Skip to Content
Uncategorized

Meet the Robo Sommelier

An “electronic tongue” can classify certain types of Spanish wine. Should sommeliers fear for their jobs?
August 8, 2011

At least the robots of the future will have good taste.

A Spanish research team at the Universitat Autònoma de Barcelona recently announced that they had developed an electronic tongue with some of the talents of an old-fashioned, human sommelier. The device, which uses advanced sensors and some clever mathematics, is able to bring all its computational power to bear on a pressing problem: the identification of wine. The robo-tongue can already sort three types of cava, a wine distinctive to the Catalonia region of Spain.

The electronic tongue achieves this feat through electrochemical analysis. Since cava wines are categorized by the amount of sugar added (ranging from Brut Nature, sugarless, up through Brut, Dry, and Sweet, which may have 50 grams of sugar per liter or more), if the tongue can detect sugar concentrations, it’s able to infer the type of wine. The tongue analyzed samples using a measurement process called cyclic voltammetry; relevant information was culled from the data using two advanced mathematical techniques: principal component analysis and discrete wavelet transform. In plain English, though (or in Catalan, as on this handy chart), the electronic tongue basically goes through the same steps as a human sommelier: acquisition of data, processing of that data, and ultimate inference as to the chemical composition of the wine in question.

The electronic tongue is inspired by biological mechanisms, and behaves like them–down to the need for education. No sommelier comes by his skill innately; similarly, “a learning and training process is needed so that the electronic tongue can be capable of recognizing the properties that must be identified,” according to the UAB.

The team analyzed 21 sparkling wines in total: 19 Spanish cava wines – everything from Rondel Blue to Extra de Codorniu to Jaume Serra, for the wine aficionados out there – plus a pair of French champagnes, “included as outliers,” writes the team. (One imagines that the lab wasn’t lacking for beverages to celebrate the research’s eventual publication in the journal Electroanalysis!)

Believe it or not, the quest for an electronic sommelier is a (relatively) old one. The Barcelona team, in a paper published on their work, link to several others, including one dating back to 1999. The other studies differ in a few ways, though, focusing on wines from different regions, or different properties of a given bottle – the features of its foam, for instance, or the volatile and nitrogen compounds in the wine. The other studies also tended to use very different techniques, such as mass spectrometry, which separates heavy substances from lighter ones.

With an array of researchers working on this important problem from so many different angles, we welcome the good news that robots, so often unfairly maligned as lacking an appreciation for the finer side of life, will in fact be consummate oenophiles. Good news for everyone, that is, except the human sommeliers, who might want to start taking programming classes.

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.