In this vision for the future, robots would do physically strenuous tasks such as lifting bricks or moving sheets of drywall, for example, while humans could figure out the best way to do a particular task or make adjustments when the built structure needs to deviate from the original plan.
Construction is a $10 trillion industry that globally employs 180 million workers. In the US, construction jobs have historically provided sustainable income to support a middle-class lifestyle. However, future construction work is confronted by two critical problems. First, growth in productivity of construction work has been practically stagnant relative to other industries that have seen productivity grow by as much as 1500% since 1945. Experts agree that the industry “seems to be stuck in a time warp” and is not able to adopt innovations that affect workplace efficiency. Second, it has been difficult to offset the aging and retiring workforce by younger workers or individuals of different abilities, causing the supply of skilled workers to significantly fall short of the rising demand from increased infrastructure spending. One key reason for this is that construction work tends to be repetitive and strenuous leading to occupational hazards that sometimes force workers to retire at an early age.
There has been significant interest in automation and robotics as potential solutions to transform future construction work. However, adopting such solutions is not straightforward. There is a significant lack of understanding related to the social and economic implications of introducing robots on the prospects of future workers, the morphosis of the work environment, and the evolution of the construction industry itself. On one hand, today’s construction robots are technically incapable of autonomously performing much useful construction work. On the other hand, the pursuit of such capabilities in isolation raises concern about automation replacing a large segment of the workforce, while affecting the nature and quality of the work itself in undesired ways (e.g., lack of architectural detail resulting from modularization). More importantly, successful adoption of these technologies in construction can only be achieved through transformative educational programs and professional development opportunities that support construction worker aspirations and provide opportunities for upskilling and lifelong learning.
This project hypothesizes that human workers can benefit from working with a robot assistant (RA) where the human carries out the planning tasks and supervises the RA to perform quasi-repetitive construction tasks that require physical exertion. For such a symbiotic human-robot collaboration to benefit a construction worker and at the same time result in wide deployment in future construction work, the human workers will need to be educated and equipped to use interactive task learning and collaborative interfaces to teach RA work-related knowledge and at-work improvisation. This envisioned approach parallels the classical Master-Apprentice vocational model prevalent in today’s construction industry, wherein novice workers develop their skills by completing apprenticeships under the tutelage of skilled workers and exposure to different work conditions on multiple projects. The skills that human workers need to develop will however look different. They will still learn the basic construction means and methods but will also need to be trained in using interactive task learning methods to facilitate interaction with their RA. The RA, on the other hand, cannot be preprogrammed with construction tasks due to the uniqueness of each construction project and its circumstances resulting in differences not only between projects but even deviations between as built and as designed installations. Thus, we propose to develop and test technologies that the human workers can use to naturalistically interact with their RA and teach them to perform tasks specific to the project at hand. The RA over time become intelligent and can proceed to execute some pre-learned tasks but will continuously require human input as unencountered situations arise in new projects.
The pursuit of this vision will enable future construction workers to transition their role to perform high-level planning, sequencing, and improvisation tasks as they collaborate with their RA who will do the physical work. This transition will be achieved through innovation in the construction vocational curriculum, where, in addition to learning the fundamentals of construction work, human workers will learn and use new methods to interact with the RA that they will teach and supervise. These new skills will enable workers to advance their work roles, encourage upward mobility in the profession, and open avenues for people of diverse abilities to be productive members of the construction workforce, a prospect that is impossible today.
National Science Foundation
Using wearable-based technology to help seniors stay mobile and age in place, while avoiding exposure to falls and environmental risks or hazards.
Using remote sensing and security camera data to better understand how people are using the Detroit RiverFront Conservancy public spaces.
Structural monitoring of highway retaining walls using remote sensing techniques to assess performance and prioritize infrastructure investments.
Application of real-time sensing and dynamic control on existing wastewater infrastructure to reduce the frequency and volume of Combined Sewer Overflows.
A major source of bridge deterioration requiring constant maintenance is mechanical expansion joints installed between adjacent simple span bridge decks.
Mapping detailed geographies of digital access and exclusion across Detroit’s neighborhoods.
The Great Lakes Water Authority is looking for ways to rehabilitate large diameter water mains without actually having to dig up city streets.
The University of Michigan is developing a structural reliability framework to quantify the probability of failure of pipe segments throughout the GLWA system.
The goal of this project is to develop a data-driven asset management framework that quantifies risk in the water distribution network for southeast Michigan.
The city of Benton Harbor wishes to transform Ox Creek into a residential, recreational and commercial centerpiece linking important segments of the community.
While parks are designed and managed to generate community benefits, there remains a need for tools that can more rigorously measure how communities use parks.
Collecting travel data to help Benton Harbor improve travel options for residents, with the goal of increased employment participation and retention.
The first in a series of health clinic prototypes that bring technology-enabled chronic health care monitoring to remote, underserved global populations.
Rethinking how transit infrastructure can expand access to food, health, learning, and mobility services by creating multimodal hubs.
A grassroots train-the-trainer program on how to install, operate and maintain faucet-mounted point-of-use filters to protect for lead in drinking water.
The Sensors in a Shoebox project focuses on empowering Detroit youth as agents of change for their city.
The project aims to reduce energy use of vehicular travels by incentivizing individual travelers to adjust travel choices and driving behaviors.
Associate Professor and John L. Tishman Faculty Scholar in the Department of Civil and Environmental Engineering
Carol C. Menassa is an Associate Professor and John L. Tishman Faculty Scholar in the Department of Civil and Environmental Engineering at the University of Michigan (U-M). Carol directs the Intelligent and Sustainable Civil Infrastructure Systems Laboratory at U-M. Her research focuses on understanding and modeling the interconnections between human experience and the built environment. Her research group designs autonomous systems that support wellbeing, safety and productivity of office and construction workers, and provides them opportunities for lifelong learning and upskilling. Carol has more than 120 peer reviewed publications. Carol currently serves as a member of the Board of Governors of the ASCE (American Society of Civil Engineers) Construction Institute. She previously served as chair for the ASCE Construction Research Congress Executive Committee. Carol is an Associate Editor for the ASCE Journal of Computing in Civil Engineering and Assistant Specialty Editor for the ASCE Journal of Construction Engineering and Management. Carol is the recipient of the 2021 ASCE Arthur M. Wellington Prize, the 2021 ASCE Collingwood Prize, the 2017 ASCE Daniel Halpin Award, 2017 ASCE Alfred Noble Prize, 2017 Outstanding Early Career Researcher from Fiatech, 2015 CII Distinguished Professor Award and 2014 NSF Career award. She also received several best paper awards.
Professor in the Departments of Civil and Environmental Engineering, and Electrical Engineering and Computer Science
Vineet R. Kamat, Ph.D. is a Professor in the Departments of Civil and Environmental Engineering, and Electrical Engineering and Computer Science at the University of Michigan. He directs the Laboratory for Interactive Visualization in Engineering. Dr. Kamat’s research is primarily focused on Virtual and Augmented Reality Visualization, Simulation, Mobile Computing, Robotics, and their applications in Construction Management and Sustainable Building Systems. Dr. Kamat was awarded the 2020 Peurifoy Construction Research Award, the 2015 Walter L. Huber Civil Engineering Research Prize, and the 2012 Daniel W. Halpin Award for scholarship in construction by the American Society of Civil Engineers. Dr. Kamat is an Associate Editor of the ASCE Journal of Computing in Civil Engineering and a member of the editorial board for the journal Automation in Construction and the journal Advanced Engineering Informatics.
Dr. Kamat serves on the Board of Governors of the International Association of Automation and Robotics in Construction (IAARC). He has also served as the Chair of the ASCE Construction Institute’s Construction Research Council, and as a Member of the Board of Governors of the ASCE Construction Institute. He has also chaired the ASCE Visualization, Information Modeling and Simulation committee. Dr. Kamat’s research has been published in over 200 peer-reviewed journal publications and conference papers to date. He has presented his work in invited talks throughout the world and has organized several technical sessions on construction visualization at all major conferences in his field of research. He received a Ph.D. in Civil Engineering in 2003 from Virginia Polytechnic Institute and State University.
Associate Professor, Architecture and Material Performance (Architecture and Urban Planning)
Director of the FABLab
Wes McGee explores the integration of advanced manufacturing technologies with critical design-driven workflows. He is known for innovating in the space of design and fabrication across a range of material processes, particularly in the application of industrial robotic tools to architectural production. Wes is Co-founder and Partner of Matter Design. He is currently an associate professor and the director of the Fabrication and Robotics Lab at the University of Michigan Taubman College of Architecture and Urban Planning. He received a Bachelor of Science in Mechanical Engineering and a Master of Industrial Design, both from Georgia Tech. He has taught workshops and master classes across the US, Europe, the Middle East and in Australia. McGee has been recognized with awards such as the Architectural League Prize for Young Architects & Designers, the Design Biennial Boston Award, and the ACADIA Award for Innovative Research, as well as multiple Architect Magazine R+D awards. His work has been published widely in books, periodicals, conferences, and peer-reviewed journals and he has collaborated with an extensive range of architects, engineers, and artists. McGee’s research revolves around the interrogation of the means and methods of material production in architecture, focusing on developing new connections between design, engineering, materials, and manufacturing processes as they relate to the built environment. At Matter Design he explores these techniques across a range of scales and materials, with the goal of creating new possibilities for design and architecture.