Iterative learning control (ILC) is a well-established methodology which has proved successful in achieving accurate tracking control for repeated tasks. However, the majority of ILC algorithms require a nominal plant model and are sensitive to modelling mismatch. This paper focuses on the class of gradient-based ILC algorithms and proposes a data-driven ILC implementation applicable to a general class of nonlinear systems, in which an explicit model of the plant dynamics is not required. The update of the control signal is generated by an additional experiment executed between ILC trials. The framework is further extended by allowing only specific reference points to be tracked, thereby enabling faster convergence. Necessary convergence conditions and corresponding convergence rates for both approaches are derived theoretically. The proposed data-driven approaches are demonstrated through application to a stroke rehabilitation problem requiring accurate control of nonlinear artificially stimulated muscle dynamics.

迭代学习控制（ILC）是一种行之有效的方法，已证明成功地实现了对重复任务的精确跟踪控制。但是，大多数ILC算法都需要标称工厂模型，并且对建模不匹配敏感。本文重点介绍基于梯度的ILC算法，并提出一种适用于一般非线性系统的数据驱动ILC实现，其中不需要显式的植物动力学模型。控制信号的更新是通过在ILC试验之间执行的附加实验生成的。通过仅跟踪特定参考点来进一步扩展该框架，从而实现更快的收敛。从理论上推导了两种方法的必要收敛条件和相应的收敛速度。