New AI-based technology to programme robots to locate lost objects

Researchers have developed a new artificial intelligence (AI) based technology to programme robots to help people locate essential objects such as medicines, glasses, phones and other items they have lost.

The researchers want to initially use the technology to help people with dementia, and in future anyone who needs to search for something they have misplaced.

"The long-term impact of this is really exciting," said Ali Ayub, a post-doctoral fellow at the the University of Waterloo in Canada.

"A user can be involved not just with a companion robot but a personalised companion robot that can give them more independence," Ayub said.

Dementia restricts brain function, causing confusion, memory loss and disability. Many people with the condition repeatedly forget the location of everyday objects, which diminishes their quality of life and places additional burden on caregivers.

The researchers believe that a companion robot with an episodic memory of its own could be a game-changer in such situations. And they succeeded in using AI to create a new kind of artificial memory.

The team used an object-detection algorithm to programme the robot to detect, track and keep a memory log of specific objects in its camera view through stored video.

With the robot capable of distinguishing one object from another, it can record the time and date objects enter or leave its view.

The researchers then developed a graphical interface to enable users to choose objects they want to be tracked and, after typing the objects' names, search for them on a smartphone app or computer.

Once that happens, the robot can indicate when and where it last observed the specific object, the researchers said.

Tests have shown the system is highly accurate. And while some individuals with dementia might find the technology daunting, Ayub said caregivers could readily use it.

The researchers will now conduct user studies with people without disabilities, then people with dementia.

A paper on the project was presented at the 2023 ACM/IEEE International Conference on Human-Robot Interaction in March in Stockholm, Sweden.