University of Edinburgh scientists create AI-powered robot that can make coffee in a busy kitchen setting

An AI-powered robot that can make cups of coffee in a busy kitchen provides a glimpse into “a future where increasingly intelligent machines are commonplace”, a new study suggests.

The robot was developed by a team at the University of Edinburgh, who said it was capable of carrying out “skilful interactions” with objects and people, and adapting to unforeseen events.

Traditionally, robots have relied on pre-programmed actions and responses, meaning they are good at working in tightly-controlled settings such as factories but struggle in less predictable places such as kitchens.

Researchers said the robot, which consists of a robotic arm with seven movable joints, is able to interact with its surroundings in a “more human-like way” thanks to cutting-edge AI, sensitive sensors and fine-tuned motor skills.

The team explained the process by which the robot was able to make a cup of coffee in an “unpredictable” kitchen setting.

It begins, they said, with the robot interpreting verbal instructions and analysing its surroundings.

Next it searches the kitchen to find a mug by working out how to access drawers with opening mechanisms it has not encountered before.

Finally, it measures and mixes ground coffee from a jar with water from a kettle.

The researchers said the technology behind the robot meant it could adapt to unforeseen events, such as if someone bumped or moved the mug unexpectedly while it was working.

They said the study showed the “power” of combining AI and robotics, with developments in these areas having previously taken place largely independently of each other.

Study lead Ruaridh Mon-Williams, from the University of Edinburgh’s School of Informatics, said: “We are glimpsing a future where robots with increasingly advanced intelligence become commonplace.

“Human intelligence stems from the integration of reasoning, movement and perception, yet AI and robotics have often advanced separately.

“Our work demonstrates the power of combining these approaches and underscores the growing need to discuss their societal implications.”

The research, published in the journal Nature Machine Intelligence, was supported by the Engineering and Physical Sciences Research Council.