Transferring Shotcrete Skills to Robots

Traditionally performed by skilled nozzle opera-tors, shotcrete remains a painful and risky task, where recurrent physical discomfort leads to severe and long-term health issues. When performed by novices or ill-trained workers, it can lead to waste. The shotcrete process guidelines advise operators on how to best maneuver the nozzle tool during spraying to reduce waste. This technique involves moving the nozzle with rhythmic circular movements while remaining at an optimal distance from the shotcrete surface. Adhering to these standards is challenging and adds to the operator's discomfort. To alleviate these issues, robotic solutions can be developed to partially or completely substitute the operator's work. This paper presents a first step towards modeling the technique employed by experienced nozzle operators and transferring them to control a robotic arm. We recorded the motion generated at the nozzle during a set of shotcrete operations by two expert nozzle operators and one novice. We analyze the pattern of motion and confirm that we model the shotcrete task and showcase its use for autonomous control of a mock-up of a shotcrete robot using expandable foam. Furthermore, we implement an intuitive shared control framework to support operators during shotcrete. The experimental results from quasi-real-world evaluations of our proposed framework on a seven-degrees-of-freedom robotic manipulator demonstrate the efficacy of our proposed control approach.