Assessing industrial end-user programming of robotic production cells: A controlled experiment

Adapting the behavior of robots and their interaction with other machines on the shop floor is typically accomplished by non-programmers. Often these non-programmers use visual languages to specify the robot’s and/or machine’s control logic. While visual languages are explored as a means to enable novices to program, there is little understanding of what problems novices face when tasked with realistic adaptation programming tasks on the shop floor. In this paper, we report the results of a controlled experiment where domain experts in the injection molding industry inspected and changed realistic programs involving a robot, injection molding machine, and additional external machines. We found that participants were comparably quick to understand the program behavior with a familiar sequential function chart-based language and a Blockly-based language used for the first time. We also observed that these non-programmers had difficulty in multiple aspects independent of language due to the interweaving of physical and software-centric interaction between robot and machine. We conclude that assistance needs to go beyond optimizing available language elements to include suggesting relevant programming elements and their sequence.