Waterloo engineers task AI robot to help people with dementia

With no cure established, treatments for dementia aim at slowing the progression of the disease and improving quality of life.

To this end, Engineers at the University of Waterloo have designed a robot that could help people with dementia locate medicines, glasses, and other objects they need but have lost.

Dr. Ali Ayub, a postdoctoral fellow in electrical and computer engineering, presented a paper on the project at the ACM/IEEE International Conference on Human-Robot with his team this year.

“The long-term impact of this is really exciting,” Dr. Ayub said. “A user can be involved not just with a companion robot but a personalized companion robot that can give them more independence.”

Although the team primarily focuses on a specific group of people, they expect the technology to be used by anyone in the future to track any item they have misplaced.

AI to shine a light on objects

Dr. Ayub and his colleagues were driven to this research by a deep concern for people diagnosed with dementia and its rising numbers. They believe a companion robot driven by artificial intelligence and possessing episodic memory can make a difference in the quality of life and take away some burden from caregivers.

The team’s vision started with a Fetch mobile manipulator robot which has an arm, enabling it to manipulate objects, multiple sensors, and cameras.

The robot was then programmed with an object-detection algorithm that allows it to detect and keep track of specific objects that enter its field of vision.

Users can choose objects they want to keep track of through a graphical interface on their smartphone or computer.

When the item needs to be found, the user can search for it using this interface, triggering the robot to indicate where and when it was seen last.

While the technology might seem daunting for some individuals, Dr. Ayub speaks of it being user-friendly and accurate.

The team looks to begin testing with people in the real world, first with people without disabilities and then with patients with dementia.

The study was published in ACM.

Study Abstract

Persons with Dementia face the issue of a deteriorating memory. As assistive robots are being increasingly adapted as a helper to persons with dementia, this paper presents an additional feature to such robots. Assistive robots that might assist with different tasks in users' households can also be utilized to track salient objects to quickly find them in case they are misplaced. This paper presents an episodic memory system that can enable a robot to recognize salient objects and track them while moving in and out of the environment. We also demonstrate how to develop access to the robot's memory in an easy-to-understand way using a graphical user interface (GUI). The proposed system is integrated with a Fetch mobile manipulator robot to track, store and visualize various household objects in an environment. Results from a system evaluation study are encouraging and the system will be further investigated in future co-design and user studies.