Skip to Content

Microsoft Has an Operating System for Your House

Microsoft aims to simplify home automation with software that connects different Internet-enabled devices.
July 18, 2013

Researchers at Microsoft have released software aimed at making it easier for homes to be monitored, automated, and controlled using computers and the Internet. It also paves the way for developers to create apps that can be “installed” into homes with numerous different devices to make use of them in new ways.

Although Internet-connected products for the home—including security cameras, thermostats, and motion sensors—are readily available, it can be challenging to install them, and they typically work independently. The new software from Microsoft, called Lab of Things, provides a centralized virtual dashboard for monitoring and controlling different “smart home” devices. It also provides standards for building “apps” for homes with the Lab of Things software installed.

Microsoft researcher Arjmand Samuel announced the Lab of Things software this week at Microsoft’s annual Faculty Summit, held for researchers from inside and outside the company. He said it was needed because the challenges of installing and running collections of home automation devices are holding back research into new possible uses for the technology.

The Lab of Things software “lowers the barrier to deploying field studies in connected homes,” he said, explaining that trials of home automation systems that combine multiple types of sensors and other devices are typically small-scale and short-lived due to the inconveniences for both researchers and the volunteers who welcome them into their homes.

Providing a common platform will help ready technology for consumers who want to automate or augment their home, said Samuel, by making it easier for researchers to try out new ideas and create home automation apps.

Lab of Things is named for the phrase Internet of Things, which refers to the idea that inanimate objects and devices will begin to coӧperate using the Internet. The project builds on an earlier Microsoft Research software package called HomeOS, which was used by outside researchers in projects including ones that allowed gesture control of home appliances, and for mobile apps to configure home automation devices.

The Lab of Things software, available from the project’s home page, needs to be installed onto a computer in a home, and can then automatically detect home automation devices sharing the same network.

In a demonstration by Microsoft researcher A.J. Brush, Lab of Things automatically recognized a sensor that detects whether a door is open or closed as soon as it was connected to the same network. Brush could then use a Web interface to configure an alert that would send an e-mail as soon as the sensor detected a door had been opened. Brush also showed how she could log into Lab of Things running in her own home via the Web to view footage from a security camera there.

A separate presentation at Microsoft’s Faculty Summit by Kamin Whitehouse of University of Virginia described trials of a sophisticated use of home automation. Whitehouse, who is not part of the Lab of Things project, installed large numbers of sensors into 20 houses to research how home automation could address energy use.

Sensors over each door in participating homes, combined with others monitoring water and electricity use, made it possible for software to follow the habits of people in those houses, and identify ways they could save power without compromising their routines.

Without needing to program in the layout of a house or details of who lives there, “we can identify the floor plan of the house, which people are in the house, which rooms they’re in, and the electrical and water usage,” said Whitehouse of his system. “No configuration [is] required. You open your phone app and it’s there.”

However, Kamin also spoke of the challenges of hooking up hundreds of sensors in a house and keeping the system going. The Microsoft team working on Lab of Things hopes it can enable more studies like Whitehouse’s at even larger scales.

Dean Mohamedally, a researcher at University College London who attended the talk introducing Lab of Things, said that the project had merit, but argued it should widen its scope beyond homes. Medical facilities, care homes, and commercial places such as gyms could have much to gain from building automation technology, he suggested: “I think it’s a starting point for a lot of other areas.”

Some researchers believe that automation will ultimately have a larger payoff in working buildings. Energy savings in such buildings can be greater, for example, and organizations can use automation in other ways; for example, a care home might use it to monitor patient movements. 

Joe Paradiso, an associate professor at the MIT Media Lab who was present at the event, said that Lab of Things software should be integrated with commercial efforts to help home automation devices link up, such as AllJoyn and DNLA. “There are standards that exist that you should take advantage of,” he said.

Ratul Mahajan, a researcher on the Lab of Things team, said that standard protocols developed by these efforts are useful, and the Microsoft software would use them. But he also said that interconnection protocols alone can’t address the more significant challenge of making devices work together seamlessly. “We are exploring this whole other space that works on top of this ability to talk to devices.”

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.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

How scientists traced a mysterious covid case back to six toilets

When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

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.