UW developing robotic exoskeleton using AI and cameras

Researchers at the University of Waterloo are developing robotic exoskeleton legs capable of making controlled decisions using AI technology.

The exoskeleton would be applied to someone's legs and essentially, it would do the walking for you.

Built with cameras and fused with Artificial Intelligence, it would make the wearer able to walk without fail.

The project is called ExoNet.

Brokoslaw Laschowski, a PhD candidate in systems design engineering who leads ExoNet tells 570 NEWS prior tech would require joysticks and manual movements for someone to walk.

“These manual control systems are inconvenient and time consuming and even cognitively demanding,” says Laschowski. “My work focuses on developing autonomous controlled systems, so that robotic exoskeletons can think and control themselves.”

Laschowski says walking is dictated by the surrounding environment, so there are extra sensors on the exoskeleton to help make it happen. 

“There are also other sensors on the exoskeleton to tell you its current state. Then the wearable camera provides future state information.”

He says these robotic legs are equivalent to the tech you see in self-driving cars.

“So, autonomous cars make use of cameras as well as artificial intelligence to decode those images and use that information to autonomously drive the car. We're essentially doing a similar thing with robotic exoskeletons, which have never been done before.”

The next phase of the ExoNet research project will involve sending instructions to motors so that robotic exoskeletons can climb stairs, avoid obstacles or take other appropriate actions based on analysis of the user's current movement and the upcoming terrain.

The research team also includes engineering professor Alexander Wong, the Canada Research Chair in Artificial Intelligence and Medical Imaging, and William McNally, also a PhD candidate in systems design engineering and a student member of Waterloo.ai.