ROS-driven Disassembly Planning Framework incorporating Screw Detection

Abstract

The automation of electronic waste disassembly processes is very challenging due to the diversity and conditions of the products, but also due to the heterogeneous disassembly environments based on different hardware and software components. All these resources and the subjacent information flows should be coordinated and integrated to ensure an effective disassembly process. In this paper, we present a developed architecture for closed-loop planning and controlling dynamic disassembly processes of robots. We extended the infrastructure provided by the Robot Operating System (ROS) to integrate the components of the robotic system with its vision system and the software components for inference, replanning, and knowledge transfer. The architecture was implemented for a real use case of antenna amplifier disassembly. The implemented framework is generalizable for other purposes implementing four automatic configuration mechanisms to support domain-specific tailoring: code generation, object serialization, object mapping, and object-triple mapping.