Mixed Reality Enabled Skill Training Systems
Traditional apprenticeship programs do not provide sufficient feedback on postures and motions to inform trainees of their functional adaptation. In other fields (e.g., athletics), novices are encouraged to learn the intricacies of effective movement techniques through professional instruction. This study is to investigate how craft workers may learn and practice proper working techniques to intuitively understand how to move safely and efficiently. Analyzing motion data with AI can articulate experts' ‘physical wisdom’. With emerging technology, we might ask whether we can convey the ‘physical wisdom’ as functional learning to train apprentices. With a combination of an IMC system and mixed reality, users can observe and follow 3D computer graphic (CG) animations of experts' motion via stereoscopic displays generated from captured data. Furthermore, by combining the system with digital information from the actual workspaces, workers will be able to improve their efficiency and safety at complex and multi-scale worksites.
On-Site Ergonomic-Focused Assessment Systems
Estimating joint loads is crucial for establishing ergonomic workplace design, task-load assessment, and safety limits. Inverse dynamic analysis is used in biomechanics to predict the forces and moments developing in muscles and joints during body motions. It requires a range of experimental data, including the subject's anthropometric measurements, their motion kinematics, and the external forces applied to the body during motion. In this research, we aim to develop on-site ergonomic-focused assessment systems applying whole-body inverse dynamics with emerging sensing technologies. Specifically, we use (1) inertial motion capture (IMC) systems enabling in situ studies of human motions and (2) smart insole-imbedded wearable pressure sensors for measuring external forces. The developed systems in this project will present unprecedented opportunities for real-time assessment and feedback about workers' exposure to biomechanical risk for trainers, supervisors or managers. Furthermore, it can improve workplace ergonomics by providing insight into WMSD risks associated with job and workstation design.
Occupational Injury Prevention Using Wearable Sensors and AI
The industry is currently undergoing rapid technological improvement. Emerging wearable sensing technologies, such as IMU, EEG, EMG, and PPG, and artificial intelligence (AI) facilitate great opportunities to improve people's lives and enable entrepreneurial, livable, and safe environments. This research plan focuses on measuring and analyzing people's responses to change within their work environment using adaptive wearable sensing for interactions with users, devices, machines, and cloud infrastructure. To this end, we will include adaptive sensor-based decision-making for integrated safety management and intelligent occupational injury prevention systems. These areas analyze people's dynamic reactions to new integrated safety and risk management platforms, enabling predictive, agile, and scalable transfer and analysis of massive amounts of data in real-time.
Semi-Automated Work Systems
Variability of construction sites and tasks makes their automation prohibitively complex. Workers continue to carry out physically demanding tasks which adversely affect their health, safety, and productivity. The flexibility of semi-automated work systems, where operators work in conjunction with machines and robots, presents an attractive alternative. It is critical to estimate the anticipated effectiveness of these interventions before integrating them into current work processes. This study proposes a systematic and objective methodology to assess the value of a semi-automated work system in a construction context as it pertains to reduced exposure to musculoskeletal disorder risks and productivity improvements. The introduction of robotics and automation into a workplace may introduce new risks if ergonomics principles are not integrated into the design, work processes, and operation and maintenance requirements. This methodology has the potential for creating a proactive approach to evaluating both the health and productivity of semi-automated work systems, which would mitigate this concern.