TITLE: AUTONOMOUS NAVIGATION PROBLEMS FOR RESOURCE CONSTRAINED MOBILE ROBOTS USING SINGLE PIXEL CAMERAS.
ABSTRACT: Problems in autonomous navigation are often solved with state of the art
methods and technology. However in the resource constrained setting, standard
tools and algorithms may require modifications, or fundamentally different
approaches may be needed.
My research project focuses on the use of a Single Pixel Camera and variable
resolution optical flow in order to reduce the number of measurements
and overall computational load in acquiring sequences of images, flow fields
and maps of unknown environments. Preliminary results with downsampling
images using wavelet mask patterns show that both estimated flow fields and
reconstructed images can be obtained from very few measurements.
Thus, my further research will study the tradeoff between minimal measurement
acquisition and sufficiently accurate reconstruction of unknown environments
to develop algorithms and accompanying controllers which tackle
increasingly challenging navigation problems.
COMMITTEE: ADVISOR Professor Sean Andersson, ME/SE; Professor John Baillieul, ME/SE/ECE; Professor Roberto Tron, ME/SE