Motion Data Based Construction Worker Training Support Tool: Case Study of Masonry Work

Construction work involves a number of repetitive and physically demanding tasks. Exposure to these labor intensive tasks with awkward postures result in an increase in biomechanical risk factors that may lead to work-related musculoskeletal disorders (WMSDs). Thus, it is essential to provide training for apprentice-level workers to adopt safe working postures. Recent advancements in sensing technologies have enabled us to automatically collect body motion data and analyze posture. The present work presents an automated posture assessment method using inertial measurement units (IMUs) allowing for in-depth ergonomic analysis via kinematic data. A case study on masonry work was performed and body motion data from masons with varying experience levels were collected. For the posture analysis, we first investigated the risk of working posture between experience groups using observation-based posture assessment methods (RULA and REBA), then compared the assessment scores between experience groups. Finally, a prototype training tool based on working posture was introduced. The experimental results show that the automated collection and analysis of motion data can provide greater understanding of working postures adopted by workers with different experience levels with the potential to be used as a training tool in apprenticeship programs.