A robot “chef” has been trained to taste food at different stages of the chewing process to examine whether it is salty enough, imitating the same process in humans.
The University of Cambridge researchers suggest their results may very well be useful in the event of automated or semi-automated food preparation by helping robots to learn what does and doesn’t taste good, making them higher cooks.
When food is chewed, people notice a change in taste and texture.
For instance, biting right into a fresh tomato at the peak of summer will release juices, and because it is chewed, saliva and digestive enzymes are released, changing our perception of the tomato’s flavour.
Robot tasting eggs and tomato
The robot, which has already been trained to make omelettes, tasted nine different variations of scrambled eggs and tomatoes at three different stages of the chewing process.
It then produced taste maps of different dishes.
The researchers found this “taste as you go” approach improved the robot’s ability to quickly and accurately assess the saltiness of the dish.
Grzegorz Sochacki from Cambridge’s Department of Engineering, the paper’s first writer, said: “Most home cooks might be acquainted with the concept of tasting as you go – checking a dish throughout the cooking process to examine whether the balance of flavours is correct.
“If robots are for use for certain features of food preparation, it’s necessary that they’re able to ‘taste’ what they’re cooking.”
Co-author Dr Arsen Abdulali, also from the Department of Engineering, said: “Current methods of electronic testing only take a single snapshot from a homogenised sample, so we wanted to copy a more realistic means of chewing and tasting in a robotic system, which should end in a tastier end product.”
To mimic the human means of chewing and tasting of their robot chef, researchers attached a probe – which acts like a saltiness sensor – to a robot arm.
They prepared scrambled eggs and tomatoes, various the variety of tomatoes and the quantity of salt in each dish.
Using the probe, the robot “tasted” the dishes in a grid-like fashion, returning a reading in only just a few seconds.
In an effort to imitate the change in texture brought on by chewing, the team then put the egg mixture in a blender and had the robot test the dish again.
Different readings at different points of this chewing produced taste maps of every dish.
In accordance with the study, there was a big improvement in the flexibility of robots to evaluate saltiness over other electronic tasting methods, which are sometimes time-consuming and only provide a single reading.
Researchers say that by imitating the human processes of chewing and tasting, robots will eventually give you the option to provide food that humans will enjoy and may very well be tweaked in accordance with individual tastes.
Dr Abdulali said: “When a robot is learning the way to cook, like every other cook, it needs indications of how well it did.
“We wish the robots to know the concept of taste, which can make them higher cooks.
“In our experiment, the robot can ‘see’ the difference within the food because it’s chewed, which improves its ability to taste.”
Dr Muhammad Chughtai, senior scientist at with domestic appliances manufacturer Beko, which is collaborating on the project, said: “We imagine that the event of robotic chefs will play a serious role in busy households and assisted living homes in the longer term.
“This result’s a breakthrough in robotic cooking, and by utilizing machine and deep learning algorithms, mastication will help robot chefs adjust taste for various dishes and users.”
The findings are published within the journal Frontiers in Robotics & AI.
