Abstract: The complexity of robotic path planning problems in industrial manufacturing increases significantly with the current trends of product individualization and flexible production systems. In many industrial processes, a robotic tool has to follow a desired manufacturing path most accurately, while certain deviations, also called process tolerances and process windows, are allowed. In this work, a path planning framework is proposed, which systematically incorporates all process degrees of freedom (DoF), tolerances and redundant DoF of the considered manufacturing process as well as collision avoidance. According to the specified process properties, the objective function terms as well as the hard and soft constraints of an optimization problem can be easily parametrized to find the optimal joint space path. By providing the analytical gradients of the objective function and the constraints and utilizing modern multi-core CPUs, the computation performance can be significantly improved. The proposed path planning framework is demonstrated for an experimental drawing process and a simulated spraying process. The planner is able to solve complex planning tasks of continuous manufacturing paths by systematically exploiting process properties and allowing to move through singular robot configurations, which cannot be performed with state-of-the-art concepts.
Paper: T. Weingartshofer, B. Bischof, M. Meiringer, C. Hartl-Nesic, and A. Kugi, “Optimization-based path planning framework for industrial manufacturing processes with complex continuous paths”, Robotics and Computer-Integrated Manufacturing, vol. 82, no. 102516, 2023. https://doi.org/10.1016/j.rcim.2022.102516