In the latest episode of Approximately Correct, we explore the importance of human-centered AI research with Amii Fellow and Canada CIFAR AI Chair Patrick Pilarski. 

He co-leads the Bionic Limbs for Improved Natural Control Lab at the University of Alberta, developing groundbreaking AI technology to control prosthetic limbs in ways that were previously impossible.

The BLINC lab takes a unique approach to its research, fostering a partnership between researchers and test pilots with participatory design in research that could be a model for the way research is done in the future..

This collaboration is key to BLINC Lab’s work. By thinking of the test pilot more as a part of the research team, they gain a deeper understanding of their needs and perspectives of people with limb difference,  creating AI systems that are more intuitive and effective.  

"It's all about helping people intuitively control these devices that they use in their daily life," says Pilarski.

 "Instead of having to think hard about the device and its control, it’s about what they're actually trying to achieve and how they're trying to express themselves."  

Pilarski says this approach is an alternative to traditional research methods, which can sometimes miss out on the unique perspectives and valuable information that can come from research participants and test pilots. And that is vital for creating AI systems and technologies that are focused on the human experience. 

Listen or watch the full interview to learn more about the work being done at BLINC Lab, and to hear Pilarki talk about the surprising insights that his team gathered while competing in Cybathlon, an international competition for prosthetic limb design, this past fall. 

Approximately Correct: An AI Podcast from Amii is hosted by Alona Fyshe and Scott Lilwall. It is produced by Lynda Vang, with video production by Chris Onciul. Subscribe to the podcast on Apple Podcasts or Spotify.