PFI-TT: Smart pose and position guidance system for construction workers' safety and productivity

Georgia Tech Research Corporation, Atlanta GA

Investigators

Abstract

The broader impact/commercial potential of this Partnerships for Innovation - Technology Translation (PFI-TT) project is to improve worker safety and productivity in dynamic construction job sites by enabling commercialization of a wireless pose and position guidance system. If successful, this project is expected to radically change job hazard safety management for the $1.2 trillion U.S. construction industry in which approximately three to four workers die every working day. The proposed technology is expected to help owners, contractors, and construction managers to make better and safer decisions for dynamic construction work. In addition, this study can provide valuable data regarding the safety condition of workers, which benefits the individuals' health as well as safety management and society in general. The collected data will preserve safety knowledge within the company and help knowledge transfer from experienced professionals to new generations. The research project will also provide an opportunity to engage underrepresented students from diverse socio-economic backgrounds to learn about the challenging engineering problems in the construction industry and equip them with scientific knowledge to address those problems. The proposed project aims to provide a holistic solution for intelligently monitoring individual workers' exposure to hazards and unsafe postures. For a system to be feasible as well as practically acceptable in construction which has dynamic and transient work environmental characteristics, the system needs to satisfy many factors: cost, ease of use, scalability, real-time ability, network connectivity, form factor, system deployment, accuracy, reliability, and privacy. While satisfying the factors, a Building Information Model (BIM)-driven Internet of Things (IoT) application will be used as a central platform for user interface and sensor tracking algorithms in the proposed PFI project. In particular, when the construction work schedules are set and incorporated into BIM, daily and weekly work activity information is extracted. These data can serve to automatically or semi-automatically identify potential hazards in advance based on construction progress. In addition to the location-based safety risks, postural working conditions of the workers are monitored through a motion recognition function using machine learning algorithms. The monitored and quantified information can provide valuable data regarding the safety condition of workers, empower our knowledge about each worker's health and safety-related behavior in a quantitative manner, and thus deliver an objective, comprehensive safety reinforcing system to a job site. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.