VISTA — Vision-based inspection system for automated testing of aircraft interiors: A panoramic view

Abstract

Automation is a driving force in manufacturing, enabling quality and scalability during production and assembly. In contrast with the automotive industry, civil aerospace automation has traditionally lagged. However, the adoption rate of methodologies embracing automation for manufacturing, assembly, and testing is now accelerating, with new technologies being tested to enable reliable and safe assembly and inspection steps. This paper introduces a semi-automated system for quality control during the final production steps of single-aisle aircraft, namely after the automated assembly of hatrack and sidewall elements in the passengers' area, but before any seating elements are assembled in the environment. Quality control is performed using color and 3d cameras mounted on a custom holonomic mobile robot. The acquired data is processed for identifying geometrical or surface defects by using machine learning based models and 3D processing-based algorithms. The results are provided to an inspector officer using different on-site and off-site validation modalities. The obtained results enable us to affirm that the proposed solution looks very promising for semi-automatic quality control, and it can serve as a foundational framework for efficient manufacturing in the aerospace industry. • Multi-modal assembly lining quality control, using both 3d and color imaging, for detecting geometric and surface defects. • Unified script-based automation for quality control, for navigation, manipulation, sensing, data exchange, and processing. • XR (AR & VR) presentation modes customized for both on-site and off-site validation scenarios.