Optimal control planning strategies with fuzzy entropy and sensor fusion for robotic part assembly tasks

Optimal control planning techniques for a robotic part assembly, part-bringing (macro-assembly) and part insertion (micro-assembly), with a fuzzy entropy and a sensor fusion are introduced. The part-bringing task, in an environment that contains obstacles, is accomplished using a learning algorithm that coordinates with a fuzzy optimal process model for the purpose of part insertion. By connecting the learning algorithm to information obtained by fused pressure and vision systems, the assembly conditions that the part confronts can be identified. The part insertion task is accomplished using a fuzzy control that coordinates with a fuzzy optimal process model, based on measured force and moment information, to avoid jamming related to a quasi-static part insertion. Fuzzy set theory, well-suited to the management of uncertainty, is introduced to address the uncertainty problem associated with the part assembly procedure. The degree of uncertainty associated with the part assembly is used as an optimality criterion, or cost function, e.g. minimum fuzzy entropy, for a specific task execution. The proposed technique is applicable to a wide range of robotic tasks including pick and place operations, part mating with various shaped parts, and other manufacturing tasks. (C) 2002 Elsevier Science Ltd. All rights reserved.