Randomized Robotic Visual Quality Inspection with In-hand Camera

Robotic visual inspection is based on manually pre-defined postures (relation) between the camera and the object, and the robot either moves the object in front of the camera, or the in-hand camera around of the object. Either the complete object, or-in order to save time-some critical parts are checked. The path of the robot is typically always the same, determined in advance. But, in order to check only a random subset out of all possible aspects of the product, we need to generate all possible transitions between all possible aspects, and then choose the corresponding subset of motions. In this paper, we experimentally evaluate various motion planning algorithms to autonomously generate transitions between different, random inspection postures for guiding an in-hand camera with a robot in a confined space. This allows for completely random sequences of motion through predefined postures for visual quality inspection. Results show that for our use-case Transition-based RRT outperformed other available motion planners.