Skip to Content

New Boss on Construction Sites Is a Drone

Drones are being used to capture video footage that shows construction progress at the Sacramento Kings’ new stadium in California.
August 26, 2015

For some construction workers, any thoughts of slacking off could soon seem rather quaint. The drones will almost certainly notice.

Video imagery combined with computer designs show how the Sacramento Kings’ new stadium will develop.

The site of a lavish new downtown stadium for the Sacramento Kings in California is being monitored by drones and software that can automatically flag slow progress.

Once per day, several drones automatically patrol the Sacramento work site, collecting video footage. That footage is then converted into a three-dimensional picture of the site, which is fed into software that compares it to computerized architectural plans as well as a the construction work plan showing when each element should be finished. The software can show managers how the project is progressing, and can automatically highlight parts that may be falling behind schedule.

“We highlight at-risk locations on a site, where the probability of having an issue is really high,” says Mani Golparvar-Fard, an assistant professor in the department of civil engineering at the University of Illinois, who developed the software with several colleagues. It can show, for example, that a particular structural element is behind schedule, perhaps because materials have not yet arrived. “We can understand why deviations are happening, and we can see where efficiency improvements are made,” Golparvar-Fard says.

The project highlights the way new technologies allow manual work to be monitored and scrutinized, and it comes as productivity in other areas of work, including many white collar jobs, is being tracked more closely using desktop and smartphone software.

Software developed at the University of Illinois can show different stages of construction.

Such additional scrutiny is sometimes controversial. The tracking of office workers raises worries over privacy, for instance, and fears that people may be encouraged to work excessive hours.

Golparvar-Fard concedes that this could be an issue, but he defends the idea. “It’s not new to the construction industry that there would either be people standing and observing operations, or that there would be fixed cameras,” he says. “Yes, making this autonomous has a different feeling for the workers. But you have to keep in mind that it’s not really questioning the efficiency of the workers, it’s questioning what resources these guys need to be more efficient.”

Such concerns aren’t slowing down development of the technology required for monitoring construction work. The falling cost of drone hardware and the availability of sophisticated control, navigation, and planning software have helped the aerial vehicles make a large impact on the agriculture industry already (see “10 Breakthrough Technologies 2014: Agricultural Drones”).

Monitoring activity across a large, complex construction site is particularly difficult because there are so many moving parts, and because the jobs being performed change frequently. A report published in 2009 by the National Research Council of the National Academies found that construction lags behind other industries such as manufacturing in terms of productivity, and blamed the situation on problems with planning, coӧrdination, and communication.

Another project involves tracking the activity of individual construction workers in video footage.

At the Sacramento project, video is being captured by a drone-operating company called ImageInFlight. The software developed by the University of Illinois team can show how different subcontracting teams are working together.

Lincoln Wood, regional manager for virtual design and construction at Turner Construction, which is running the Sacramento project, says that while it is common to monitor progress closely, the near-real-time aerial images and software analysis being used there provides a more comprehensive picture of what’s going on, and can highlight how a slowdown in one area may affect the entire project. “The nice thing about it is that it’s showing all the tasks in an area, so people are seeing the global impact,” he says.

The software developed by Golparvar-Fard and his colleagues including Timothy Bretl, an associate professor of robotics, and Derek Hoiem, an associate professor of computer science, is also being used at a high-rise construction project in Arizona, and by Taisei, a large construction company in Japan.

The University of Illinois team is currently testing a system that will allow drones to attach cameras to locations across a building site, so that activity can be monitored continually. In experiments, they are also using a crowdsourcing platform to categorize workers’ activities in video footage. A manager can then see how different tasks are being performed overall, and how much time each individual is spending on a job.

This level of surveillance could prove even more controversial. A spokesman for the Laborer’s International Union of North America (LIUNA) said the organization was not aware of such technology, and declined to comment.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.