My Research

Research Statement

My research interests can be summarized as the investigation of intelligent Mechatronic control systems. With regards to sensing, I am 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, I am 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). In particular, my interest in haptics is focused on vibrotactile stimulation, its control, measurement and preception and the effects of mediums in direct contact (e.g., skin, clothing) and indirect (e.g., muscle movements) have on the stimulus and measurement processes. 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. My 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) haptics; (3) dynamic probabilistic computer vision techniques; (4) mobile robot navigation; and (5) human-robot interaction.