback control policies obtained from full-state measurements to setups with only partial measurements. Our approach is demonstrated in a simulated environment by minimising the aerodynamic drag of a simplified road vehicle. Reinforcement learning algorithms can optimally solve this control task when trained on full-state measurements by placing sensors in the wake. However, in real-world applications, sensors are limited and typically only on the vehicle, providing only partial measurements. To address this, we propose to train a Domain Specific Feature Transfer (DSFT) map reconstructing the full measurements from the history of the partial measurements. By applying this map, we derive optimal policies based solely on partial data. Additionally, our method enables determination of the optimal history length and offers insights into the architecture of optimal control policies, facilitating their implementation in real-world environments with limited sensor information.