Latest in Gear

Image credit: Intel

Intel's AI wheelchair can be controlled by facial expressions

The Wheelie 7 makes the majority of motorized wheelchairs even more accessible.
310 Shares
Share
Tweet
Share
Save
Intel

Motorized wheelchairs are traditionally controlled by a joystick or sensors attached to the user's body, but now innovation in artificial intelligence is helping severely disabled people drive their chairs with their facial expressions.

Working in partnership with Intel, Brazil-based Hoobox Robotics has created the Wheelie 7, a piece of AI-leveraging kit that allows disabled people to control a motorized wheelchair though 10 facial expressions, from raising eyebrows to sticking out tongues.

The tech learns about the user's gestures automatically and takes just seven minutes to install (hence the name "Wheelie 7"). Using an app, the user -- with assistance from a caregiver -- can assign which expressions are linked to the chair's movements. Through a combination of facial recognition software, sensors, robotics and an Intel 3D RealSense Depth Camera that's been mounted on the wheelchair, Wheelie captures a 3D map of the face and uses AI algorithms to process data in real time to direct the wheelchair. The kit works in both sunlight and dim light, and is compatible with 95 percent of motorized wheelchairs currently on the market.

The prototype is currently being tested by more than 60 people in the US, most of whom have quadriplegia, amyotrophic lateral sclerosis or have age-related disabilities. According to the National Spinal Cord Injury Statistical Center, there are around 280,000 people in the US with spinal injuries, and 17,700 new cases every year.

"The Wheelie 7 is the first product to use facial expressions to control a wheelchair. This requires incredible precision and accuracy, and it would not be possible without Intel technology," said Dr. Paulo Pinheiro, co-founder and CEO of HOOBOX Robotics. "We are helping people regain their autonomy."

From around the web

ear iconeye icontext filevr