image: Coffee-making robot pours water from a kettle into a cup
Credit: Ruaridh Mon-Williams
An AI-powered robot that can prepare cups of coffee in a busy kitchen could usher in the next generation of intelligent machines, a study suggests.
Using a combination of cutting-edge AI, sensitive sensors and fine-tuned motor skills, the robot can interact with its surroundings in more human-like ways than ever before, researchers say.
The new technology, developed by a team at the University of Edinburgh, could transform robots’ ability to carry out tasks that previously could only be done by people.
While robots are adept at working in tightly controlled settings such as factories and production lines, they struggle in dynamic, unpredictable places like kitchens, experts say.
This is because robots have traditionally relied on pre-programmed actions and responses, and lack the ability to adapt to unforeseen obstacles in real-time, the researchers say.
Now, the Edinburgh team has combined advances in sensitive motor skills and AI to create a robot that can interact skilfully with objects and people in challenging settings. Previous developments in these areas had taken place largely independent of each other, the team says.
The new device – a robotic arm with seven movable joints – first interprets verbal instructions it receives, then analyses its surroundings.
Next, it searches the kitchen to find a mug by working out how to access drawers with opening mechanisms it has never encountered before. The robot then measures and mixes a set ratio of ground coffee from a jar with water from a kettle.
The technology behind the robot enables it to adapt seamlessly to unforeseen events, such as if someone bumps or moves the mug unexpectedly while it is working, the team says.
The research, published in the journal Nature Machine Intelligence, was supported by the Engineering and Physical Sciences Research Council (EPSRC). The work was led by Ruaridh Mon-Williams, a PhD student jointly at the University of Edinburgh, Massachusetts Institute of Technology and Princeton University.
Ruaridh Mon-Williams, of 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.”
Journal
Nature Machine Intelligence