Human-robot interaction for extraction of robotic disassembly information

Disassembly of end-of-use products is critical to the economic feasibility of circular feedstock, reusing, recycling and remanufacturing loops. High-volume disassembly operations are constrained by disassembly complexity and product variability. The capability to buffer against timing, quantity and quality uncertainties of end-of-use products impacts the efficiency and profitability of demanufacturing systems. To achieve a competitive operation in the manufacturing life-cycle, disassembly systems need automated lines, however, the unpredictability of core supply challenges automation adaptability. Disassembly robot trajectories that are programmed manually or controlled by vision systems can be time intensive and subject to variability in lighting conditions and image recognition models. Alternatively, this paper presents a novel human-robot disassembly framework to systematically extract and generate robot trajectories derived from human-collaborative robot (cobot) disassembly. The collaborative training station proposed classifies trajectory segments and then adjusts trajectories to station-specific robots in a high-volume disassembly line. Virtual and physical collaborative disassembly case studies are presented and discussed. Results demonstrate the effectiveness of the disassembly data extraction method but indicate a disparity between the expected and ideal disassembly trajectories due to variability from human handling, which is further discussed in this paper.