Skip to Content

A Smart, Safe Wheelchair for Kids Who Can’t Walk

The tricked-out wheelchair can predict and avoid collisions.
September 28, 2012

By the age of five, most kids have outgrown the bumping-into-things phase of childhood. But most adults would agree that they’re still too young to get their own set of wheels.

This is a problem for young children with disabilities as they don’t get their first run in a wheelchair until they’re well over five years old. This limits how independent they are in their younger days, and how comfortable they are with moving around when they’re older.

Harold Soh, an electrical engineer at Imperial College London, is building a smart wheelchair named ARTY with navigation features that could let young kids to move around in a wheelchair safely.

ARTY is short for “Assistive Robotic Transport for Youngsters” and is designed to help kids who have trouble judging distances and depth navigate safely. As a graduate student at the Personal Robotics Lab of Yiannis Demiris, Soh has been working on ARTY for almost three years.

ARTY is really a tricked out version Skippi, a commercially sold pediatric motorized wheelchair. But ARTY is outfitted with three laser scanners and five bump sensors that feed information about its surroundings into a two micro-PCs and a tablet mounted on the wheelchair.

Soh has designed software that makes sense of the distance and spatial data picked up by ARTY’s sensors. As ARTY moves around, its intelligent electronics predicts impending collisions and adjusts the speed and direction to avoid nasty bumps. The level to which ARTY interferes with the driver’s commands can be scaled up, or scaled back.

ARTY was recently out for test runs with eight healthy 11-year-olds, and one five-year-old with special needs. The five-year-old’s occupational therapist had considered him too young for a wheelchair, and his experience with ARTY was a first. After a series of short supervised test run on his own (where ARTY was set to a very low velocity), his therapists regarded the experiment a success overall, Soh and Demiris triumphantly note in their paper, which they are due to present at Intelligent Robots and Systems conference next month.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

OpenAI teases an amazing new generative video model called Sora

The firm is sharing Sora with a small group of safety testers but the rest of us will have to wait to learn more.

Google’s Gemini is now in everything. Here’s how you can try it out.

Gmail, Docs, and more will now come with Gemini baked in. But Europeans will have to wait before they can download the app.

This baby with a head camera helped teach an AI how kids learn language

A neural network trained on the experiences of a single young child managed to learn one of the core components of language: how to match words to the objects they represent.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.