The invention discloses an intelligent anti-interference control method for a saturated
nonlinear system, and belongs to the technical field of robots. The method includes: taking an uncertain
nonlinear system as a
research object, and taking an instruction of which the output can accurately track expectation under the common influence of
coupling uncertain factors such as saturated nonlinearity, nonlinear dynamic, external interference and the like as a control target, performing
estimation and feed-forward compensation on non-matching and matching unknown nonlinear dynamic states through a
radial basis function neural network; performing
estimation and feed-forward compensation on non-matching external interference and matching external interference through an extended
state observer; aiming at the influence of'differential explosion 'existing in the controller, performing optimization through a control strategy based on instruction filtering
backstepping; and aiming at the influence of saturation and filtering errors, performing real-time compensation through an
auxiliary system based on the saturation and filtering errors. According to the method, it can be guaranteed that
system output can accurately track expected instructions, the influence of differential explosion is avoided, and application in complex working conditions is better facilitated.