SmartArm’s AI-powered prosthesis takes the prize at Microsoft’s Imagine Cup

A pair of Canadian students making a simple, inexpensive prosthetic arm have taken home the grand prize at Microsoft’s Imagine Cup, a global startup competition the company holds yearly. SmartArm will receive $85,000, a mentoring session with CEO Satya Nadella, and some other Microsoft goodies. But they were far from the only worthy team from the dozens that came to Redmond to compete.

The Imagine Cup is an event I personally look forward to, because it consists entirely of smart young students, usually engineers and designers themselves (not yet “serial entrepreneurs”) and often aiming to solve real-world problems.

In the semi-finals I attended, I saw a pair of young women from Pakistan looking to reduce stillbirth rates with a new pregnancy monitor, an automated eye-checking device that can be deployed anywhere and used by anyone, and an autonomous monitor for water tanks in drought-stricken areas. When I was their age, I was living at my mom’s house, getting really good at Mario Kart for SNES and working as a preschool teacher.

Even Nadella bowed before their ambitions in his appearance on stage at the final event this morning.

“Last night I was thinking, ‘What advice can I give people who have accomplished so much at such a young age?’ And I said, I should go back to when I was your age and doing great things. Then I realized…I definitely wouldn’t have made these finals.”

That got a laugh, but (with apologies to Nadella) it’s probably true. Students today have unbelievable resources available to them and as many of the teams demonstrated, they’re making excellent use of those resources.

SmartArm in particular combines a clever approach with state of the art tech in a way that’s so simple it’s almost ridiculous.

The issue they saw as needing a new approach is prosthetic arms, which as they pointed out are often either non-functional (think just a plastic arm or simple flexion-based gripper) or highly expensive (a mechanical arm might cost tens of thousands). Why can’t one be both?

Their solution is an extremely interesting and timely one: a relatively simply actuated 3D-printed forearm and hand that has its own vision system built in. A camera built into the palm captures an image of the item the user aims to pick up, and quickly classifies it — an apple, a key ring, a pen — and selects the correct grip for that object.