Safety-Critical Online Control with Adversarial Disturbances

TL;DR

This paper develops an online control method for safety-critical systems under adversarial disturbances, ensuring safety and minimizing cost with a logarithmic regret bound, validated through process control experiments.

Contribution

It introduces an iterative controller synthesis approach using a modified Riccati equation that enforces safety constraints in an online adversarial setting.

Findings

Regret grows logarithmically with time horizon.

Controller maintains safety constraints under adversarial attacks.

Validated on process control system with two attack types.

Abstract

This paper studies the control of safety-critical dynamical systems in the presence of adversarial disturbances. We seek to synthesize state-feedback controllers to minimize a cost incurred due to the disturbance, while respecting a safety constraint. The safety constraint is given by a bound on an H-inf norm, while the cost is specified as an upper bound on the H-2 norm of the system. We consider an online setting where costs at each time are revealed only after the controller at that time is chosen. We propose an iterative approach to the synthesis of the controller by solving a modified discrete-time Riccati equation. Solutions of this equation enforce the safety constraint. We compare the cost of this controller with that of the optimal controller when one has complete knowledge of disturbances and costs in hindsight. We show that the regret function, which is defined as the difference between these costs, varies logarithmically with the time horizon. We validate our approach on a process control setup that is subject to two kinds of adversarial attacks.