Planned perception within concurrent mapping and localization
Loading...
Authors
Slavik, Michael P.
Subjects
Advisors
Date of Issue
2002-06
Date
2002
Publisher
Language
Abstract
The fundamental requirement of truly autonomous mobile robots is navigation. Navigation is the science of determining one's position and orientation based on information provided by various sensors. Mobile robot navigation, especially autonomous vehicle navigation, is confronted with the problem of attempting to determine the structure of an a priori unknown environment, while at the same time using this information for navigation purposes. This problem is referred to as concurrent mapping and localization (CML). This thesis addresses the question of how to improve CML performance through smarter sensing strategies affecting robot behavior. Planned perception is the process of adaptively determining the sensing strategy of the mobile robot. The goal of integrating planned perception within concurrent mapping and localization is to attempt to answer the question of how a mobile robot should behave so as to attempt to optimize CML performance. This thesis demonstrates in simulation how the CML framework could be improved with planned perception by motivating changes in robot pose and hence, sensing locale.
Type
Thesis
Description
Series/Report No
Department
Massachusetts Institute of Technology
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
132 p. : ill. (some col.) ; 28 cm.
Citation
Distribution Statement
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.