Autonomous Robot-Enabled Data Collection, Classification, and Processing Method for Real-Time Construction Schedule Updating
Loading...
Author(s)
Maqsoodi, Aras
Advisor(s)
Editor(s)
Collections
Supplementary to:
Permanent Link
Abstract
Despite significant advancements in the manufacturing sector, the construction industry has been lagging in adopting computer-aided and robotic technologies. This has resulted in inefficient and unproductive construction procedures not being fully addressed. Construction progress tracking is an essential part of project management and keeps the project’s shareholders updated and confident about finishing the project on time within the specified budget and quality. Monitoring, data collection, and updating the schedule are some of project management's most time-consuming and labor-intensive tasks.
Modern technologies such as robots and computer vision present a potential solution to this issue. Although previous research enhanced data collection and data processing separately, a considerable amount of manual effort is needed to classify and transform collected data to the processing stages. This research presents a novel framework to address the gap, utilizing autonomous four-legged robots to capture images from indoor building construction, classify data for creating quantified material lists, generate as-built models, and compare them with original models to enable real-time construction schedules updates.
The proposed method offers a streamlined, optimized, and productive inspection and data collection approach, potentially reducing time and labor requirements. By providing decision-makers with live updates, construction project managers may reduce overruns, meet deadlines, and reach the project’s ultimate goals. The study highlights the technical details of the proposed procedure, discusses the potential benefits of adopting quadrupeds in the construction industry, and presents a direction for future research and development in this area.
Sponsor
Date
2023-11-20
Extent
Resource Type
Text
Resource Subtype
Thesis