Data-Driven Distributionally Robust Mixed-Integer Control Through Lifted Control Policy

• 成果类型: Article
• 署名作者: Ma, Xutao; Ning, Chao; Du, Wenli; Shi, Yang
• 署名单位: Shanghai Jiao Tong University; East China University of Science & Technology; University of Victoria
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2025.3558138
• 发表日期: 2025
• 页码: 6268-6275
• 关键词: uncertainty; Upper bound; training; Stochastic processes; safety; Robust control; performance analysis; measurement; Linear systems; INVENTORY CONTROL; distributionally robust control (DRC); lifted control policy (LCP); mixed-integer control; Wasserstein Metric

摘要

This article investigates the finite-horizon distributionally robust mixed-integer control (DRMIC) of uncertain linear systems. However, deriving an optimal causal feedback control policy for this DRMIC problem is computationally formidable for most ambiguity sets. To address the computational challenge, we propose a novel distributionally robust lifted control policy (DR-LCP) method to derive a high-quality approximate solution to this DRMIC problem for a rich class of Wasserstein metric-based ambiguity sets, including the Wasserstein ambiguity set and its variants. In theory, we analyze the asymptotic performance and establish a tight nonasymptotic bound of the proposed method. In numerical experiments, the proposed DR-LCP method empirically demonstrates superior performance compared with existing methods in the literature.