Localisation under Large Appearance Change

dc.contributor.advisorAmayo, Paul
dc.contributor.authorChurch, Matthew
dc.date.accessioned2024-07-05T13:06:04Z
dc.date.available2024-07-05T13:06:04Z
dc.date.issued2024
dc.date.updated2024-07-02T14:04:32Z
dc.description.abstractLocalisation is a foundational building block for more complex robot applications, and thus if low-cost localisation solutions can be found, the number of activities a robot can undertake will increase. However, appearance-based localisation systems in the past have required frequent traversals of the environment in order to sufficiently capture the change indicative of that environment. There are applications such as agriculture in which this frequent data collection is not appropriate. This thesis presents an appearance-based localisation system that combines generated and recorded data in the form of experience-localiser pairs combined to create an experience based network that can be used for localisation. The inclusion of generated data reduces the requirement for frequent data collection, provided an adequate generation model can be trained. The experience, which is a collection of images and transforms describing a traversal of an environment is the primary means through which this generation of data can influence the network. The images contained in the generated experiences were created from two parent experiences capturing two specific times of the day. The network trained learns a mapping from the two parent experiences creating intermediate domains that represent times between the parents, effectively filling in the gaps left by sparse data collection. While the performance of the generation network narrows the functional scope of the system, within that narrow scope, experiences generated from recorded outings outperform the recorded counterparts provided the parent does as well, such that an experience generated from a recording collected at 10:00 and made to mimic the conditions at 14:00 will outperform the recording collected at 14:00. Should a version be used such that all recorded experiences are utilized as a collective, the system outperforms that of a system making use of just recorded data
dc.identifier.apacitationChurch, M. (2024). <i>Localisation under Large Appearance Change</i>. (). ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering. Retrieved from http://hdl.handle.net/11427/40401en_ZA
dc.identifier.chicagocitationChurch, Matthew. <i>"Localisation under Large Appearance Change."</i> ., ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering, 2024. http://hdl.handle.net/11427/40401en_ZA
dc.identifier.citationChurch, M. 2024. Localisation under Large Appearance Change. . ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering. http://hdl.handle.net/11427/40401en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Church, Matthew AB - Localisation is a foundational building block for more complex robot applications, and thus if low-cost localisation solutions can be found, the number of activities a robot can undertake will increase. However, appearance-based localisation systems in the past have required frequent traversals of the environment in order to sufficiently capture the change indicative of that environment. There are applications such as agriculture in which this frequent data collection is not appropriate. This thesis presents an appearance-based localisation system that combines generated and recorded data in the form of experience-localiser pairs combined to create an experience based network that can be used for localisation. The inclusion of generated data reduces the requirement for frequent data collection, provided an adequate generation model can be trained. The experience, which is a collection of images and transforms describing a traversal of an environment is the primary means through which this generation of data can influence the network. The images contained in the generated experiences were created from two parent experiences capturing two specific times of the day. The network trained learns a mapping from the two parent experiences creating intermediate domains that represent times between the parents, effectively filling in the gaps left by sparse data collection. While the performance of the generation network narrows the functional scope of the system, within that narrow scope, experiences generated from recorded outings outperform the recorded counterparts provided the parent does as well, such that an experience generated from a recording collected at 10:00 and made to mimic the conditions at 14:00 will outperform the recording collected at 14:00. Should a version be used such that all recorded experiences are utilized as a collective, the system outperforms that of a system making use of just recorded data DA - 2024 DB - OpenUCT DP - University of Cape Town KW - Engineering LK - https://open.uct.ac.za PY - 2024 T1 - Localisation under Large Appearance Change TI - Localisation under Large Appearance Change UR - http://hdl.handle.net/11427/40401 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/40401
dc.identifier.vancouvercitationChurch M. Localisation under Large Appearance Change. []. ,Faculty of Engineering and the Built Environment ,Department of Electrical Engineering, 2024 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/40401en_ZA
dc.language.rfc3066Eng
dc.publisher.departmentDepartment of Electrical Engineering
dc.publisher.facultyFaculty of Engineering and the Built Environment
dc.subjectEngineering
dc.titleLocalisation under Large Appearance Change
dc.typeThesis / Dissertation
dc.type.qualificationlevelMasters
dc.type.qualificationlevelMSc
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
thesis_ebe_2024_church matthew.pdf
Size:
205.52 MB
Format:
Adobe Portable Document Format
Description:
License bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.72 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections