Robotic Framework for Autonomous Assembly: a Report from the Robothon 2021 Grand Challenge

Abstract

Up to now, many repetitive industrial processes, like welding in automotive, have been automated. However, robust solutions for assembly operations that, besides precise robot positioning, also require precise tactile interaction are not available yet. The current research efforts on sensitive collaborative robots and their control are a promising step towards assembly automation. In our contribution we present an autonomous robotic framework to automate assembly tasks. It implements state-of-the-art algorithms for object localization, motion planning, force control, error handling and task scheduling. We present the implementation details of our localization and insertion skills on a FRANKA EMIKA robot and an Intel RealSense, the two main components of the framework. Further, we introduce the Robothon Grand Challenge, a new biennial competition series that deals with automated electronic waste decomposition. Within that competition, our framework made the fifth place out of nine teams.