Stochastic distribution tracking control for stochastic non-linear systems via probability density function vectorisation

This paper presents a new control strategy for stochastic distribution shape tracking regarding non-Gaussian non-linear systems. The objective can be summarised as adjusting the probability density function (PDF) of system output to any given desired distribution. In order achieve this objective, PDF has first been formulated analytically, which is time-variant. Then, vectorisation implemented simplify model description. Using vector-based representation, identification and design have performed tracking. practice, evolution difficult implement in real-time, thus data-driven extension also discussed paper, where obtained using kernel estimation (KDE) with real-time data. Furthermore, stability presented analysed, validated by numerical example. As an extension, multi-output systems joint proposed algorithm, perspectives advanced controller discussed. main contribution propose: (1) sampling-based transformation reduce modelling complexity, (2) approach online implementation without pre-training, (3) feasible framework integrate existing methods.