Towards a Visual Simultaneous Localization and Mapping System for Computationally Constrained Systems

Future robotic planetary exploration missions such as sample retrieval and in-situ resource utilization will require more accurate localization techniques such as Simultaneous Localization and Mapping (SLAM) to achieve the science goals. In this thesis, a visual SLAM system aimed towards computationally constrained systems is presented. In this work, Binary Robust Invariant Scalable Keypoints (BRISK) and Oriented FAST and Rotated BRIEF (ORB) feature descriptors are introduced and compared against Speeded Up Robust Features (SURF). BRISK is shown to achieve similar relative pose estimation performance than SURF while being an order of magnitude faster. This work also discusses a simple back-end pose-graph optimization approach using libg2o. The back end system improved the position estimation as well as detected loop closure events. These initial results show that computationally inexpensive feature detectors such as BRISK and ORB can be used as core feature detection algorithms for a visual SLAM system.

Name thesis:degree_name

Master of Applied Science (M.App.Sc.)

Level thesis:degree_level

Master's

Discipline thesis:degree_discipline

Engineering, Aerospace

Grantor dc:publisher

Carleton University

Year dc:date.issued

2015

Author dc:creator

• Molina Cabrera, Pablo Roberto

Statement dc:rights

• Copyright © 2015 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, research, scholarship, and teaching. Theses may only be shared by linking to Carleton University Institutional Repository and no part may be used without proper attribution to the author. No part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.

Language dc:language.iso

en

DOI

10.22215/etd/2015-10849

OAI identifier oai:identifier

oai:carleton.scholaris.ca:20.500.14718/39260