Imagine having your own personal chef robot? A robot capable of cooking has long been discussed in fiction and movies. That imagination may someday be realistic—at least according to research carried by the University of Cambridge. Researchers used machine learning to train robots how to cook.
"Cooking is a really interesting problem for roboticists, as humans can never be totally objective when it comes to food, so how do we as scientists assess whether the robot has done a good job?" said Dr. Fumiya Iida from Cambridge's Department of Engineering, who led the research.
Learn more about earlier attempts on teaching robots to cook:
Although a challenging task, the researchers have trained the robot to cook an omelet—this included cracking the eggs and plating the finished dish.
"An omelette is one of those dishes that is easy to make, but difficult to make well," said Iida. "We thought it would be an ideal test to improve the abilities of a robot chef, and optimise for taste, texture, smell and appearance."
"Another challenge we faced was the subjectivity of human sense of taste -- humans aren't very good at giving absolute measures, and usually give relative ones when it comes to taste," said Iida. "So we needed to tweak the machine learning algorithm -- the so-called batch algorithm -- so that human tasters could give information based on comparative evaluations, rather than sequential ones."
But how did the robot measure up as a chef? "The omelettes in general tasted great -- much better than expected!" said Iida.