发表机构
Lund University; ETH AI Center, ETH Zürich; University of Pennsylvania(隆德大学; 苏黎世联邦理工学院人工智能中心; 宾夕法尼亚大学)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
本文提出利用Frank-Wolfe方法求解有限时域线性动力系统的最优输入设计问题,通过将子问题转化为LQ问题求解,并证明目标值O(1/M)和迭代点O(1/√M)的收敛速率,同时扩展到系统辨识和自适应LQR。
AI 中文摘要
我们研究有限时域内线性动力系统的最优输入设计问题。目标是在能量预算约束下最小化加权逆协方差(信息)准则。由因果策略可实现的协方差集合是凸的,但缺乏易处理的显式描述,这排除了基于投影的方法。我们证明Frank-Wolfe方法自然适用:每个线性最小化子问题是一个受预算约束的有限时域线性二次(LQ)问题,可通过Riccati递归和关于拉格朗日乘子的一维二分法求解。利用目标函数在可行集上的光滑性,我们建立了目标值的$\mathcal{O}(1/M)$收敛速率,而强凸性则产生迭代点的$\mathcal{O}(1/\sqrt{M})$速率。我们进一步将该框架扩展到未知动力学系统辨识的输入设计以及自适应在线LQR,并通过数值实验说明了该方法。
英文摘要
We study optimal input design over a finite horizon for linear dynamical systems. The goal is to minimize a weighted inverse-covariance (information) criterion subject to an energy budget. The set of covariances achievable by causal policies is convex but lacks a tractable explicit description, ruling out projection-based methods. We show that Frank--Wolfe applies naturally: each linear minimization subproblem is a budget-constrained finite-horizon linear quadratic (LQ) problem, solvable by a Riccati recursion and one-dimensional bisection over a Lagrange multiplier. Using smoothness of the objective over the feasible set, we establish an $\mathcal{O}(1/M)$ convergence rate for the objective value, while strong convexity yields an $\mathcal{O}(1/\sqrt{M})$ rate for the iterates. We further extend the framework to input design for system identification with unknown dynamics and adaptive online LQR, and illustrate the approach numerically.
Comments7 pages, 4 figures