Skip to Content

Commuter Rail Workers in Boston Are About to Get Bionic Eyes

Smart glasses for field mechanics will use augmented reality to improve train efficiency and reduce costs.
August 17, 2016

Add commuter rail to the list of industries adopting augmented reality to boost efficiency, cut costs, and increase their workers’ skills.

In September, Keolis Commuter Services (KCS), which operates the Greater Boston commuter rail system for the Massachusetts Bay Transportation Authority (MBTA), will give AR smart glasses to field mechanics so they can communicate with expert technicians in its main maintenance facility. The aim is to speed up train repairs and reduce the disruptions they cause.

The project will use software from a startup called AMA XpertEye that links smart glasses with a Web-based interface. AMA XpertEye buys the glasses from manufacturers (Epson, Google, ODG, or Vuzix) and loads its own Android-based operating system onto them. The technology enables the wearer to stream video and converse in real time—typically from the field—with someone located elsewhere, such as an office.

KCS commuter railroad workers will be testing these ODG smart glasses, as well as a pair from Vuzix.

Usually, the person in the field accesses the interface via the smart glasses and a smartphone that is tethered to them, while the remote expert on the other end uses a laptop. Both participants can exchange written messages and take screenshots of the video, annotate the images, and send them to each other. The video can also be saved for later replay or training purposes. The connection, which is encrypted, can use 3G, 4G, Wi-Fi, or Ethernet cable.

Think of the technology as AR “lite,” or augmented vision. “What we do is enhance people’s vision through image processing,” says Anne-Fleur Andrle, the CEO of AMA XpertEye. “It’s not what people expect when they think of augmented reality.” While design-intensive industries such as architecture and engineering might prefer full-blown AR software and tools like Microsoft’s HoloLens head-mounted computer, AMA XpertEye’s technology and its partners’ smart glasses appeal to companies that want to use AR for remote maintenance, monitoring, and training. In these tasks, it’s more important for people to see exactly what their colleagues are seeing than to view virtual objects integrated into their physical environment.

Yann Veslin, KCS’s manager for operation planning and performance improvement, says AMA XpertEye’s technology should help his employer keep more trains in service despite aging infrastructure, snowy winters, and a sprawling territory that stretches from Providence, Rhode Island, in the south to the New Hampshire border in the north and Worcester, Massachusetts, in the west.

KCS plans to test smart glasses in three different locations: on a set of tracks near the MBTA’s maintenance facility in Somerville, Massachusetts; at a smaller maintenance facility in the Boston neighborhood of Readville; and at a “layover” facility located at the end of one of the MBTA’s train lines. The first scenario would save KCS mechanics a half-hour walk, while the second and third would prevent KCS from having to transport trains to the main facility every time something malfunctioned in a locomotive or coach car. “[Remote workers] could easily fix a broken door, loudspeaker, or heating or air-conditioning system if they had a good way to consult our maintenance experts,” says Veslin. “They’ll also learn more through this visual experience than they would if they just called each other on the phone.”

Once KCS has thoroughly tested the technology, train drivers might even be able to use smart glasses to make emergency repairs while passengers are on board. Currently, drivers use a special radio in such situations and have to rely on voice directions.

AMA XpertEye’s technology has other applications beyond train maintenance. Car manufacturers can use it to supervise third-party auto repairs, insurance companies to remotely assess property damage and claims, and security guards and factory managers to remotely monitor buildings.

A number of companies offer similar technology. APX Labs makes smart-glasses software geared toward field service and maintenance work. CrowdOptic has live video-streaming software that can be incorporated into smart glasses, drones, and safety helmets. Interapt creates Google Glass apps for workplace collaboration and employee training. But some of these companies support only one smart-glasses brand, some make software targeted to specific industries, and some develop technology for a range of wearables instead of focusing on smart glasses. AMA XpertEye’s closest competitor is probably Pristine, which specializes in video collaboration that can be used for remote customer support, field service, inspections, quality assurance, supervision, and training.

Ease of use may be AMA XpertEye’s biggest differentiator. The startup, which was incorporated in January, is based in Cambridge, Massachusetts, and is the Americas division of the French company AMA SA, which got its start as a mobile game developer and is a sister company to the game developer Ubisoft. Andrle says AMA’s experience producing games taught it the importance of intuitive design.

Veslin, the KCS manager, says simplicity is an important consideration for its train mechanics and engineers, especially those who have worked for the MBTA for decades and are skeptical of new processes. “We’ll be asking everyone [who tries XpertEye], ‘Was it easy to use?’ and ‘Did we save time?’” he says. “If they say yes, it’s a good investment.”

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 with a list of newsletters you’d like to receive.