Anthropocentric Robot Collaboration in Construction
Labor-intensive construction accounts for a significant portion of the U.S. economy. However, construction suffers from significant occupational injuries/deaths, stagnant productivity, lack of skilled laborers, and an aging workforce. To address these issues, the construction industry is gradually gearing up for robotic automation, particularly for human-robot collaboration. While many research and development efforts to date have been focusing on improving the functionality and capability of robots, fundamental questions in human-robot collaboration in construction remain unanswered: How can a robot work with a human worker and build and maintain his/her trust? What are the best strategies to design future construction work environments for human-robot collaboration? How can the construction industry retrain existing workers and attract new ones in this new working environment? To answer these questions, we propose anthropocentric robot collaboration in construction. In essence, we make human-robot collaboration human-centric to better understand how he/she responds to co-work with construction robots. We aim to learn his/her response to different scenarios of human-robot collaboration in construction, which will be used to maximize the overall performance of human-robot collaboration Further, such learning can provide a firm foundation to answer the aforementioned fundamental questions on future construction work environment and how we can prepare for existing and new workforce.
Safe Human Robot Collaboration in Construction
The construction industry has the highest number of fatalities and injuries due to hazardous working conditions. The introduction of robots on construction sites has the potential to relieve human workers from dangerous and repetitive tasks by making machines intelligent and autonomous. However, robotic solutions for construction face significant challenges. Construction robots must be highly mobile and collaborative, and must be able to adapt to their unstructured and dynamic surroundings. Robotic scene understanding is thus a critical concern for human workers, who will not accept co-robots that do not project complete safety and trust in environments where the consequences of failure could be disastrous. In this research, automated monitoring and intervention through computer vision is pursued to provide a means to dramatically improve the perception of construction safety in the presence of co-robots. The new methods developed in this project have the potential to impact computer vision, machine learning, and effective human-robot collaboration in unstructured environments, while significantly contributing to safety.
On-site Marker-less Motion Capture and Activity Analysis
Due to dynamic and uncluttered construction site conditions, manual observation methods to monitor and evaluate workers’ performances (e.g., productivity, safety and ergonomics) are time-consuming, subjective and error-prone. This research proposes a computer vision-based approach, which can automatically capture workers’ motions (e.g., skeletons) without interfering with their on-going work (e.g., no need to attach sensors to human body). Because human motion capture is a cornerstone for various forms of automated activity analysis such as ergonomic risk assessment, unsafe behavior monitoring and productivity analysis, a major effort is concentrated on developing an accurate and fast motion capture method to enable on-site monitoring. We are particularly interested in a mobile app so that anybody can do a motion capture with his/her smartphone.
Wearable Biosensors-based Measurement of Workers’ Physical and Mental Status
Construction is known as one of the most stressful occupations due to its physically and psychologically demanding tasks performed in a hazardous work environment. The objective of this research is to develop advanced signal processing and machine learning algorithms to acquire construction workers’ quality physiological signals at real sites as well as to infer their physical and mental status applying off-the-shelf wearable sensors. This study also investigates the distinguishing power of different biosignals — electroencephalogram (EEG), Electromyography (EMG), electrodermal (EDA), skin temperature (ST), and photoplethysmogram (PPG) — in detecting workers’ physical and mental states without interfering with workers’ ongoing work. This research contributes to an in-depth understanding of how workers experience occupational stress in hazardous environments analyzing unprecedented data, non-invasively collecting workers’ physiological signals.
Potential of Wearable Technologies to Measure Fall Risk, Fatigue, and Heat Stress for Preventive Jobsite Safety
Wearable sensors such as wearable biosensors and inertial measurement units (IMU) can greatly improve construction workers’ safety and health by monitoring their physical and cognitive status during ongoing work. However, most of their applications have focused on reaction to accidents, not prevention. To address this issue, this project will explore how wearable sensors can be applied along with recent machine learning, signal processing techniques, and psychophysiological theories to identify important risks of construction workers (e.g., fall risk, physical fatigue, and heat stress), thereby preventing potential accidents. The outcome of this project will contribute to construction sites’ preventive safety by empowering proactive interventions that alleviate risks before accidents actually happen.
Social Influence in Temporary Organizations
Due to the complexity and dynamicity of construction projects, project participants are frequently asked to make improvised decisions and behaviors, which have a significant impact on project performance. In such uncertain situations, social influence plays an important role in decision-making and behaviors. However, the unique characteristics of the temporary organization in construction projects (e.g., multiple organizational memberships, pre-defined limited duration, and task-oriented relationship) make the social influence process more complex and difficult to apply. In this study, we investigate how the unique features of the temporary organization affect social influence processes and ultimately project participants’ behaviors. To do this, we employ various quantitative methods such as traditional surveys and statistical analyses, behavioral economic experiments, computer simulations of organizational behavior, and field experiments. We have been exploring several important behaviors related to construction projects such as workers’ safety behavior, organizational identification, absence, and lateness as well as managers’ interface management behaviors.
Non-Invasive Personalized Normative Messaging Intervention for the Reduction of Household Energy Consumption
Household fossil fuel consumption in the U.S. is responsible for approximately 22% of primary energy consumption and CO2 equivalent emissions (1,184 million metric tons annually). Despite significant contributions to carbon emissions, buildings are often operated inefficiently, with between one third and half of all energy consumed while unoccupied. Even in identical buildings, differences in occupant behavior can significantly impact energy consumption. As such, it is imperative to identify widely applicable intervention methods capable of promoting environmentally responsible behaviors. The goal of this research is to advance our understanding of how personalized normative comparison groups influence the effectiveness of normative feedback interventions through the development and validation of a non-invasive data mining–based behavior intervention framework based on households’ hourly energy consumption data. Successful implementation of the proposed research will significantly contribute to reducing harmful emissions from the built environment through the enhancement of pro-environmental feedback intervention design by providing a detailed first look into personalized normative feedback.
Wearable Biosensor-based Urban Sensing to Facilitate the Disabled and Older Adults’ Mobility in the Built Environment
As disabled and older population continues to increase, their mobility issue becomes more closely related to our social prosperity. Despite such importance, the disabled and older adults’ mobility is limited by stress resulting from their stressful interactions with diverse barriers in the current built environment, including steep stairs, cracked sidewalks, and complex traffic signage. As such, an understanding of the stressful interactions between frail individuals and the built environment is critical to improve the built environment for their intact mobility. This project aims to develop a new urban sensing method that efficiently monitors frail individuals’ stressful interactions with the built environment by applying wearable biosensing, signal processing, pattern recognition algorithms, and a geographical information system. The developed urban sensing method will be a basis of diverse interventions (e.g., stress-free routing and community redesign) that alleviate disabled and older individuals’ stress in daily trips, thereby facilitating their mobility.
Digital Twin for Robotic Construction
We collaborate with UM researchers who create high-quality damage-tolerant sensor embedded bricks, known as Engineered Cementitious Concrete (ECC) bricks. These ECC bricks are designed and 3D printed in plants and transported to construction sites, which can be assembled into facilities/infrastructure with robots. At the end of life of the facility/infrastructure, these bricks will be disassembled robotically and will be moved to another construction site or reconfigured in the plant to be used for other facility/infrastructure. We aim to create a digital twin for manufacturing, logistics, and construction as a backbone framework to automatically control this process. Given that these ECC bricks can be aware of their status with sensors, a novel digital replica of a life cycle of this new construction will greatly contribute to such robotic construction.
Blockchain-based Smart Project Delivery and Value Generation for Infrastructure Finance
The construction industry has made a significant effort to digitize the building and occupant data generated during a whole life cycle of a project (e.g., design, prefabrication, construction, operation, maintenance, and demolition phases). The digitized data helps not only to facilitate efficient management of building, but also to improve collaboration between a construction project’s participants. It is, however, difficult to continuously and efficiently collect, validate and update building information, mainly due to fragmentation in the construction industry. To address this issue, we propose a blockchain-based smart project delivery by leveraging BIM and IoTs with decentralized, shared, and immutable data exchange. Particularly, we are interested in creating and transferring value generated from such data. This value is expected to create a new business opportunity to fund new construction, while also facilitating the rehabilitation of existing infrastructure to improve our quality of life.
Below are several examples of past research projects. These are a basis for the above current research, and DPM is also active in extending these past projects. Their results can be found in Publications.
- IMU-based Heavy Equipment Cycle and Productivity Measurement
- Durability and Effect of Social Networks in Behavior Interventions in Residential Energy Consumption
- Quantification and Mitigation of Environmental Impact from Construction Processes
- Virtual Prototyping of Human-Robot Collaboration in Unstructured Construction Environments
- Automatic Behavior Monitoring for In-depth Analysis of Construction Fatalities and Injuries
- Disaster Preparedness and Response System for Facility Management Using a Distributed and Open Simulation Platform
- Interface Management
- Cross-level Feedback between Individual Absence Behavior and Absence Culture in the Construction Industry
- Synthetic Environment for Steel Construction
- Hybrid System Dynamics and Discrete Event Simulation for Large-scale Construction Management
- Quality and Change Management in Large-scale Construction Projects