Automatic close-optimal workpiece positioning for robotic manufacturing

Robot programming is still an expert dependent and not automatically optimized task. In order to make this process more automatic and intuitive for the end-user, this paper presents a novel approach to determine a close-optimal workpiece pose for different robotic manufacturing processes like welding and milling. The approach is based on a model-based interpretation of the Product, Process, and Resource (PPR) components defined in an internally developed Computer-Aided Manufacturing (CAM) software. After the interpretation addressed to simplify the path planning, an algorithm uses sample-based motion planning techniques and optimization algorithms, in order to find optimal motions in reaction to infeasible states of the robot (i.e. maximum joint limits and reachability) and a close-optimal workpiece pose. The optimized path planning is achieved by exploring an interpreted Configuration Space (C-space) using a Degree of Freedom (DoF) of the Robot Manufacturing Processes (RMP) and by interpreting its constraints. Simulation results are presented for robotic welding and milling task by optimizing welding orientations and robot stiffness respectively in the path planning and the joint movements and gravity cost criteria in the workpiece positioning. Optimization of these criteria could be used in RMP to address improvement of the process quality.