No abstract

The undersigned hereby assigns to The Institute of Electrical and Electronics Engineers, Incorporated (the "IEEE") all rights under copyright that may exist in and to: (a) the Work, including any revised or expanded derivative works submitted to the IEEE by the undersigned based on the Work; and (b) any associated written or multimedia components or other enhancements accompanying the Work.

This article presents PMF-Vision, a digital assistant for manual assembly based on the concept of augmented reality information projected on the workspace. This digital assistant aims at assisting operators with mild mental deficiencies in their assembly tasks by tracking their actions in real-time. In this research, we analyzed hand tracking algorithms based on the latest deep learning techniques and highlighted the best candidate for our context in terms of accuracy and processing time. We present different interaction concepts for the system and propose to evaluate two visualisation concepts to assist the operator during component placement. The results of the exploratory study (N =6) highlighted the excellent usability of the system and the interest, expressed by the target population, to use such tools in their daily tasks.