Skip to Content

What Apple’s M7 Motion-Sensing Chip Could Do

Apple’s always-on motion-sensing M7 chip points the way to an era of mobile gesture-recognition and “ambient intelligence.”
September 25, 2013

The motion-processing M7 chip in the new iPhone 5S will serve as an aid to fitness-tracking apps, says Apple. But over the long term, the chip could help advance gesture-recognition apps and sophisticated ways for your smartphone to anticipate your needs, or even your mental state, researchers say.

While smartphones have long contained motion-sensors—accelerometers to detect speed, gyroscopes to detect orientation, and compasses—these are kept off when the phone is “asleep” to avoid tying up the main processor and draining the battery. The M7, operating separately from the main processor, aggregates all of the data from those sensors and allows them to stay active and be analyzed all the time, even when the phone itself is asleep.

 “I think the new M7 processor can be huge,” says Tanzeem Choudhury, an associate professor at Cornell University. “Apps using motion sensing can now work much more power-efficiently. The addition of other sensors in the future could enable richer tracking of not only physical activity states but also emotional ones.”

At a simple level, the user could program a gesture that might serve as a password—a unique shake or swivel could, in effect, become the screen-unlocking password, an instruction to call home, or a distress signal. Already, some phones, such as the Moto X, let users answer a call with a particular motion signature (see “Motorola’s Moto X: Interface Innovation with a Learning Curve”).

Having always-on motion signatures “would enable recognizing current activity and possibly the intention of the user, based on unique gesture patterns— and changing what the phone does in response,” says Pattie Maes, a professor at MIT’s Media Lab. “The user could possibly associate unique gestures with starting an app or changing some settings.”

Gestures can be powerful tools. In a recent research project, researchers at Rice University and Motorola evaluated whether software could accurately detect a set of eight predefined gestures—such as drawing a circle in the air, or moving the phone in a square shape—no matter who made it. After eight users made the gestures a total of 4,000 times, the researchers found that the software accurately identified the movements 98.6 percent of the time.

Choudhury has contributed to a smartphone project meant to promote well-being by detecting certain modes of behavior, such as walking, taking part in a conversation, or sleeping. The project was limited, however, by the fact that a user’s phone would frequently be asleep to avoid having sensors drain the battery.

A few sports-related apps that use the M7 have already emerged, including ones from Nike and Argus.  But even without special apps for fitness enthusiasts and self-quants, a phone always detecting motion could track and analyze overall activity levels over months, something that today requires an additional device such as the Fitbit.

With Apple widely rumored to be working on a smart watch, the iPhone 5S could be an important test for a new processor designed for always-on motion sensing. In a future smart watch, motion sensing could be a particularly important way of interacting with a device that is almost always affixed to your arm and has a tiny screen, making touch interaction more challenging. And if a future smart watch processor added other sensors able to capture physiological signals like heart rate and skin conductance, it could make for a powerful technology to track your well-being (see “Wrist Sensor Tells How Stressed Out You Are”).

Apple’s move in creating the M7 is similar to what Google’s Motorola Mobility did with the Moto X. That includes a low-power chip whose only function is to process data from a microphone, which can help establish context (see “The Era of Ubiquitous Listening Dawns”).

An always-on microphone can do things like tell whether you are in a noisy environment and respond by making the ringtone louder, for example. Choudhury has demonstrated new ways to leverage the fact that you can detect stress by changes in pitch or speaking rate. An always-on microphone in a smartphone, for example, might help you identify what’s making you stressed out.

The small hardware decisions by Motorola Mobility and Apple could be just a start to making phones smarter and far more aware of what the user is trying to do. “Apple and other phone companies may add more sensors on the co-processors, making potential applications even more diverse,” Choudury says.

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.

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.

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.

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.