The Sensorimotor Integration & Machine Learning core focuses on enhancing the function and acceptability of advanced assistive devices (e.g., exoskeletons, artificial limbs and neural prostheses) by addressing the human-machine interface, resulting in more efficient cooperative interactions.
This core also aims to reduce the cognitive burden of controlling a device by endowing the devices with intelligence using cutting-edge machine learning approaches.
Validated gaze and movement assessment technology
Effective sensory-motor training strategy for prosthesis control
Studying the effects of an innovative augmented sensory feedback protocol for motor control training using a virtual environment and a desktop mounted robotic arm
Developing an inexpensive, modular prosthetic socket platform to reduce time and resource costs for evaluation of myoelectric control
Conducting studies on lower limb osseointegration (direct skeletal fixation of a prosthesis)
Determining if the use of the 3D-printed modular socket is quantitatively and qualitatively similar to that of a user-specific prosthetic socket
Exploring integration of sensory feedback systems into our modular sockets
Development and translation of the Gaze and Movement Analysis (GaMA), a novel testing protocol using synchronized motion and eye tracking to explore and quantify human visual-motor behaviour during goal-directed reaching tasks
Translation of this metric to other sites in North America
Modular prosthetic limb
Bipedal robots
Wireless electromyography systems
Real-time machine learning
Brachioplexus
Mac mini servers
3D printer
Eye tracking system
Bento arm
Handi-hand
Cyberglove