WhatsNew2Day
Latest News And Breaking Headlines

Robot chef is trained to taste food at different chewing stages

A robot chef has been trained to “taste” food at different stages of the chewing process, just like humans do.

The machine, created at the University of Cambridge, consists of a probe that can detect salt levels in food connected to the end of a robotic arm.

The experts used the robot to test the scrambled eggs during different stages of chewing, including a runny liquid that would appear just before swallowing.

According to scientists, robotic chefs who ‘taste’ dishes instead of humans could be part of busy restaurant kitchens of the future.

The experimental setup: the machine comprises a conductance probe (acting as a salinity sensor) attached to the end of a robotic arm

The experimental setup: the machine comprises a conductance probe (acting as a salinity sensor) attached to the end of a robotic arm

A robot 'chef' has been trained to taste food at different stages of the chewing process to assess if it is seasoned enough.  The researchers used a fairly simple dish of scrambled eggs with tomatoes for their experiments.

A robot ‘chef’ has been trained to taste food at different stages of the chewing process to assess if it is seasoned enough. The researchers used a fairly simple dish of scrambled eggs with tomatoes for their experiments.

HOW WILL WE KNOW?

Taste perception is a complex process in humans that has evolved over millions of years.

The appearance, smell, texture, and temperature of food affect how we perceive taste.

Saliva produced during chewing helps transport chemical compounds from food to taste receptors, primarily on the tongue.

Signals from taste receptors are transmitted to the brain. Once our brains are aware of the taste, we decide whether or not we enjoy the food.

Taste is also very individual. Some people love spicy food, while others have a sweet tooth.

A good cook, whether amateur or professional, relies on their sense of taste and is able to balance the various flavors within a dish to make a complete end product.

Researchers from the University of Cambridge worked in collaboration with appliance manufacturer Beko for the project.

“Most home cooks will be familiar with the concept of tasting as you go – checking a dish throughout the cooking process to check if the balance of flavors is just right,” said Grzegorz Sochacki of Cambridge’s Department of Engineering.

“If robots are going to be used for certain aspects of food preparation, it’s important that they be able to ‘taste’ what they’re cooking.”

As we chew food, we notice a change in texture and flavor as the teeth and sage break down the bite.

For example, biting into a fresh tomato in the middle of summer will release juices, and as we chew, releasing saliva and digestive enzymes, our perception of the tomato’s taste will change.

“When we taste, the process of chewing also provides continuous feedback to our brain,” said co-author Dr. Arsen Abdulali, also from the Department of Engineering.

“Current electronic testing methods only take a snapshot of a homogenized sample, so we wanted to replicate a more realistic chewing and tasting process on a robotic system, which should result in a more palatable end product.”

The robot chef, who has already been trained to make omelettes based on feedback from human tasters, sampled nine different variations of a simple dish of scrambled eggs and tomatoes at three different stages of the chewing process.

The team did this because the breakdown of food in the mouth affects the distribution of salinity.

In other words, salty food can appear more or less salty depending on how much is chewed before swallowing.

The three different stages were ‘unchewed’ (as it would appear before consumption), ‘half chewed’ (slightly broken down in the mouth), and ‘chewed’ (homogeneous and ready to swallow).

The robot chef, who has already been trained to make omelettes based on feedback from human tasters, sampled nine different variations of a simple scrambled egg dish (pictured)

The robot chef, who has already been trained to make omelettes based on feedback from human tasters, sampled nine different variations of a simple scrambled egg dish (pictured)

The robot tasted the food in three different stages: 'unchewed' (as it would appear before consumption; A and B), 'half-chewed' (slightly broken down in the mouth, C) and 'chewed' (homogeneous and ready to eat). .  be swallowed, D)

The robot tasted the food in three different stages: ‘unchewed’ (as it would appear before consumption; A and B), ‘half-chewed’ (slightly broken down in the mouth, C) and ‘chewed’ (homogeneous and ready to eat). . be swallowed, D)

Instead of a researcher starting to chew on the plate and spitting it out, the team used a blender to make the plate appear as if it had been chewed or half-chewed.

At each stage, the robot inserted its conductance probe, which acts as a salinity sensor, into the food and took a salinity reading by measuring the movement of the ions.

This “test-on-the-fly” approach significantly improved the robot’s ability to quickly and accurately assess dish salinity compared to other electronic sampling methods, which are often time-consuming and only provide a single reading.

Different readings at different ‘chewing’ points produced flavor maps of each dish, showing dark areas of low salt ion conductivity by the sensors.

Figure showing the flavor mapping of the same scrambled tomato after mixing it at three different stages, the extreme cases being no mixing and

Figure showing the flavor mapping of the same scrambled tomato after mixing it at three different stages, the extreme cases being unmixed and “visually homogeneous”.

While their technique is a proof of concept, the researchers say that by mimicking the human processes of chewing and tasting, the robots will eventually be able to produce food that humans will enjoy and could be modified according to individual tastes.

In the future, the team wants to improve the robot chef so that it can taste different types of food and improve detection capabilities so that it can taste sweet or oily foods, for example.

“Beko has a vision to bring robots into the home environment that are safe and easy to use,” said Dr. Muhammad W. Chughtai, Senior Scientist at Beko.

“We believe that the development of robotic chefs will play an important role in busy households and assisted living homes in the future.

“This result is a leap forward in robotic cooking, and by using deep and machine learning algorithms, chewing will help robotic chefs adjust taste for different dishes and users.”

The results have been published in the journal Frontiers in robotics and AI.

MEET CHIPY! CHIPOTLE TRIALS A ROBOT CHEF TO MAKE TORTILLA CHIPS

It’s a Mexican fan favorite fast food restaurant, and now Chipotle has announced its latest employee: a robot chef named Chippy.

Chippy will be tasked with making Chipotle’s famous tortilla chips, using artificial intelligence to perfect the chain’s exact recipe.

It has been developed in collaboration with the Pasadena-based startup Miso Robotics, best known for its other robotic chef, Flippy, who can flip up to 300 burgers a day.

Chippy will initially be tested at Chipotle’s innovation center in Irvine, California, before being integrated into a restaurant in Southern California later this year.

It’s unclear when, or if, Chippy will roll out to Chipotle restaurants in the UK.

Read more: Chipotle is testing a ROBOT CHEF to make tortilla chips

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. Accept Read More