• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2011.05b
• /
• pp.77-79
• /
• 2011

As residents and building owners demand maintenance that is required to achieve sustainable building performance, efficient building management methods are required. Even though the demand for maintenance systems is increasing, current maintenance work for high-rise buildings mostly uses conventional ropes and gondolas that pose a high risk of accidents and exhibit poor performance and efficiency. Thus, there is an urgent need to develop an automation robot system that can reduce accidents and improve the maintenance efficiency of the conventional high-rise building façade maintenance system. As a preceding work for the development of an automation robot system, this study classified and analyzed the work processes of actual construction sites and proposed basic techniques for the work mechanisms of the robot system by investigating the motions of cleaning workers.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.11a
• /
• pp.155-156
• /
• 2022

In the process of developing an industrial robot, various simulations should be conducted to evaluate the driving, movement, and performance of the robot. Space and time constraints exist to manufacture existing robots and implement various simulations, and efficiency is reduced due to high costs. To solve this problem, many simulations can be conducted by implementing the same movement and working environment as the real environment in virtual reality using digital twin technology. This study proposes a process for establishing a digital twin model of automated layout robots. Using the digital twin model, it is expected that it will not only evaluate the hardware performance of the robot in the future, but also verify the robot's algorithms such as motion planning and work process, identify and solve potential problems in advance, and prevent problems caused by software.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.1049-1056
• /
• 2024

Human-robot collaboration (HRC) is an emerging form of work anticipated to improve construction productivity by integrating robotic capabilities with human expertise. With the expected transition towards tasks that demand more cognitive efforts for human workers, considering the cognitive status of each co-worker, such as task engagement and vigilance, can become crucial to achieve high-quality human performance during HRC, potentially contributing to a more productive HRC in construction. However, the potential cognitive changes of each co-worker have remained unclear during HRC, as studies have primarily focused on identifying general trends from aggregated cognitive responses of people, in which an individual's response can be overlooked. In this study, we examine the cognitive response of each co-worker during HRC for a construction task. We observed the cognitive responses of 18 people while they were experiencing different collaborating conditions, such as the robot's different movement speed, during a bricklaying task with an arm-type collaborative robot. For each participant, we analyzed electroencephalogram (EEG) signals to identify the changes in cognitive status by using a wearable EEG headset. The results present that the cognitive responses of almost all the participants were significantly and differently affected during HRC, impacting the estimated productivity of their human-robot teams. The findings of the study present the importance of considering each co-worker's potentially unique cognitive response as a way to achieve cognitive wellbeing while pursuing high productivity within human-robot teams, potentially contributing to overall productive HRC in construction.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2011.05a
• /
• pp.167-169
• /
• 2011

Construction Automation as a way to solve the problems of lack of skilled labor by decrease in construction population productivity and quality decrease. We are on the way to develop a construction automation system adequate for domestic circumstances in Korea; it is called RCA(Robotic-crane based Construction Automation) system. Climbing hydraulic robot system is a part of RCA system and makes Construction Factory(CF) climb next floor. The controller can control movement needs to be developed for CF safety. Synchronous control the actual field was applied to the controller logic and synchronous control of the process through which the safety has been verified. The purpose of this study that control of climbing hydraulic robot system behavior on real-time, and to improve safety for overall construction automation system through synchronous motion controller.

• International conference on construction engineering and project management
• /
• 2009.05a
• /
• pp.1088-1093
• /
• 2009

To improve construction productivity and quality, and to make the construction environment safe, a new system, Robot-based Construction Automation (RCA), is currently being developed in Korea. To determine whether RCA is an improvement over traditional construction methods (TCMs), an evaluation method, called the Performance Evaluation Index (PEI), is suggested for RCA. The PEI considers the relationships among the factors influencing the performance of the system obtained using the Delphi method and the analytic hierarchy process (AHP). As the evaluation shows, RCA is much better than TCM except for three factors: the rate of work success, quality improvement by learning experience, and construction duration.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2023.11a
• /
• pp.267-268
• /
• 2023

Unmanned patrol robots are currently being developed for autonomous data survey in construction sites. As the amount of data acquired by robots increases, it is important to utilize proper metadata and system to manage data flow. In this study, we developed three materials, metadata design, robot system and web system, in the purpose of automating construction site data survey using unmanned patrol robots. The metadata was mainly designed to represent when and where raw data was acquired. To identify the location of data acquired, localization data from SLAM algorithm was converted to suit the construction drawings. The robot system and web system were developed to generate, store and parse the raw data and metadata automatically. The materials developed in this study was adopted to Boston Dynamics SPOT, a quadruped robot. Autonomous data survey of 360-picture and environment sensor was tested in two construction sites and the robot worked as intended. As a further study, development on the autonomous data survey to improve the convenience and productivity will be continued.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.837-842
• /
• 2007

Since construction materials have been towards larger and heavier, the rate of accident associated with installation works of heavy construction materials is increasing. Installation works of heavy construction materials lead to frequent accidents, increasing the WMSDs(Work-Related Musculo-Skeletal Disorders) in construction site. In case of installation work of heavy glass ceiling, the rate of accidents such as falling and collision is increasing as well. This paper describes a ergonomic design of working platform(deck) in a glass ceiling installation robot. As well as, a design of working process is considered to accomplish an efficient installation work. As a result of the design, an installation work of heavy glass ceiling by the robot will be expected safety assurance and retrenchment of the construction cost and period.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.328-335
• /
• 2022

With the advance of robot capabilities and functionalities, construction robots assisting construction workers have been increasingly deployed on construction sites to improve safety, efficiency and productivity. For close-proximity human-robot collaboration in construction sites, robots need to be aware of the context, especially construction worker's behavior, in real-time to avoid collision with workers. To recognize human behavior, most previous studies obtained 3D human poses using a single camera or an RGB-depth (RGB-D) camera. However, single-camera detection has limitations such as occlusions, detection failure, and sensor malfunction, and an RGB-D camera may suffer from interference from lighting conditions and surface material. To address these issues, this study proposes a novel method of 3D human pose estimation by extracting 2D location of each joint from multiple images captured at the same time from different viewpoints, fusing each joint's 2D locations, and estimating the 3D joint location. For higher accuracy, the probabilistic representation is used to extract the 2D location of the joints, considering each joint location extracted from images as a noisy partial observation. Then, this study estimates the 3D human pose by fusing the probabilistic 2D joint locations to maximize the likelihood. The proposed method was evaluated in both simulation and laboratory settings, and the results demonstrated the accuracy of estimation and the feasibility in practice. This study contributes to ensuring human safety in close-proximity human-robot collaboration by providing a novel method of 3D human pose estimation.

• Journal of the Korea Institute of Building Construction
• /
• v.18 no.2
• /
• pp.161-168
• /
• 2018

Recently, a prototype of a guide rail type window cleaning robot was developed, and is currently undergoing field testing. The size and the load of the robot have not yet been optimized. In this study, a stress analysis was performed to derive quantitative data to improve the current window cleaning robot and secure its structural safety. Through the analysis of its own weight, resistance to wind speed, and other factors, it was found that the robot can be improved in terms of the drooping caused by its own weight and the drag force against wind pressure. The analysis results obtained will be directly applied to improve the design of the window cleaning robot, and it is expected that this will advance the completeness of the robot's design.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.312-318
• /
• 2022

Robot-based layout automation has been recently promoted for the purpose of improving productivity and quality. Marking robots have various functional demands to secure marking precision and environmental adaptability. In particular, in order to automate marking work of building structure, correction of the marking line through position recognition of rebars placed is required. Because the rebars must maintain a constant cover thickness from the formwork surface, if the rebars are out of planned position, the rebar or marking line need to be corrected to secure the cover thickness. Thus, the marking robot for structural work needs to have the function for determining the position correction of the rebar or the marking line. In order to judge the correction of marking line, it is required to measure the distance between the planned marking line and the rebar placed. Therefore, this study proposes an algorithm that can measure the distance between the planned line and the rebar, and correct marking line for the automatic operation of the marking robot. The results of this study will be utilized as a core function for unmanned operation of the marking robot and contribute to securing precise marking by reflecting construction errors.