Searcharxiv⌕ Search

arXiv subjects

Olle Kjellqvist

Publications and source records attributed to Olle Kjellqvist.

10 recordsLinked to original sources
arXiv2024

Output Feedback Minimax Adaptive Control

This paper formulates adaptive controller design as a minimax dual control problem. The objective is to design a controller that minimizes the worst-case performance over a set of uncertain systems. The uncertainty is described by a set of linear time-invariant systems with unknown parameters. The main contribution is a common framework for both state feedback and output feedback control. We show that for finite uncertainty sets, the minimax dual control problem admits a finite-dimensional information state. This information state can be used to design adaptive controllers that ensure that the closed-loop has finite gain. The controllers are derived from a set of Bellman inequalities that are amenable to numerical solutions. The proposed framework is illustrated on a challenging numerical example.

math.OC↗
arXiv2024

Minimax dual control with finite-dimensional information state

This article considers output-feedback control of systems where the function mapping states to measurements has a set-valued inverse. We show that if the set has a bounded number of elements, then minimax dual control of such systems admits finite-dimensional information states. We specialize our results to a discrete-time integrator with magnitude measurements and derive a surprisingly simple sub-optimal control policy that ensures finite gain of the closed loop. The sub-optimal policy is a proportional controller where the magnitude of the gain is computed offline, but the sign is learned, forgotten, and relearned online. The discrete-time integrator with magnitude measurements captures real-world applications such as antenna alignment, and despite its simplicity, it defies established control-design methods. For example, whether a stabilizing linear time-invariant controller exists for this system is unknown, and we conjecture that none exists.

math.OC↗
arXiv2024

Minimax Performance Limits for Multiple-Model Estimation

This article concerns the performance limits of strictly causal state estimation for linear systems with fixed, but uncertain, parameters belonging to a finite set. In particular, we provide upper and lower bounds on the smallest achievable gain from disturbances to the point-wise estimation error. The bounds rely on forward and backward Riccati recursions -- one forward recursion for each feasible model and one backward recursion for each pair of feasible models. We give simple examples where the lower and upper bounds are tight.

math.OC↗
arXiv2023

Distributed Adaptive Control for Uncertain Networks

Control of network systems with uncertain local dynamics has remained an open problem for a long time. In this paper, a distributed minimax adaptive control algorithm is proposed for such networks whose local dynamics has an uncertain parameter possibly taking finite number of values. To hedge against this uncertainty, each node in the network collects the historical data of its neighboring nodes to decide its control action along its edges by finding the parameter that best describes the observed disturbance trajectory. Our proposed distributed adaptive controller is scalable and we give both lower and upper bounds for its $\ell_{2}$ gain. Numerical simulations demonstrate that once each node has sufficiently estimated its local uncertainty, the distributed minimax adaptive controller behaves like the optimal distributed $\mathcal{H}_{\infty}$ controller in hindsight.

eess.SY↗
arXiv2022

Learning Team Decisions

In this paper, we treat linear quadratic team decision problems, where a team of agents minimizes a convex quadratic cost function over $T$ time steps subject to possibly distinct linear measurements of the state of nature. We assume that the state of nature is a Gaussian random variable and that the agents do not know the cost function nor the linear functions mapping the state of nature to their measurements. We present a gradient-descent based algorithm with an expected regret of $O(\log(T))$ for full information gradient feedback and $O(\sqrt(T))$ for bandit feedback. In the case of bandit feedback, the expected regret has an additional multiplicative term $O(d)$ where $d$ reflects the number of learned parameters.

math.OC↗
arXiv2022

On Infinite-horizon System Level Synthesis Problems

System level synthesis is a promising approach that formulates structured optimal controller synthesis problems as convex problems. This work solves the distributed linear-quadratic regulator problem under communication constraints directly in infinite-dimensional space, without the finite-impulse response relaxation common in related work. Our method can also be used to construct optimal distributed Kalman filters with limited information exchange. We combine the distributed Kalman filter with state-feedback control to perform localized LQG control with communication constraints. We provide agent-level implementation details for the resulting output-feedback state-space controller.

eess.SY↗
arXiv2022

Distributed Implementation of Minimax Adaptive Controller For Finite Set of Linear Systems

This paper deals with a distributed implementation of minimax adaptive control algorithm for networked dynamical systems modeled by a finite set of linear models. To hedge against the uncertainty arising out of finite number of possible dynamics in each node in the network, it collects only the historical data of its neighboring nodes to decide its control action along its edges. This makes our proposed distributed approach scalable. Numerical simulations demonstrate that once each node has sufficiently estimated the uncertain parameters, the distributed minimax adaptive controller behaves like the optimal distributed H-infinity controller in hindsight.

eess.SY↗
arXiv2022

Minimax Adaptive Estimation for Finite Sets of Linear Systems

For linear time-invariant systems with uncertain parameters belonging to a finite set, we present a purely deterministic approach to multiple-model estimation and propose an algorithm based on the minimax criterion using constrained quadratic programming. The estimator tends to learn the dynamics of the system, and once the uncertain parameters have been sufficiently estimated, the estimator behaves like a standard Kalman filter.

math.OC↗
arXiv2022

Learning-Enabled Robust Control with Noisy Measurements

We present a constructive approach to bounded $\ell_2$-gain adaptive control with noisy measurements for linear time-invariant scalar systems with uncertain parameters belonging to a finite set. The gain bound refers to the closed-loop system, including the learning procedure. The approach is based on forward dynamic programming to construct a finite-dimensional information state consisting of $\mathcal H_\infty$-observers paired with a recursively computed performance metric. We do not assume prior knowledge of a stabilizing controller.

math.OC↗