GabyGordon Ramsay, Jamie Oliver, and other celebrity chefs better be on their toes, as they have a competitor – a cooking robot that easily learns to cook just by watching cooking videos.
Researchers from the University of Cambridge programmed a robot to cook food as a professional chef would.
Using complex artificial intelligence The robot easily replicates human actions from videos because it can capture and remember every frame it sees. Its main difference from its predecessors is that the robot can recognize and select the necessary objects for cooking. In other words, it clearly understands the difference, for example, between a vegetable, a hand, and a knife, and will never confuse them.
Technologists assure that over time, the robot will learn to independently determine which ingredients pair best and even point out mistakes made by a real chef – for example, if the chef has chosen the wrong quantity of an ingredient.
Of course, cooking robots are not a novelty in their field. Time and again, researchers strive to recreate the ideal artificial intelligence. After all, cooking is a very complex task for a robot.
Some commercial companies have already created prototypes of cooking robots, although none of them have been made available for sale. And, to be honest, they lag significantly behind humans, meaning professional chefs, in skills.
The author of the study, Grzegorz Sochacki, a research associate at the Cambridge Laboratory of Bio-inspired Robotics, noted: “We wanted to see if we could teach a cooking robot to acquire knowledge in the same gradual way that humans do – that is, by identifying ingredients and how they combine to create a dish. We were surprised by how many nuances the robot was able to detect.”
He also added, “Our robot is not interested in the cooking videos that have flooded social media because they are too difficult to follow. But we aim to teach our cooking robot to identify ingredients from videos more quickly and accurately, so it can memorize recipes, for example, from YouTube.”
There is hope that the results published in the IEEE Access journal will make it easier and cheaper to develop and manufacture cooking robots.
Initially, the researchers created a “cookbook” with eight simple salad recipes and filmed the cooking process. A cooking robot, equipped with neural networks that mimic the functioning of the human brain, watched 16 such videos. By identifying the ingredients and actions of the human chef, it was able to accurately replicate 93% of the process.
He also easily identified small variations in the recipe, for example, he determined a double portion.
The robot was also able to recognize an entirely new ninth salad, added it to its cookbook, and… prepared it.
The research was partially supported by Beko plc and the Engineering and Physical Sciences Research Council (EPSRC), which is part of the UK Research and Innovation (UKRI) institute.
What other professions will robots take over?
The greatest risk of being left “out in the cold” is faced by those who work in physical jobs: machine operators or fast-food workers are most likely to be replaced by robots.
The consulting company McKinsey (New York, USA) focused on the number of jobs that will be lost due to automation and which professions are at the highest risk.
The report states that data collection and processing are categories that machines will perform better and more efficiently.
This could displace a large number of workers, for example, in the lending sector, as well as paralegals, accounting specialists, and transaction processing staff in back offices.
The most “human” professions remain those whose activities take place in unpredictable conditions and environments.
The report also notes that “professions such as gardener, plumber, nanny, or caregiver are less likely to be automated than others – at least until 2030. They are technically difficult to automate and do not require high wages, making automation unprofitable.”
