A “chef” robot was trained to taste food at different stages of the chewing process to check if it is salty enough.

Cambridge University researchers developed the bot to mimic human chewing and tasting processes, so they could eventually produce foods that humans will not only enjoy, but can also be modified to suit individual tastes. .

If the robot lgain what tastes good and what doesn’t, making them better cooks, they could also be useful in the development of automated or semi-automated food preparation.

When food is chewed, people notice a change in taste and texture.

For example, biting into a fresh tomato at the height of summer releases juice, and as it is chewed, saliva and digestive enzymes are released, altering our perception of the tomato’s flavor. .

The robot, which was previously trained to make omelettes, tasted nine different variations of scrambled eggs and tomatoes at three different stages of the chewing process.

He then produced taste maps of the different dishes.

The researchers found that this “taste as you go” approach improved the robot’s ability to quickly and accurately assess the saltiness of the dish.

Grzegorz Sochacki of Cambridge’s Department of Engineering, the paper’s first author, said: “Most home cooks are familiar with the concept of tasting as you go – checking a dish through the process of cooking to check if the balance of flavors is correct.

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

Co-author Dr Arsen Abdulali, also from the Department of Engineering, explained that to mimic human chewing and tasting, they attached a probe – which acted as a salinity sensor – to a robot arm.

He added: “Current electronic testing methods only take a single snapshot from a homogenized sample, so we wanted to replicate a more realistic chewing and tasting process in a robotic system, which should result in a tastier end product.

They made scrambled eggs and tomatoes, varying the number of tomatoes and the amount of salt in each dish.

Using the probe, the robot “tasted” the dishes like a grid, returning a reading in just seconds.

In order to mimic the change in texture caused by chewing, the team then put the egg mixture in a blender and had the robot test the dish again.

Improved ability to taste

The different readings at different points of this mastication produced taste maps of each dish.

According to the study, there was a significant improvement in the robots’ ability to assess salinity compared to other electronic tasting methods, which are often time-consuming and provide only a single reading.

Dr Abdulali said: “When a robot is learning to cook, like any other cook, it needs feedback on its performance.

“We want robots to understand the concept of taste, which will make them better cooks.

“In our experiment, the robot can ‘see’ the difference in food as it is chewed, which improves its ability to taste.”

Dr Muhammad Chughtai, a senior scientist at appliance maker Beko, which is collaborating on the project, said he believes robotic chefs will play “a major role in busy households and assisted living facilities in the future”. .

The results are published in the journal Frontiers in Robotics & AI.