Drone helps elderly escape from burning nursing homes

Students at Eindhoven University of Technology (TU/e) have developed an interactive drone that guides elderly people to the exit during a fire in a nursing home, even before the fire brigade arrives.

Photo
eam manager Paul van Kuppevelt and the Blue Jay Aeden.
Source: Rien Boonstoppel.

The student team Blue Jay has introduced an interactive drone that guides elderly people to the exit during a fire in a nursing home, even before the fire brigade arrives. The Blue Jay Aeden is said to be the first interactive drone in the world that can transmit emotions and can fulfil an important function in saving people's lives.

On average, 600 times a year a nursing home has to be evacuated because of a fire risk. "During an evacuation, elderly people often do not know what to do, which makes them anxious and can sometimes cause them to panic. Because they panic, they often cannot find their own way out, which can lead to dangerous situations and even death," explains Paul van Kuppevelt, team manager of Blue Jay. In 2020 alone, 25 people died as a result of these situations. To prevent this, Blue Jay has developed the first drone that can reassure the elderly and help them find the right route.

Programmed to see emotions

The drone contains a small camera that is programmed to see and understand the emotions of the elderly. This is done by means of a pair of eyes on the front. A convolutional neural network (CNN) is used for this, a form of deep learning that enables the drone to recognise emotions by analysing a large amount of visual images. The drone can recognise five different emotions (angry, happy, sad, neutral, surprised) with an accuracy of 94 per cent.

After an emotion is detected, the drone will react by showing an emotion itself. This makes the drone appear human, so that the resident feels more at ease and is more likely to trust and follow the drone. According to Van Kuppevelt, this works best if there is a natural response to the resident's emotion: "For example, if a resident looks happy, it is obviously important that the drone looks happy in return, and not angry or sad."

In order to make the drone show the right emotions, the team worked together with a group of elderly people from the Joris Zorg nursing home in Oirschot. Via several tests in the nursing home, it was possible to find out how the elderly and the staff react to the presence and the emotions shown by the drone. Manon Schreurs, ARBO Advisor at Joris Zorg: "We are proud that we can make a contribution by investigating the human aspect together with our residents."

Live watch

Through a live stream, the fire brigade can watch via an app what the drone sees at that moment. Van Kuppevelt: "This way, firefighters know exactly what is happening in the nursing home, so they can be better prepared. This saves precious minutes, which means more lives can be saved."

The fire brigade is delighted and is looking forward to the moment that they can actually use the drone. When that will be depends on a number of factors such as laws and regulations. For now, the drone is not permitted to fly in public areas. In addition, the team is currently working on technological solutions that will ultimately allow the drone to fly completely autonomously and ensures that it  is not obstructed by closed or locked doors.

Paul van Dooren, Innovation Advisor at Safety Region Brabant Zuidoost: "The interactive part of this drone ensures that it can provide added value to the existing resources. Resources such as fire alarms do give a signal, but cannot offer specific help to every person in need. The fact that the drone can now recognise emotions is a good step towards making this possible. Hopefully in the future we can develop this into a full analysis of the situation, for example through speech or object detection."

Subscribe to our newsletter

Related articles

Diabetes retinal screening through deep learning

Diabetes retinal screening through deep learning

Ubotica has developed a deep learning-based solution for detecting the presence of diabetic retinopathy indicators in retinal images.

Quantum sensors for next-gen brain-computer interfaces

Quantum sensors for next-gen brain-computer interfaces

Recently, Professor Surjo R. Soekadar outlined current and upcoming applications of brain-computer interfaces.

AI picks up mutations in colorectal cancers

AI picks up mutations in colorectal cancers

A deep learning algorithm picks up molecular pathways and the development of key mutations more accurately than existing methods.

Researchers psychoanalyse artificial intelligence

Researchers psychoanalyse artificial intelligence

We can run tests and experiments, but we cannot always predict and understand why AI does what it does.

The progress and risks of artificial intelligence

The progress and risks of artificial intelligence

Artificial intelligence has reached a critical turning point in its evolution, according to an international panel of experts.

AI identifies drug combinations to fight COVID-19

AI identifies drug combinations to fight COVID-19

Data scientists have used deep learning to identify the right synergistic drug combinations for the rapidly spreading SARS-CoV-2.

Deep learning helps visualize X-ray data in 3D

Deep learning helps visualize X-ray data in 3D

Scientists have leveraged artificial intelligence to train computers to keep up with the massive amounts of X-ray data taken at the Advanced Photon Source.

Using AI to predict 3D printing processes

Using AI to predict 3D printing processes

Engineers use Frontera supercomputer to develop physics-informed neural networks for additive manufacturing.

Deep learning predicts viral infections

Deep learning predicts viral infections

Using fluoresence images from live cells, researchers have trained an artificial neural network to reliably recognize cells that are infected by adenoviruses or herpes viruses.

Popular articles

Subscribe to Newsletter