Page - 148 - in Proceedings - OAGM & ARW Joint Workshop 2016 on "Computer Vision and Robotics“

Figure 1- collaborative screwdriver robot system Figure 2-manual polishing workplace 4.2 Machining (polishing) of continuous casting moulds (use case B) Continuous casting of profile bars requires high precision moulds with excellent surface finish. Casting moulds are crafted from flat material by wire electro discharge machining that leaves eroded surfaces without the required surface finish quality. Manual polishing (Figure 2) by air pressure driven oscillating polishing machines is extraordinary labour intensive, unergonomic and harmful to health. Prolonged exposure to hand transmitted vibration from powered processes or tools is associated with an increased occurrence of symptoms and signs of disorders in the vascular, neurological and osteoarticular systems of the upper limbs [13]. Setup and programming time is crucial for the use case since continuous casting molds are usually one of a kind products, manufactured in lot size one, with polishing being by far the most labor intensive production step causing umpteen hours of labor per mold. Therefore an assistive system, easy to program and setup, is desirable that can reduce the amount of labor especially for ergonomic and health reasons. A state-of-the-art collaborative robot system [10] [11] is equipped with a polishing tool and programmed to perform polishing operations. In the first expansion stage, the project evaluated the effectivity and simplicity of the user interface as implemented by the robot manufacturer and proposed modifications, which will inform the implementation of expansion stages 2 and 3. 5. Preliminary User Trials The first expansion stage of the two use cases was evaluated in the first year of the project. In total three user trials were conducted in order to get feedback from the workers who actually used the new robotic system. Participants were recruited by our industrial partners and we explored the teaching of the robotic arm in Trial 1 and 2 and the actual collaboration with the robot in Trial 3 (see Table 1 for an overview). All participants in Trial 1 and 2 successfully completed both teaching tasks (only one participant did not finish the second task due to time constraints). The gathered data showed that the touch panel in its off-the-shelf version was experienced as not feasible and too complex to control the robot during the teaching task for participants of both use cases. There was a strong tendency to omit the panel as an intermediate device and to try to directly control the robot using kinesthetic teaching. However, this type of control was also limited in feasibility as the robot arm was experienced as too bulky and 148