Vision-based robotic disassembly of aircraft engines with YOLO-SAM: a novel method for task orientation estimation

Abstract

The growing demand for sustainable end-of-life management in aerospace has increased the need for robotic disassembly. This paper presents a novel pipeline for aircraft engine disassembly, operating in automatic and semi-automatic modes with state-of-the-art vision-based techniques. The key contributions are: (1) a method combining the Segment Anything Model (SAM) with YOLO for detecting removable bolts, independent of engine model and adaptable to various worn bolt types using vision-only perception; and (2) a SAM-based approach for estimating task orientation, ensuring precise tool alignment. Validated in simulations and real-world tests, the pipeline demonstrates high accuracy and adaptability for solutions in aerospace manufacturing.