Smooth trajectory tracking of three-link robot: a self-organizingCMAC approach

摘要

A neuro fuzzy system which is embedded in the conventional controlntheory is proposed to tackle physical learning control problems. Thencontrol scheme is composed of two elements. The first element, the fuzzynsliding mode controller (FSMC), is used to drive the state variables tona specific switching hyperplane or a desired trajectory. The second onenis developed based on the concept of the self organizing fuzzyncerebellar model articulation controller (FCMAC) and adaptive heuristicncritic (AHC). Both compose a forward compensator to reduce thenchattering effect or cancel the influence of system uncertainties. Angeometrical explanation on how the FCMAC algorithm works is provided andnsome refined procedures of the AHC are presented as well. Simulations onnsmooth motion of a three-link robot is given to illustrate thenperformance and applicability of the proposed control scheme