Artificial Learning for Part Identification in Robotic Disassembly Through Automatic Rule Generation in an Ontology

Abstract

With the increasing concern for sustainable treatment of waste electrical and electronic equipment (WEEE), methods of robotic disassembly of WEEE to address various challenges of handling end-of-life products has been a trend in research. The main challenge for robotic disassembly is the uncertainties of product structures, models, and conditions. The ability of a robotic disassembly system to learn new product structures and reason about existing knowledge of product structure is vital to addressing this challenge. This paper presents an effective learning framework and demonstrates the system’s ability to learn relevant information for the disassembly of LCD monitors. The learning algorithm uses a database of previous disassembly experience of the product family and analyses it to create rules and relations between the components and disassembly concepts before expanding the generic ontology for future disassembly runs. The results show a significant increase from 11% to 87% in successful part identification of LCD monitors after being trained on past disassembly experience. The proposed method can greatly aid robotic disassembly of any product family. Note to Practitioners—Robotic systems struggle to disassemble electronic waste due to the complexity and uncertainties in end-of-life products and variations in models and parts. An artificially intelligent method is proposed to enable a robotic disassembly system to address these uncertainties. The method uses a computing technique resembling the cognitive reasoning of a human mind in the form of a map of disassembly concepts connected by relationships. Artificial learning by the robotic system occurs by collecting data from previous disassembly runs of a product, analyzing the data, and expanding the map of knowledge with new concepts and relational rules found. The approach is tested on the robotic disassembly system’s ability to identify parts of LCD monitors which possess uncertainties. An improvement from 11% of successful part identification to 87% is found, which demonstrate that learning has taken place. This approach will be implemented in a larger robotic disassembly system and tested with real robotic disassembly runs in the near future.