Teachless teach-repeat: Toward vision-based programming of industrial robots

摘要

Modern programming of industrial robots is often based on the teach-repeat paradigm: a human operator places the robot in many key positions, for teaching its task. Then the robot can repeat a path defined by these key positions. This paper proposes a vision-based approach for the automation of the teach stage. The approach relies on a constant auto-calibration of the system. Therefore, the only requirement is a precise geometrical description of the part to process. The realism of the approach is demonstrated through the emulation of a glue application process with an industrial robot. Results in terms of precision are very promising.