Loading [a11y]/accessibility-menu.js
Wasserstein Distributionally Robust Regret-Optimal Control under Partial Observability | IEEE Conference Publication | IEEE Xplore

Wasserstein Distributionally Robust Regret-Optimal Control under Partial Observability


Abstract:

This paper presents a framework for Wasserstein distributionally robust (DR) regret-optimal (RO) control in the context of partially observable systems. DR-RO control con...Show More

Abstract:

This paper presents a framework for Wasserstein distributionally robust (DR) regret-optimal (RO) control in the context of partially observable systems. DR-RO control considers the regret in LQR cost between a causal and non-causal controller and aims to minimize the worst-case regret over all disturbances whose probability distribution is within a certain Wasserstein-2 ball of a nominal distribution. Our work builds upon the full-information DR-RO problem that was introduced and solved in Yan et al., 2023 [1], and extends it to handle partial observability and measurement-feedback (MF). We solve the finite horizon partially observable DR-RO and show that it reduces to a tractable semi-definite program whose size is proportional to the time horizon. Through simulations, the effectiveness and performance of the framework are demonstrated, showcasing its practical relevance to real-world control systems. The proposed approach enables robust control decisions, enhances system performance in uncertain and partially observable environments, and provides resilience against measurement noise and model discrepancies.
Date of Conference: 26-29 September 2023
Date Added to IEEE Xplore: 14 November 2023
ISBN Information:

ISSN Information:

Conference Location: Monticello, IL, USA

References

References is not available for this document.