Learning-Based Adaptive Optimal Control of Linear Time-Delay Systems: A Policy Iteration Approach

• 成果类型: Article
• 署名作者: Cui, Leilei; Pang, Bo; Jiang, Zhong-Ping
• 署名单位: New York University; New York University Tandon School of Engineering
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2023.3273786
• 发表日期: 2024
• 页码: 629-636
• 关键词: Optimal control; Aerospace electronics; mathematical models; Heuristic algorithms; DELAYS; trajectory; Stability criteria; Adaptive dynamic programming (ADP); linear time-delay systems; optimal control; policy iteration (PI)

摘要

This article studies the adaptive optimal control problem for a class of linear time-delay systems described by delay differential equations. A crucial strategy is to take advantage of recent developments in reinforcement learning and adaptive dynamic programming and develop novel methods to learn adaptive optimal controllers from finite samples of input and state data. In this article, the data-driven policy iteration (PI) is proposed to solve the infinite-dimensional algebraic Riccati equation iteratively in the absence of exact model knowledge. Interestingly, the proposed recursive PI algorithm is new in the present context of continuous-time time-delay systems, even when the model knowledge is assumed known. The efficacy of the proposed learning-based control methods is validated by means of practical applications arising from metal cutting and autonomous driving.