Skip to Content

Burger Profiling

September 1, 2004

Pull into the McDonald’s in Chippewa, PA, these days, and computer vision software will tell the fry cooks what you probably want for lunch before you get out of the car. Over the past year, HyperActive Technologies of Pittsburgh has equipped eight fast-food restaurants in Pennsylvania and Ohio with cameras and software that analyze incoming traffic, providing a jump on likely food orders.

HyperActive’s software counts cars as they enter, identifies the types of vehicles it spots, and makes recommendations based on past trends at the restaurant. Incoming minivans might foretell demand for chicken nuggets and other kid-friendly fare, while pickup trucks suggest double cheeseburgers or Quarter-Pounders. The program then estimates food demand for the next few minutes and transmits cooking instructions to display screens at the grills and deep fryers.

As a result, restaurants have cut customers’ waiting time by as much as one-third and reduced food waste, says HyperActive cofounder R. Craig Coulter, a former computer scientist at Carnegie Mellon University’s Robotics Institute. Pat Currie, a manager at Tri County Management, which owns the Chippewa franchise, says the system also reduced the stress on frazzled help. “It was beautiful,” says Currie. “There was no yelling and screaming.”

If HyperActive’s figures are accurate, the technology has promise, says Andy Feinstein, a food-service-technology professor at the University of Nevada, Las Vegas. Fast-food restaurants are “all about volume,” he says. “Anything that they can do to reduce waste, they would certainly work at.”

Other companies are also enlisting computer vision in the fast-food cause. Advanced Interfaces of State College, PA, has recently conducted field trials with local McDonald’s restaurants to map foot traffic, evaluate layouts and promotional displays, and help restaurants plan their menus for different times of the day or week. Which means your local burger joint might eventually know what you want days before you do.

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.