WATCH: Robot chef learns how to make recipes by copying video demos
Researchers at the Uni of Cambridge have programmed the robot
Researchers at the University of Cambridge have trained a robotic ‘chef’ to watch cooking videos and recreate dishes.
The robot is programmed with eight simple salad recipes, and after watching a human video demonstration is able to identity what recipe is being made and copy.
The videos helped the robot incrementally add to its cookbook. At the end of the experiment, the robot came up with a ninth recipe on its own.
Human cooks can learn new recipes through observation, whether that’s watching another person cook or watching a video on YouTube, but programming a robot to make a range of dishes is costly and time-consuming.
Using computer vision techniques, the robot analysed each frame of video and was able to identify the different objects and features, such as a knife and the ingredients, as well as the human demonstrator’s arms, hands and face.
Both the recipes and the videos were converted to vectors (movement from one point to another).
The robot then performed mathematical operations on the vectors to determine the similarity between a demonstration and a vector.
The robot was also able to detect that slight variations in a recipe, such as making a double portion or normal human error, were variations and not a new recipe.