Regularized GLISp for sensor-guided human-in-the-loop optimization

TL;DR

This paper introduces a sensor-guided regularized extension of GLISp that combines preference-based optimization with sensor measurements, leading to faster convergence and better solutions in human-in-the-loop calibration tasks.

Contribution

The work presents a novel grey-box approach integrating sensor data into preference-based optimization, enhancing performance over traditional black-box methods.

Findings

Faster convergence in benchmark tests

Superior final solutions in vehicle suspension tuning

Effective integration of sensor data with preference learning

Abstract

Human-in-the-loop calibration is often addressed via preference-based optimization, where algorithms learn from pairwise comparisons rather than explicit cost evaluations. While effective, methods such as Preferential Bayesian Optimization or Global optimization based on active preference learning with radial basis functions (GLISp) treat the system as a black box and ignore informative sensor measurements. In this work, we introduce a sensor-guided regularized extension of GLISp that integrates measurable descriptors into the preference-learning loop through a physics-informed hypothesis function and a least-squares regularization term. This injects grey-box structure, combining subjective feedback with quantitative sensor information while preserving the flexibility of preference-based search. Numerical evaluations on an analytical benchmark and on a human-in-the-loop vehicle suspension tuning task show faster convergence and superior final solutions compared to baseline GLISp.