Sun, W (2023) A self-localized smart hardhat system for construction 4.0. PhD thesis, Columbia University, USA.
Abstract
Human beings are at the rim of embracing Industry 4.0, which indicates the mass application of Artificial Intelligence (AI), Internet of Things (IoT), 5G, connected industrial robots, and big data may breed the next wave of the industrial revolution, and eventually increase human society’s productivity and happiness. Construction 4.0 is modeled after Industry 4.0, a confluence and convergence of emerging trends and technologies from the manufacturing industry in a dedicated framework designed for the Architecture\Engineering\Construction (AEC) industry. Within this framework vision, industrial prefabrication, cyber-physical systems, and digital technologies will work together toward a safer and more productive future. However, the cold facts were that in the past 20 years, the productivity in AEC industries only grew less than 20%, outpaced by the manufacturing industry (50%); as for the safety aspect, the industry mortality rate in the US kept steady in the last ten years. All facts point to the current approach to improving productivity, and safety may have enormous room to improve. Improving workplace safety and work efficiency is extremely important for the AEC industry's highly dynamic and GNSS-denial environment. However, the lack of precise indoor localization and estimation of the human sight field has impeded this process. It hinders augmented reality (AR) and prevents other emerging technologies (e.g., cyber-physical systems, digital twins). Acknowledging this void, this research customizes a novel wearable device system applying LiDAR as a key sensor and semantic 3D map as preload database to outperform current approaches in precision and range, even without any positioning infrastructures. In addition, preload map data can be generated directly from existing BIM models or future full-functional digital twin systems, reducing the cost of large-scale commercial deployment. Experimental results are presented to demonstrate the comparative efficacy of our system.
| Item Type: | Thesis (Doctoral) |
|---|---|
| Thesis advisor: | Feng, M Q |
| Uncontrolled Keywords: | artificial intelligence; manufacturing; prefabrication; safety; productivity; digital twin |
| Index terms: | augmented reality, digital twin, digital technology, workplace safety, society, manufacturing industry, big data, mortality, emerging technology, internet, prefabrication, localization, artificial intelligence, construction 4.0, industry 4.0, efficiency, wearable device, productivity, estimation, database |
| Subjects: | building construction, occupational health, communities and social development, visualization, urban planning, digital technology, innovation and technology management, digital engineering, data management, information systems, industry analysis, performance management, management, health monitoring assessment and metrics, financial and cost management, technology adoption, artificial intelligence, computing systems |
| Topics: | Quality Management, Health and Safety, Digital Applications, Research Practice, Cost Management, Business Strategy, Construction Technology, Governance, Stakeholder Management |
| Descriptive scope: | 2 PC |
N.B. Descriptive scope is a count of how many of the five facets of empirical research are indicated by the words used in title, abstract and keywords. It is not intended as a judgement on the research; merely a count of the kind of word we would expect to indicate Phenomenon, Concepts, Theoretical framing, Empirical techniques, Analytical techniques. If all five are present, then a code of “5 PCTEA” will indicate this. If you feel the coding for this record is questionable, we welcome discussion around the terms we matched or the way we categorized them. The facet you would expect may not be coded, or a facet may be coded inappropriately. This can also bear on a larger question, of which facets should be treated as defining in construction management research. Please get in touch, and we will look at it. More details here