Improvements in Robot Teaching for Handling Operations in Production Environments

This work describes three technical improvements to the Handling Assistant, a collaborative robot for handling and commissioning, concerning the depth of information the robot can extract from the teaching process. The teaching process involves an unskilled worker setting up the robots movements and actions through hand guiding to instruct the robot to perform a given task. Improvement potentials in picking up, placing down and optimizing the demonstrated path are identified and technical solutions to these areas are presented. The task of picking up the part is improved through the use of null space motion of the robot and exploiting part symmetry. The task of placing down parts is improved through increasing precision by using data collected during the demonstration. Finally the path of the robot is optimized using automated reinforcement learning by applying reward-weighted averaging. The developed methods are implemented and validated on a test case using a Handling Assistant which consists of a KUKA LBR iiwa robot and collaborative gripper, which is tasked to handle parts from a box onto a material carrier.