Abstract
Using the control of robotic part assembly tasks, consisting of a macro and a micro-assembly, as an example, a systematic way, not a heuristic one, that can determine an optimal membership function and rulebase among feasible fuzzy membership functions and rulebases which can execute the part assembly tasks successfully, based on a fuzzy entropy is introduced. In a macro-assembly, a part is brought from an initial position to an assembly hole or a receptacle (target or destination) for a purpose of a part mating in a partially unstructured environment that includes unknown obstacles. Then, in a micro-assembly, the part is placed at a position that is ready to mate successfully with the target without jamming. An entropy function, which is a useful measure of the variability and the information in terms of uncertainty, is introduced to measure its overall performance of a task execution related to the part assembly tasks. Three different types of membership functions are applied to two different sets of fuzzy rulebases for a macro and a micro-assembly to show a robustness. The membership function that generates the lowest degree of uncertainty in the part assembly procedure is chosen as an optimal one. The same criterion is applied to determine an optimal fuzzy rulebase. In order to address the uncertainty associated with the part assembly procedure, a fuzzy theory, that is well-suited to the management of uncertainty, is introduced. The degree of uncertainty associated with the part assembly procedure is used as an optimality criterion, or cost function, e.g. minimum fuzzy entropy, for a specific task execution. The results show the effectiveness of the proposed approach. The proposed methodology is not only a useful tool in choosing an optimal membership function and fuzzy rulebase but applicable to a wide range of robotic tasks including controlling of mobile based robots around obstacles, and a part mating and pick and place operations.