IBBRB: Intelligent Blockchain-based Reputation Broker for Robot Selection

Alharbi, Wafa Matar A.

IBBRB: Intelligent Blockchain-based Reputation Broker for Robot Selection

Alharbi, Wafa Matar A.

Permalink

Publication Type:: Thesis
Issue Date:: 2023

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (7.91 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Alharbi, Wafa Matar A.
dc.date.accessioned	2024-04-11T04:57:47Z
dc.date.available	2024-04-11T04:57:47Z
dc.date.issued	2023
dc.identifier.uri	http://hdl.handle.net/10453/177733
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	Robot as a service (RAAS) is a cloud-based subscription service that enables robotic devices to be leased instead of purchased. RAAS has recently increased in popularity due to the advantages that it offers to robotic service requesters such as flexibility, the lower cost of entry/maintenance compared to owning the equipment, and the ease of implementation. The concept of RAAS has contributed to the increased use of robots in different disciplines, such as industry, education, health and agriculture. Robotic service requesters may face difficulties in searching for the most suitable robot for their required tasks based on their preferences. Robot selection has attracted the interest of many researchers. Robot selection is based on ranking the available robotic alternatives after they have been assessed by robotic experts. The assessment process is based on customer requirements as well as the task’s functional and non-functional requirements. However, through a systematic literature review, it has been identified that selecting a robot based on its previous performance in similar tasks has not been discussed yet. Furthermore, all the proposed robot selection methods require robotic experts to determine the requirements and robotic alternatives. To address these issues, this research aims to propose and develop an intelligent blockchain-based reputation broker for robot selection “IBBRB”. IBBRB is an intelligent reputation system that allows robotic service requesters to rate the performance of robots after hiring them. To avoid data manipulation, which is a common issue with reputation systems, blockchain technology is used to store all trust values in IBBRB. IBBRB is built to provide novel and intelligent mechanisms to: (i) standardise robotic knowledge across all robotic service requesters, suppliers and manufacturers by encapsulating all the robotic attributes and their relationships into an ontological manifestation called Robotic Attribute Ontology (RAO), and then to propose a blockchain-based method for RAO evolution using a crowdsourcing approach, (ii) develop a method to carry out robotic reputation computations termed Reliable Reputation Computation Method for Robotics (RRCM). RRCM incorporates building: (a) a reputation model that produces reputation values for robots based on previous customers’ ratings, and (b) a prediction model that predicts reputation values for non-reviewed robots to bootstrap new robots and overcome the cold start issue, (iii) develop a method to infer reputation values for all non-reviewed contexts of multi-purpose robots based on their similarities to the reviewed contexts. Finally, we use software prototyping to validate the performance and accuracy of the aforementioned proposed methods.	en_US.UTF-8
dc.format	Thesis (PhD)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/177733/1/thesis.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	© 2023 Wafa Matar A Alharbi
dc.rights	au.edu.uts.lib/cph
dc.title	IBBRB: Intelligent Blockchain-based Reputation Broker for Robot Selection	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

Robot as a service (RAAS) is a cloud-based subscription service that enables robotic devices to be leased instead of purchased. RAAS has recently increased in popularity due to the advantages that it offers to robotic service requesters such as flexibility, the lower cost of entry/maintenance compared to owning the equipment, and the ease of implementation. The concept of RAAS has contributed to the increased use of robots in different disciplines, such as industry, education, health and agriculture. Robotic service requesters may face difficulties in searching for the most suitable robot for their required tasks based on their preferences. Robot selection has attracted the interest of many researchers. Robot selection is based on ranking the available robotic alternatives after they have been assessed by robotic experts. The assessment process is based on customer requirements as well as the task’s functional and non-functional requirements. However, through a systematic literature review, it has been identified that selecting a robot based on its previous performance in similar tasks has not been discussed yet. Furthermore, all the proposed robot selection methods require robotic experts to determine the requirements and robotic alternatives. To address these issues, this research aims to propose and develop an intelligent blockchain-based reputation broker for robot selection “IBBRB”. IBBRB is an intelligent reputation system that allows robotic service requesters to rate the performance of robots after hiring them. To avoid data manipulation, which is a common issue with reputation systems, blockchain technology is used to store all trust values in IBBRB. IBBRB is built to provide novel and intelligent mechanisms to: (i) standardise robotic knowledge across all robotic service requesters, suppliers and manufacturers by encapsulating all the robotic attributes and their relationships into an ontological manifestation called Robotic Attribute Ontology (RAO), and then to propose a blockchain-based method for RAO evolution using a crowdsourcing approach, (ii) develop a method to carry out robotic reputation computations termed Reliable Reputation Computation Method for Robotics (RRCM). RRCM incorporates building: (a) a reputation model that produces reputation values for robots based on previous customers’ ratings, and (b) a prediction model that predicts reputation values for non-reviewed robots to bootstrap new robots and overcome the cold start issue, (iii) develop a method to infer reputation values for all non-reviewed contexts of multi-purpose robots based on their similarities to the reviewed contexts. Finally, we use software prototyping to validate the performance and accuracy of the aforementioned proposed methods.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/177733