Home / Blog / AI to cook an omelette?!

AI to cook an omelette?!

Ever seen something as complicated as this to cook a plain vanilla omelette? And it is, actually, even more complicated than it looks. There is plenty of software to make this robot learn how to prepare the very best omelette. Image credit: Cambridge University

We have already seen robots cooking. Robots flipping hamburger (meet Flippy at Caliburger in California), others having a menu of up to 600 dishes (Robochef cooks Indian, Chinese and Mediterranean cuisine) other can prepare cocktails (Tipsy has 60 cocktail recipes up to its sleeve…). We have even seen a fully robotic kitchen (Moley).

Hence a news of yet another robot, this one to prepare omelette should be a “no-news”! But that is not so.

A collaboration between Beko, a domestic appliance company, and the University of Cambridge has produced a robot that by listening to comments coming from its customers on its omelette can improve its way of cooking preparing better and better omelette.

This is possible thanks to an artificial intelligence software that explore alternative ways of preparing an omelette and take into account the feedback from customers. This is not easy and not, probably, for what you think. The problem the robot has to face is not improving the omelette as such but improving the overall perception of its customers. This is tricky. Some customers may like it fluffier, some other want to have it well done, others are looking for some yolk oozing out … How can the robot decide among personal preferences and an abstract idea of a perfect omelette?

There have to be compromises to be taken and customer interaction is crucial to deliver the best “customer experience”.

It is probably the first time that a robot gets endowed with the capability of appreciating the comments on its work and looking to get better as result of those comments. This goes well beyond the cooking of an omelette. It points to robots that can learn to get better based on subjective -and most likely contradictory- feedback from humans.
This is an important trait that will take us all one step forward in the human robotic collaboration, not based on “rules” and prescribed interfaces, rather on a dynamically adjustable framework that is being defined and redefined as collaboration takes place. Exactly what happens in human to human collaboration.

This is why this news is so important!

About Roberto Saracco

Roberto Saracco fell in love with technology and its implications long time ago. His background is in math and computer science. Until April 2017 he led the EIT Digital Italian Node and then was head of the Industrial Doctoral School of EIT Digital up to September 2018. Previously, up to December 2011 he was the Director of the Telecom Italia Future Centre in Venice, looking at the interplay of technology evolution, economics and society. At the turn of the century he led a World Bank-Infodev project to stimulate entrepreneurship in Latin America. He is a senior member of IEEE where he leads the New Initiative Committee and co-chairs the Digital Reality Initiative. He is a member of the IEEE in 2050 Ad Hoc Committee. He teaches a Master course on Technology Forecasting and Market impact at the University of Trento. He has published over 100 papers in journals and magazines and 14 books.