Human Assisted Computer Vision on Industrial Mobile Robots

Abstract

Much research is directed at developing increasingly efficient and flexible production, and one important potential advancement is Autonomous Industrial Mobile Manipulators (AIMM’s). The idea behind AIMM’s is to have robots that have the ability to perform a wide variety of tasks, and which can easily and efficiently be reconfigured when the requirements changes. In this paper, the paradigm of skill based programming is investigated, and in particular how computer vision abilities can be integrated in this. Three applications of computer vision developed in a skill based framework are presented; namely vision pick, quality control, and fast calibration. All three are implemented on Aalborg University’s AIMM, Little Helper, and tested in a real-life industrial environment at the Danish company Grundfos A/S.