Simultaneous localization and mapping with mobile robots in an indoor environment
Speaker: Wenyan Hu, ITEE
When: 2003-10-14 12:00:00
Venue: 78-420
Host: Prof Tom Downs
Abstract:Simultaneous localization and Mapping (SLAM), which addresses the
problem of incrementally building a map of the environment while
concurrently using this map to compute robot location, has received
considerable attention in the past two decades. A variety of
approaches have been developed to seek the solution to this
problem. However, most of the existing methods, except The Extended
Kalman Filters, are not capable of estimating the full posterior
over the SLAM problem in real time. My research will consider
estimating the full posterior from uncertainty data from sonar and
mono-vision sensors. I study particle filters and the occupancy
approach, which are the state-of-the-art approaches in robotics,
propose to decompose the SLAM problem into a robot localization
problem and a collection of landmark estimation problems, employ the
Rao-Blackwellised particle filter and standard occupancy grid
methods to solve them. I also propose employing the occupancy grid
approach to create sonar mapping models, and suggest ways to deal
with sensor noise. I finally discuss the feasibility of combing
sonar array and visual information to a practical SLAM model for
application in an indoor environment
Biography:(biography unavailable)
Type: Ph.D confirmation
Contact:Prof Tom Downs, seminar host (td@csee.uq.edu.au)
or Guido Governatori (ITEE seminar co-ordinator)
(guido@itee.uq.edu.au)