Parallel robots have complicated structures as well as complex dynamic and kinematic equations, render-ing model-based control approaches as ineffective due to their high computational cost and low accuracy.Here, we propose a model-free dynamic-growing control architecture for parallel robots that combinesthe merits of self-organizing systems with those of interval type-2 fuzzy neural systems. The proposedapproach is then applied experimentally to position control of a 3-PSP (Prismatic–Spherical–Prismatic)parallel robot. The proposed rule-base construction is different from most conventional self-organizingapproaches by omitting the node pruning process while adding nodes more conservatively. This helpspreserve valuable historical rules for when they are needed. The use of interval type-2 fuzzy logic struc-ture also better enables coping with uncertainties in parameters, dynamics of the robot model anduncertainties in rule space. Finally, the adaptation structure allows learning and further adapts the rulebase to changing environment. Multiple simulation and experimental studies confirm that the proposedapproach leads to fewer rules, lower computational cost and higher accuracy when compared with twocompeting type-1 and type-2 fuzzy neural controllers.

Keywords