SEMINAR: Statistics Seminar

Simultaneous Localisation and Mapping (SLAM) refers to the techniques used by autonomous robots to build a map within an unknown environment while at the same time keeping track of their current locations. This problem requires an appropriate mathematical representation of the vehicle's surroundings (the map) in the presence of sensing/feature detection uncertainties such as false positives, missed detections and spatial errors. Significant research activity now exists in representing both measurements and the map as spatial point patterns rather than the conventional vector representation. This is not merely a triviality of representation, but is fundamental from an estimation view point. Recent research has also shown that a spatial point process (or random finite set) formulation can eliminate the necessity of fragile map management and feature association algorithms. This talk provides an introduction to SLAM and the spatial point process framework for solving the problem.

About the speaker: Ba-Ngu Vo received his Bachelor degrees jointly in Science and Electrical Engineering with first class honours from UWA in 1994, and PhD from Curtin in 1997. He had held various research positions before joining the department of Electrical and Electronic Engineering at the University of Melbourne in 2000. He joined UWA in 2010 and is currently with Curtin University. Ba-Ngu is a recipient of the Australian Research Council’s inaugural Future Fellowship and the 2010 Australian Museum Eureka Prize for Outstanding Science in support of Defense or National Security. His research interests are signal processing, systems theory and stochastic geometry with emphasis on target tracking, robotics and computer vision.