Robots are commonly being recruited to solve many problems for humans in society. One of their incredible uses is in food preparation, with some being able to cook and plate up entire meals.

An issue that still needs to be tackled in this area is their ability to adapt to seasoning. The texture and taste of a dish are difficult things to program due to the fact they change at different stages of the chewing process in humans. Biting into a fresh tomato is one example of this, as the eating process unfolds the fruit release juices, and as we chew, releasing both saliva and digestive enzymes, our perception of the tomato’s flavor will change.

A team from the University of Cambridge wanted to tackle this, by creating a system that can help robots learn what tastes good and what doesn’t, making them better cooks. Previous experiments have allowed robots to adjust the saltiness of dishes based on human feedback. Further development revealed that the “taste as you go” approach significantly improved the robot’s ability to find correct levels of saltiness.

“When we taste, the process of chewing also provides continuous feedback to our brains,” said co-author Dr. Arsen Abdulali. “Current methods of electronic testing only take a single snapshot from a homogenized 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.”

The taste testing robots were fitted with a conductance probe – a sensor that measures salinity – on their arm. The team then put their idea to the test, getting the robot to measure the taste and texture of scrambled eggs and tomatoes… and it worked! Not only that, but the machine was able to come back with the most advanced system to assess saltiness over any other electronic tasting methods.

“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.”

Machines such as this could be a huge help in assisted living homes of the future and may be able to take some of the pressure off of a busy family. They hope to further develop their product to be able to adjust to different flavor constraints – such as sweet or oily food – and be able to program individual taste preferences through advancing the complexity of their algorithms.

Source study: Frontiers in Robotics & AI – Mastication – Enhanced Taste-Based Classification of Multi-Ingredient Dishes for Robotic Cooking