Control of an industrial desktop robot using computer vision and fuzzy rules

Abstract

Desktop robots are suitable for various production line systems in industrial applications like dispensing, soldering, screw tightening, pick’n place, welding or marking. Despite their capabilities to meet diverse requirements, they have to be programmed off-line using waypoints and path information. Misalignments in the workspace location during loading cause injuries in the workpiece and tool. Further, in modern flexible industrial production, machinery must adapt to changing product demands, both to the simultaneous production of different types of workpieces and to product styles with short life cycles. In this paper, visual data processing concepts on the basis of fuzzy logic are applied to enable an industrial desktop robot to raise its flexibility and address these problems that limit the production rate of small industries. Specifically, a desktop robot performing dispensing tasks is equipped with a CCD camera. Visual information is used to autonomously change previously off-line stored robot programs for known workpieces or to call worker’s attention for unknown/misclassified workpieces. A fuzzy inference classifier based on a fuzzy grammar, is used to describe/identify workpieces. Fuzzy rules are automatically generated from features extracted from the workpiece under analysis. Regarding the evaluation of the system performance, different types of workpieces were tested and a good rate performance, higher than 90%, was achieved. The obtained results illustrate both the flexibility and robustness of the proposed solution as well as its capabilities for good classification of workpieces. The overall system is being implemented in an industrial environment.