Electric wheelchairs first came on the scene in the 1950s, pioneered by Canadian inventor, George Klein and a team of engineers working for the National Research Council of Canada in a program to assist veterans returning after World War II.
The technology has remained basically the same ever since Everest & Jennings began mass manufacturing them in 1956. Most electric wheelchairs are generally powered using a joystick. For those users with multiple sclerosis, amyotrophic lateral sclerosis (ALS, also known as Lou Gherig’s disease), spinal cord injuries, and Parkinson’s Disease, a device called a Sip-and-Puff (SNP) controller is available.
Better mobility through robotic automation
In 2015, researchers at the University of Toronto’s Engineering Department and the Institute for Aerospace Studies (UTIAS), an advanced research facility for aeronautics and aerospace engineering, collaborated with Cyberworks Robotics, Inc, and François Michaud and his team at the Université de Sherbrooke to find a way to give electric wheelchairs more mobility.
Robotic automation was the obvious choice, and there are several groups around the world working on self-driving wheelchairs. “Imagine parking a car in a tight space using only a tiny joystick,” says Professor Jonathan Kelly (UTIAS), who is leading the new collaboration. “That would be annoying for anyone.”
Professor Kelly cites Microsoft Kinect platform, which has both a visible-spectrum camera and an infrared laser to detect distances. “Sensors like that used to cost thousands of dollars, but now you can buy them for less than $200,” says Kelly. “It has been a game-changer for robotics.”
Developed in 2010, Kinect was originally used to enhance people’s interactions with Xbox 360 and Xbox One video game consoles and Microsoft Windows PCs. The Kinect device allows users to control and interact with their console/computer without the need for a game controller, through a natural user interface using gestures and spoken commands.
Kelly was approached by Vivek Burhanpurkar, the CEO of Cyberworks Robotics, Inc. about two years ago. Cyberworks has a long history in autonomous robotics, including self-driving industrial cleaning machines, but they wanted to get into assistive devices.
“It’s only the past five years that we’ve reached a critical inflection point, allowing us to achieve unprecedented levels of autonomous behaviors at consumer level price-points,” says Burhanpurkar, who started Cyberworks after studying under U of T Engineering Professor Emeritus K.C. Smith (ECE). “Jonathan’s group was a natural partner for us because they have the same set of altruistic values and goals as we do. We share a common vision for the future, which is a rare thing between academia and industry.”
The team decided to use an already available electric wheelchair instead of creating one from scratch. So they focused on retrofitted existing chairs with sensors, controllers, and a small computer. The team also spent a good part of the last two years on creating software and developing algorithms to cover many situations a wheelchair user might encounter, such as narrow doorways and obstacles.
“Once we have the user study data, the product is essentially ready for commercialization,” Professor Kelly says. “It wasn’t always easy, but I’ve been really surprised to see how far we’ve come in two years. We’ve had so many talented people working on the project, and now when I see it operating it always brings a smile to my face. I’m super excited about it now.”
Digital Journal spoke with Marit Mitchell, the Communications & Media Relations Strategist with the U of T Engineering Department. She confirmed that the sensor the team used was a Microsoft Kinect and was now in the process of testing the wheelchair in a controlled environment to make sure there are adequate algorithms to cover all the situations a user might encounter.
The one thing that this writer finds particularly fascinating is how artificial intelligence and machine learning plays such a critical role in the finished product, in this case, the self-driving wheelchair. When a user first begins operating the newly developed chair, not only will the user be learning, but the chair’s artificial intelligence will be learning.
It brings to mind a baby surveying its world for the first time and learning by repetition. The more times the chair takes a certain path, the more it will grow in intelligence, knowing where the user wants to go almost immediately.
