C. Son
Macro and micro-assembly, intelligent control planning, neuralnetwork, fuzzy coordinator, optimality criterion (fuzzy entropy),machine intelligence, vision sensor
This paper addresses problems of a mobile base robotic part assembly. The process can be broken down into two phases; macro- and micro-assemblies. For the macro-assembly task, we introduce a control planning algorithm, to lead a mobile base robot with a part from an initial position to a destination (target or exit) in a partially unknown workspace that is composed of compartments (or maze) including unknown entrances or exits for the purpose of a part mating. This is accomplished by combining a fuzzy optimal control strategy coordinating with a neural network process model. For the micro-assembly task, we employ a neural network control strategy coordinating with a fuzzy optimal process model, to insert a part into an assembly hole or a receptacle without jamming during the part mating. In both the macro- and the micro-assembly tasks, a fuzzy set theory, well suited to the management of uncertainty, is introduced to address the uncertainty associated with the part assembly procedures. An entropy function, specifically a fuzzy entropy, is introduced to measure its overall performance of task executions related to part assembly tasks, because it is a useful tool to measure the variability and the information in terms of uncertainty. A degree of uncertainty associated with the part assembly is used as an optimality criterion, or cost function, for example minimum fuzzy entropy, for a specific task execution. The algorithms utilize knowledge processing functions such as machine reasoning, planning, inferencing, learning, and decision-making. The results show the effectiveness of the proposed approaches. The proposed techniques are applicable to a wide range of mobile robotic tasks, including pick-and-place operations, maneuvering around a workspace, manufacturing, or part mating tasks.
Important Links:
Go Back
