The robot chef who can taste as it goes could now potentially create your favourite meal. While the robot has only learned to create salads for now, there could be potential for the robot to be able to deliver a wider variety of recipes in the future.
Researchers from Cambridge University achieved the incredible feat by showing the robot a video of a human creating a recipe, programming it to identify a range of objects and foods to carry out the recipe itself. After analyzing each frame of the video, the robot converted them into vectors. It then compared the differences between the demonstration and the vector to identify any similarities between the two. It's this technology that helps the robot to be able to make the recipes on its own. While work on the robot is continuing, it still managed to identify the correct recipe 93% of the time and successfully detect any variations in the recipes it was given.
“It’s amazing how much nuance the robot was able to detect. These recipes aren’t complex – they’re essentially chopped fruits and vegetables, but it was really effective at recognising, for example, that two chopped apples and two chopped carrots is the same recipe as three chopped apples and three chopped carrots,” said Grzegorz Sochacki from Cambridge’s Department of Engineering.
However, this chef robot isn't the only new robot on the block. Other robots around the world are being created to help with daily tasks, such as robot hoovers and even BB the beach cleaning robot.
This post is for paid subscribers only
Monthly subscription
£4.99/mo
or $199 yearly
Premium Good News Subscription includes:
Ad-free
Access to unlimited articles
Video content
Exclusive weekly newsletter
Cancel anytime
Yearly guides with positive content & mental health tips
The robot chef who can taste as it goes could now potentially create your favourite meal. While the robot has only learned to create salads for now, there could be potential for the robot to be able to deliver a wider variety of recipes in the future.
Researchers from Cambridge University achieved the incredible feat by showing the robot a video of a human creating a recipe, programming it to identify a range of objects and foods to carry out the recipe itself. After analyzing each frame of the video, the robot converted them into vectors. It then compared the differences between the demonstration and the vector to identify any similarities between the two. It's this technology that helps the robot to be able to make the recipes on its own. While work on the robot is continuing, it still managed to identify the correct recipe 93% of the time and successfully detect any variations in the recipes it was given.
“It’s amazing how much nuance the robot was able to detect. These recipes aren’t complex – they’re essentially chopped fruits and vegetables, but it was really effective at recognising, for example, that two chopped apples and two chopped carrots is the same recipe as three chopped apples and three chopped carrots,” said Grzegorz Sochacki from Cambridge’s Department of Engineering.
However, this chef robot isn't the only new robot on the block. Other robots around the world are being created to help with daily tasks, such as robot hoovers and even BB the beach cleaning robot.
The robot chef who can taste as it goes could now potentially create your favourite meal. While the robot has only learned to create salads for now, there could be potential for the robot to be able to deliver a wider variety of recipes in the future.
Researchers from Cambridge University achieved the incredible feat by showing the robot a video of a human creating a recipe, programming it to identify a range of objects and foods to carry out the recipe itself. After analyzing each frame of the video, the robot converted them into vectors. It then compared the differences between the demonstration and the vector to identify any similarities between the two. It's this technology that helps the robot to be able to make the recipes on its own. While work on the robot is continuing, it still managed to identify the correct recipe 93% of the time and successfully detect any variations in the recipes it was given.
“It’s amazing how much nuance the robot was able to detect. These recipes aren’t complex – they’re essentially chopped fruits and vegetables, but it was really effective at recognising, for example, that two chopped apples and two chopped carrots is the same recipe as three chopped apples and three chopped carrots,” said Grzegorz Sochacki from Cambridge’s Department of Engineering.
However, this chef robot isn't the only new robot on the block. Other robots around the world are being created to help with daily tasks, such as robot hoovers and even BB the beach cleaning robot.
.jpeg)
.jpeg)
.jpeg)
.jpeg)
