Simultaneous localization and mapping for autonomous robot navigation in a dynamic noisy environment

Simple item page
dc.contributor.authorAgunbiade, Olusanya Yinka
dc.contributor.promoterZuva, T., Prof.
dc.date.accessioned2022-12-05T00:20:56Z
dc.date.available2022-12-05T00:20:56Z
dc.date.issued2019-11
dc.descriptionD. Tech. (Department of Information Technology, Faculty of Applied and Computer Sciences), Vaal University of Technology.en_US
dc.description.abstractSimultaneous Localization and Mapping (SLAM) is a significant problem that has been extensively researched in robotics. Its contribution to autonomous robot navigation has attracted researchers towards focusing on this area. In the past, various techniques have been proposed to address SLAM problem with remarkable achievements but there are several factors having the capability to degrade the effectiveness of SLAM technique. These factors include environmental noises (light intensity and shadow), dynamic environment, kidnap robot and computational cost. These problems create inconsistency that can lead to erroneous results in implementation. In the attempt of addressing these problems, a novel SLAM technique Known as DIK-SLAM was proposed. The DIK-SLAM is a SLAM technique upgraded with filtering algorithms and several re-modifications of Monte-Carlo algorithm to increase its robustness while taking into consideration the computational complexity. The morphological technique and Normalized Differences Index (NDI) are filters introduced to the novel technique to overcome shadow. The dark channel model and specular-to-diffuse are filters introduced to overcome light intensity. These filters are operating in parallel since the computational cost is a concern. The re-modified Monte-Carlo algorithm based on initial localization and grid map technique was introduced to overcome the issue of kidnap problem and dynamic environment respectively. In this study, publicly available dataset (TUM-RGBD) and a privately generated dataset from of a university in South Africa were employed for evaluation of the filtering algorithms. Experiments were carried out using Matlab simulation and were evaluated using quantitative and qualitative methods. Experimental results obtained showed an improved performance of DIK-SLAM when compared with the original Monte Carlo algorithm and another available SLAM technique in literature. The DIK-SLAM algorithm discussed in this study has the potential of improving autonomous robot navigation, path planning, and exploration while it reduces robot accident rates and human injuries.en_US
dc.identifier.urihttp://hdl.handle.net/10352/553
dc.language.isoenen_US
dc.publisherVaal University of Technologyen_US
dc.subjectAutonomous roboten_US
dc.subjectTrajectoryen_US
dc.subjectNavigationen_US
dc.subjectFiltering Algorithmen_US
dc.subjectKidnap problemen_US
dc.subjectDynamic Environmenten_US
dc.subjectSimultaneous Localizationen_US
dc.subjectMappingen_US
dc.subject.lcshDissertations, Academic -- South Africaen_US
dc.subject.lcshComputer Communication Networksen_US
dc.subject.lcshAlgorithmen_US
dc.subject.lcshRoboticsen_US
dc.subject.lcshDigital mappingen_US
dc.subject.lcshAutonomous roboten_US
dc.titleSimultaneous localization and mapping for autonomous robot navigation in a dynamic noisy environmenten_US
dc.title.alternativeSimultaneous localization and mapping for autonomous robot navigation in a dynamic noisy environmenten_US
dc.typeThesisen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Agunbiade Olusanya Yinka Final D.Tech thesis Examiner correction.docx.pdf
Size:
2.83 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.02 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Theses and Dissertations (Information Communication Technology)