Using Real-time Feedback in a Training System for Manual Procedures

Abstract

Human workers remain a crucial part of production environments for conducting manual assembly or maintenance procedures, despite increasing automation. These procedures cannot be automated due to small lot sizes and high product variability. Performing manual procedures requires the application of procedural knowledge and motor skills, such as bimanual coordination and complex hand movements. Many training systems for manual procedures have been proposed. However, these systems focus on declarative knowledge about the sequence of work steps. The inherent haptic characteristics and sense for correct tool and component application gets lost. This paper proposes a training system that introduces haptic components for the training of assembly procedures. The proposed training system instructs the user in mounting two physical components by employing haptic and visual interaction. Augmentations and real-time feedback assist the user during the training and enable the assessment of applying accurate torque on screw connections. An evaluation compared the training system against video-based instructions and indicated advantages for the proposed system in terms of objective measures (time on task, precision) and in terms of subjective measures such as usability.