Simultaneous localization and mapping with omnidirectional vision

• Grant number: 06/05293-2
• Support Opportunities: Scholarships in Brazil - Master
• Start date: March 01, 2007
• End date: August 31, 2008
• Field of knowledge: Engineering - Mechanical Engineering
• Principal Investigator: Jun Okamoto Junior
• Grantee: Vitor Campanholo Guizilini
• Host Institution: Escola Politécnica (EP). Universidade de São Paulo (USP). São Paulo , SP, Brazil

Abstract

One of the fundamental problems of mobile robots nowadays is the simultaneous localization and mapping in an unknown environment from which no previous knowledge is available. Knows as the “SLAM” problem, it has been the target of extensive research in the scientific community, looking for a way to allow the implementation of systems with this capacity in a complex and dynamic environment.This work proposes the study and development of a system that solves the problem of SLAM, allowing a robot to navigate in an unknown environment, building dynamically a map at the same time that it localizes itself in the map. The simultaneous approach of this solution will keep the inherent errors small enough to provide good results even after long periods of time and great distances. To increase the information taken from the environment, this work proposes the utilization of a system of visual cues, which will collect information from the environment that can be used to improve the results of the SLAM. This system will allow the robot to recognize other kinds of patterns from the environment, providing other ways to address to the problem of simultaneous localization and mapping.

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

GUIZILINI, Vitor Campanholo. Simultaneous localization and mapping with omnidirectional vision.. 2008. Master's Dissertation - Universidade de São Paulo (USP). Escola Politécnica (EP/BC) São Paulo.