This lab is headed by Dr.
John S. Zelek.
Our research interests can be summarized as the investigation of intelligent
Mechatronic control systems. With regards to sensing, we are interested in
spatial localization (i.e., world co-ordinates, ego-centric co-ordinates,
obstacle and terrain mapping) with complex sensing arrays such as ones found
in camera systems. With regards to actuation, we are interested in both locomotion
(e.g., wheeled robot vehicles) and haptics (i.e., providing augmented feedback
to humans in the control loop via the cutaneous and kinesthetic senses).
Temporal state space estimation is achieved via a Particle filter, which
maintains multiple hypotheses and probabilistic state distributions,
adhering to the principle of least commitment. Particle filters are
compromising techniques for solving the integrals in optimal or Bayesian
filtering in state space models by replacing the complicated posterior densities
involved by discrete approximations based on particles. The system is
Mechatronic because it is complex, a synergistic integration of inter-disciplinary
areas and it involves a concurrent design process with the potential of domain
substitution and constraints in power, weight, cost, computational performance, etc.
Our main research areas include: (1) wearable sensory substitution (touch via
vibro-tactile stimulation for vision) for applications such as an aid for people
who are visually impaired or blind or for augmentation where spatial localization
is problematic; (2) dynamic probabilistic computer vision techniques; (3) mobile
robot navigation; and (4) human-robot interaction.
We are also part of the
ISL
(Intelligent Systems Lab) and collaborate with its members on various projects.
Comments, questions, suggestions?
Contact me at: jzelek@uoguelph.ca School of Engineering
University of Guelph
Guelph, ON, N1G 2W1
tel: (519)-824-4210, ext. 3916
fax: (519)-836-0227
E-mail: jzelek@uoguelph.ca