Cross-platform AR annotation for assembly-design communication in pipe outfitting

• Published in: International journal of advanced manufacturing technology 2022-08, Vol.121 (7-8), p.4981-4998
• Main Authors: Wang, Jinge, Fan, Xiumin, Zhu, Yu, Yang, Xu, Yin, Xuyue
• Format: Article
• Language: English
• Subjects: CAE) and Design; Computer-Aided Engineering (CAD; Engineering; Industrial and Production Engineering; Mechanical Engineering; Media Management; Original Article
• ISSN: 0268-3768; 1433-3015
• DOI: 10.1007/s00170-022-09637-8

Communication is an essential part of most professional activities. For complex industrial products such as ships, some design problems can only be found during the construction process. However, it is time-consuming for on-site assemblers to provide feedback on problems through traditional methods such as phone calls and photos. In recent years, adding structured visual cues through augmented reality (AR) has become an important method to assist remote collaborative tasks. However, previous studies and commercial solutions often had limited annotation types and relied on specific devices for tracking and reconstruction, which is unsatisfactory for deployment in industrial equipment and large scenes. The presented work tackles issues with feedback and collaborative decision-making of design problems in the pipe outfitting stage and proposes a cross-platform AR annotation solution on desktop computers, industrial tablets, and AR head-mounted devices (HMD). The novelty of the current work lies in a cross-functional annotation taxonomy for real-time collaboration, device-cloud integrative context awareness methods based on RGB-D sensors compatible with more devices, 2D–3D annotation mapping algorithms, and visual enhancement strategies for large scenes. A prototype system is developed and verified on a ship unit model and a physical pipe platform. The results indicate that the solution provides good performance in real-time capability and reconstruction precision, allows rapid localization of faulty parts, and creates annotations flexibly and reliably. This solution is also expected to play an active role in collaborative quality inspection and intelligent management in shipbuilding and other heavy industries.