Coarse Geometry acquisition of welding parts using a novel cheap depth sensor

Abstract:
We present a human-robot-cooperation welding system, consisting of several phases including a coarse acquisition of the work piece geometry, interactive fine-scanning of welding seam regions and automated optimizing path planning after task specification by the user. The coarse geometry acquisition component is explained in detail showing the feasible application of a novel and cheap 3D-Sensor (MS KINECT) in this domain. The evaluation shows promising and sufficient results for planning the acquisition of high-resolution fine scans using a standard laser scanner and the use of an automated path planning component. The path planning is based on a bidirectional RRT planner followed by a path optimization. The system thus enables the human coworker to specify a welding task for unknown geometries fast to the machine and relieves him from the tedious robot movement planning during the actual welding phase.