Dr. Brokoslaw Laschowski is a computational neuroscientist with expertise in robotics and artificial intelligence. He works as a Research Scientist and Principal Investigator at the Toronto Rehabilitation Institute, Canada’s largest rehabilitation hospital, and a Faculty Member at the University of Toronto with appointments in the Neuroscience Program and the Robotics Institute, where he directs the Neural Robotics Lab. We caught up with him to learn about how he’s working to give robots intelligence by developing artificial brains and by interfacing with the human brain.
What inspired you to pursue this field? Prior to specializing in robotics during my PhD, I completed a master’s in the Department of Mechanical and Mechatronics Engineering at the University of Waterloo, where I studied computational neuroscience and was developing new mathematical models to reverse engineer how the brain controls human movement. This research was part of an academic-industry collaboration with the Canadian Sport Institute and Team Canada wheelchair athletes with neurological disabilities. It was an amazing experience, which inspired me to subsequently combine my background in neuroscience with robotics and artificial intelligence (AI).
How did you become interested in AI? I started my PhD in 2016 in the Department of Systems Design Engineering at the University of Waterloo and the Waterloo Artificial Intelligence Institute, focusing on developing AI-powered control systems for robots used in rehabilitation. At the time, the field was focused on using data from mechanical, inertial, and/or neuromuscular sensors for control. However, data from these sensors have limited prediction horizons, which is somewhat analogous to walking blindfolded. Taking inspiration from how humans use biological vision for control and decision making, I developed the first environment-adaptive controller for robotic prosthetic legs using deep learning, which achieved state-of-the-art performance. Since then, I’ve developed one of the largest programs of research focused on visual perception of walking environments for robot control.
What’s the best part of doing the type of research that you do? The look on people’s faces when they hear I design robots that can think and control themselves using artificial intelligence - Just kidding. Although I’m obviously flattered that many people find our research interesting, my favorite part has been the opportunity to collaborate with interdisciplinary teams and speak with end-users such as persons with physical disabilities and hear their feedback and inspirational stories.
What outcomes do you hope your research will eventually lead to? In addition to autonomous control using computer vision (i.e., similar to self-driving cars), I’m also working on developing myoelectric and brain-machine interfaces for neural control. This dichotomy has implications for control along a spectrum of autonomy, where on one end, the robots can think and control themselves using artificial brains, and on the other end, the robots are controlled by the human brain. The long-term vision for my research program is to study what level of control (or autonomy) do individual users prefer, which remains one of the major unsolved research questions in my field.
Are you working on anything right now that you're really excited about? I’m the co-founder and director of the summer research programin the Department of Computer Science at the University of Toronto for student refugees from Ukraine. Our program is funded by theVector Institute for Artificial Intelligence. To date, we have flown over and funded more than 60 students, the majority being women, from various universities throughout Ukraine. This outreach program gives students an opportunity to continue their research and education despite the ongoing Russian invasion. If any T-CAIREM members are interested to learn more about our research or would like to get involved in assisting displaced students from Ukraine, please email me.
