Pick-to-Learn for Systems and Control: Data-driven Synthesis with State-of-the-art Safety Guarantees

TL;DR

Pick-to-Learn (P2L) is a novel framework that integrates data-driven control synthesis with safety guarantees, utilizing all available data for optimal performance in complex systems.

Contribution

The paper introduces P2L, a comprehensive framework that provides safety and performance guarantees for any data-driven control method without sacrificing data for validation.

Findings

P2L outperforms traditional methods in control and safety tasks.

P2L effectively integrates data for synthesis and certification.

Demonstrated across optimal control, reachability, and robust control.

Abstract

Data-driven methods have become paramount in modern systems and control problems characterized by growing levels of complexity. In safety-critical environments, deploying these methods requires rigorous guarantees, a need that has motivated much recent work at the interface of statistical learning and control. However, many existing approaches achieve this goal at the cost of sacrificing valuable data for testing and calibration, or by constraining the choice of learning algorithm, thus leading to suboptimal performances. In this paper, we describe Pick-to-Learn (P2L) for Systems and Control, a framework that allows any data-driven control method to be equipped with state-of-the-art safety and performance guarantees. P2L enables the use of all available data to jointly synthesize and certify the design, eliminating the need to set aside data for calibration or validation purposes. In presenting a comprehensive version of P2L for systems and control, this paper demonstrates its effectiveness across a range of core problems, including optimal control, reachability analysis, safe synthesis, and robust control. In many of these applications, P2L delivers designs and certificates that outperform commonly employed methods, and shows strong potential for broad applicability in diverse practical settings.