Automatic dimensionality reduction of Twin-in-the-Loop Observers

TL;DR

This paper introduces a method to simplify a complex vehicle observer architecture by applying supervised and unsupervised learning techniques, validated with real-world vehicle data.

Contribution

It develops a procedure for dimensionality reduction of the Twin-in-the-Loop Observer using learning approaches, enhancing its practicality and efficiency.

Findings

Effective reduction of observer complexity demonstrated

Supervised and unsupervised learning improve model performance

Validated with real-world vehicle data

Abstract

Conventional vehicle dynamics estimation methods suffer from the drawback of employing independent, separately calibrated filtering modules for each variable. To address this limitation, a recent proposal introduces a unified Twin-in-the-Loop (TiL) Observer architecture. This architecture replaces the simplified control-oriented vehicle model with a full-fledged vehicle simulator (digital twin), and employs a real-time correction mechanism using a linear time-invariant output error law. Bayesian Optimization is utilized to tune the observer due to the simulator's black-box nature, leading to a high-dimensional optimization problem. This paper focuses on developing a procedure to reduce the observer's complexity by exploring both supervised and unsupervised learning approaches. The effectiveness of these strategies is validated for longitudinal and lateral vehicle dynamics using real-world data.