-
Regret-optimal measurement-feedback control
We consider measurement-feedback control in linear dynamical systems fro...
read it
-
Regret-optimal control in dynamic environments
We consider the control of linear time-varying dynamical systems from th...
read it
-
Optimal Robust Safety-Critical Control for Dynamic Robotics
We present a novel method of optimal robust control through quadratic pr...
read it
-
Multicopter attitude control for recovery from large disturbances
We present a novel, high-performance attitude control law for multicopte...
read it
-
Meta-Learning Guarantees for Online Receding Horizon Control
In this paper we provide provable regret guarantees for an online meta-l...
read it
-
Generating Adversarial Disturbances for Controller Verification
We consider the problem of generating maximally adversarial disturbances...
read it
-
Neural Simplex Architecture
We present the Neural Simplex Architecture (NSA), a new approach to runt...
read it
Safety-Critical Online Control with Adversarial Disturbances
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.
READ FULL TEXT
Comments
There are no comments yet.