This robot has just learned how to taste

In an episode of futurama, robot Bender wants to be a chef, but has to overcome the not inconsiderable hurdle of being incapable of taste. It was beautiful.

Move over, Bender. A new robot has not only been programmed to taste, it has been trained to taste food at different stages of the cooking process to check for seasoning. Researchers from the University of Cambridge, UK, working with domestic appliances manufacturer Beko, hope the new robot will be useful in the development of automated food preparation.

It’s a cliché of cooking that you must “taste as you go”. But tasting isn’t as simple as it may seem. There are different stages of the chewing process in which the release of saliva and digestive enzymes change our perception of flavor while chewing.


More on robots: Robots to decide on beer quality


The robot chef had already mastered the omelette based on human tasters’ feedback. Now, results published in the Frontiers in Robotics & AI journal show the robot tasting nine different variations of scrambled eggs and tomatoes at three different stages of the chewing process to produce a “taste map”.

Using machine-learning algorithms and the “taste as you go” approach, the robot was able to quickly and accurately judge the saltiness of the simple scrambled egg dish. The new method was a significant improvement over other tasting tech based on only a single sample.

Saltiness was measured by a conductance probe attached to the robot’s arm. They prepared the dish, varying the number of tomatoes and amount of salt. “Chewed” food was passed through a blender, then tested for saltiness again.

“Most home cooks will be familiar with the concept of tasting as you go – checking a dish throughout the cooking process to check whether the balance of flavors is right,” said lead author Grzegorz Sochacki from the University of Cambridge’s Department of Engineering. “If robots are to be used for certain aspects of food preparation, it’s important that they are able to ‘taste’ what they’re cooking.”

The new approach aims to mimic the continuous feedback provided to the human brain in the process of chewing, says Dr Arsen Abdulali, also from Cambridge’s Department of Engineering. “Current methods of electronic testing only take a single snapshot from a homogenised sample, so we wanted to replicate a more realistic process of chewing and tasting in a robotic system, which should result in a tastier end product.”

“When a robot is learning how to cook, like any other cook, it needs indications of how well it did,” said Abdulali. “We want the robots to understand the concept of taste, which will make them better cooks. In our experiment, the robot can ‘see’ the difference in the food as it’s chewed, which improves its ability to taste.”

“We believe that the development of robotic chefs will play a major role in busy households and assisted living homes in the future,” said senior Beko scientist Dr Muhammad W. Chugtai. “This result is a leap forward in robotic cooking, and by using machine and deep-learning algorithms, mastication will help robot chefs adjust taste for different dishes and users.” Next on the menu will be training robots to improve and expand the tasting abilities to oily or sweet food, for example. Sounds pretty sweet.



Leave a Comment

Your email address will not be published.