The July 2022 issue of IEEE Spectrum is here!

Close bar

Startup Spotlight: Kinova Creating Robot Arms That Improve Lives

This Canadian company wants to build the best assistive robots for the disabled

3 min read
Startup Spotlight: Kinova Creating Robot Arms That Improve Lives

This is the second post in our Startup Spotlight series featuring new robotics companies from around the world. We’re inviting representatives from the companies to describe their technologies and how they see the marketplace. The views expressed here are solely those of the author and do not represent positions of IEEE Spectrum or the IEEE.

When he was a child, Kinova’s co-founder and CEO Charles Deguire used to spend his summer vacations with his family in the beautiful region of Gaspesie in Quebec, Canada. Among the family members were three uncles who lived with muscular dystrophy. This muscle disease, which weakens the musculoskeletal system, caused Charles’ uncles to live confined in power wheelchairs controlled only with the small residual movements left in their fingers. Charles learned at a young age all the challenges that people in wheelchairs face on a daily basis.

Startup Spotlight: Kinova

Kinova Robotics

Founded: May 2006

Location:Montreal, Canada.

Focus: Assistive robotics

Founders:Charles Deguire, Louis-Joseph Caron-L’Écuyer

Funding:Angel funding

Fun Fact:The company’s robotic arm, Jaco, is named after one of the founder’s uncles, who was an inventor and build an early robotic arm himself

One of these uncles, Jacques Forest, nicknamed Jaco, was an inventor. Jaco was constantly having new ideas. In the 1980s, he decided to build a mechanical arm to help him accomplish daily tasks. Using windshield wiper motors, bicycle wires, Luxo lamp parts, and a hot-dog claw as a gripper, he was able to build an arm that let him drink a glass of water by himself. Certainly the design wasn’t the most elegant and the control was quite rudimentary, but Jaco showed how technology could significantly improve the quality of life of upper-body disabled persons.

Two decades later, while Charles was studying electrical engineering at l’École de Technologie Supérieure, his mother asked if he ever thought of continuing his uncle’s project. Not long after, Charles asked his long-time friend and university colleague Louis-Joseph Caron-L’Écuyer (now Kinova’s CTO) to start this adventure with him. The goal: creating the best assistive robot for upper-body disabled people.

Thus was born Kinova and its first creation, the robotic arm Jaco, names after Charles’ now-deceased uncle.

It was clear from the start that Kinova should focus on building a robot specifically designed for its users: a system that both answers their needs and respects their condition. The company quickly discarded using existing robotic components or retrofitting available manipulators: those options wouldn’t be able to meet all requirements. These included a light and compact design that wouldn’t change the wheelchair balance and width. The arm also had to be able to pick a wide variety of objects, feature an intuitive control system, and be weatherproof, reliable, and easy and quick to install and repair.

It took four years to overcome all the technical challenges. From the basement of the university incubator, the two young entrepreneurs had to develop a complex carbon fiber molding process, used to build intricately shaped parts, as well as a control approach simple enough to be mastered even by users with only limited finger movements.

Jaco was introduced in the rehabilitation market in 2010 (the video below showcases the arm’s capabilities and how it can help users in different situations).

In 2012, Kinova demonstrated the Jaco Research Edition to the IEEE research community at the 2012 IEEE International Conference on Robotics and Automation (ICRA), in St-Paul, Minn. By adding the necessary programming tools to Jaco, the platform became a versatile solution for a broad range of research topics: mobile manipulation, automated grasping, brain-machine interfaces, and others.

Kinova now has sold over 150 Jaco units. The company, which currently employs 20 people, intends to expand its product line for manipulation in the next few years. At ICRA 2013, in May, Kinova will unveil its brand new manipulation solution for the research community.

Francois Boucher is business development director at Kinova, in Montreal, Canada.

The Conversation (0)

How the U.S. Army Is Turning Robots Into Team Players

Engineers battle the limits of deep learning for battlefield bots

11 min read
Robot with threads near a fallen branch

RoMan, the Army Research Laboratory's robotic manipulator, considers the best way to grasp and move a tree branch at the Adelphi Laboratory Center, in Maryland.

Evan Ackerman
LightGreen

“I should probably not be standing this close," I think to myself, as the robot slowly approaches a large tree branch on the floor in front of me. It's not the size of the branch that makes me nervous—it's that the robot is operating autonomously, and that while I know what it's supposed to do, I'm not entirely sure what it will do. If everything works the way the roboticists at the U.S. Army Research Laboratory (ARL) in Adelphi, Md., expect, the robot will identify the branch, grasp it, and drag it out of the way. These folks know what they're doing, but I've spent enough time around robots that I take a small step backwards anyway.

This article is part of our special report on AI, “The Great AI Reckoning.”

The robot, named RoMan, for Robotic Manipulator, is about the size of a large lawn mower, with a tracked base that helps it handle most kinds of terrain. At the front, it has a squat torso equipped with cameras and depth sensors, as well as a pair of arms that were harvested from a prototype disaster-response robot originally developed at NASA's Jet Propulsion Laboratory for a DARPA robotics competition. RoMan's job today is roadway clearing, a multistep task that ARL wants the robot to complete as autonomously as possible. Instead of instructing the robot to grasp specific objects in specific ways and move them to specific places, the operators tell RoMan to "go clear a path." It's then up to the robot to make all the decisions necessary to achieve that objective.

Keep Reading ↓Show less