Optimizing urban mobility: a multi-objective AI-powered personalised pedestrian route planning system

Adel Saharkhiz, Maryam

Optimizing urban mobility: a multi-objective AI-powered personalised pedestrian route planning system

Adel Saharkhiz, Maryam

Permalink

Publication Type:: Thesis
Issue Date:: 2025

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (8.57 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Adel Saharkhiz, Maryam
dc.date.accessioned	2025-11-04T03:46:59Z
dc.date.available	2025-11-04T03:46:59Z
dc.date.issued	2025
dc.identifier.uri	http://hdl.handle.net/10453/190611
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	This thesis presents a comprehensive exploration into pedestrian navigation systems, addressing critical shortcomings and redefining the landscape of pedestrian route planning. Grounded in a systematic analysis of existing literature and research gaps, the study establishes clear and focused objectives to develop an innovative and adaptive route optimization solution. The research introduces a Personalised Multi-Objective Pedestrian Route Planning System, designed to generate safe, accessible, attractive, comfortable, and overall pedestrian-friendly route by balancing multiple conflicting objectives such as safety, attractiveness, comfort, and accessibility. To ensure practical applicability, a post-optimization process is applied to select the most suitable solution from the generated Pareto front, aligning with pedestrian preferences. Key contributions include the development of comprehensive hierarchical taxonomies for categorizing route choice factors by pedestrians, a novel multi-objective pedestrian route planning problem along with associated model and framework, and an advanced GIS-based methodology for pedestrian network data preparation. The study also integrates metaheuristic algorithms, particularly Pareto-Based Multi-Objective Ant Colony Optimization (PB-MOACO) algorithm, to enhance decision-making in route selection. The effectiveness of PB-MOACO is validated through a comparative evaluation against two benchmark algorithms: Multi-Objective ACO via Weighted Aggregation (MOACO-WA) expanded and customised for this study and Dijkstra’s algorithm. Results demonstrate that PB-MOACO outperforms both benchmarks in generating safer, comfier and more pedestrian-friendly routes while maintaining reasonable computing times. Real-world validation using truth data (actual path lengths, safety conditions, comfort attributes, scenic status along the route) further confirms the superiority of the proposed approach over traditional methods. Beyond academic contributions, this research has practical implications for urban mobility planning, pedestrian safety, and intelligent transportation systems. By addressing the limitations of existing pedestrian navigation systems and introducing an adaptive, user-centric approach, this study enhances personalized pedestrian routing, offering a more efficient, flexible, and safer navigation experience.	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/10453/190611/1/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	© 2025 Maryam Adel Saharkhiz
dc.rights	au.edu.uts.lib/cph
dc.title	Optimizing urban mobility: a multi-objective AI-powered personalised pedestrian route planning system	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

This thesis presents a comprehensive exploration into pedestrian navigation systems, addressing critical shortcomings and redefining the landscape of pedestrian route planning. Grounded in a systematic analysis of existing literature and research gaps, the study establishes clear and focused objectives to develop an innovative and adaptive route optimization solution. The research introduces a Personalised Multi-Objective Pedestrian Route Planning System, designed to generate safe, accessible, attractive, comfortable, and overall pedestrian-friendly route by balancing multiple conflicting objectives such as safety, attractiveness, comfort, and accessibility. To ensure practical applicability, a post-optimization process is applied to select the most suitable solution from the generated Pareto front, aligning with pedestrian preferences. Key contributions include the development of comprehensive hierarchical taxonomies for categorizing route choice factors by pedestrians, a novel multi-objective pedestrian route planning problem along with associated model and framework, and an advanced GIS-based methodology for pedestrian network data preparation. The study also integrates metaheuristic algorithms, particularly Pareto-Based Multi-Objective Ant Colony Optimization (PB-MOACO) algorithm, to enhance decision-making in route selection. The effectiveness of PB-MOACO is validated through a comparative evaluation against two benchmark algorithms: Multi-Objective ACO via Weighted Aggregation (MOACO-WA) expanded and customised for this study and Dijkstra’s algorithm. Results demonstrate that PB-MOACO outperforms both benchmarks in generating safer, comfier and more pedestrian-friendly routes while maintaining reasonable computing times. Real-world validation using truth data (actual path lengths, safety conditions, comfort attributes, scenic status along the route) further confirms the superiority of the proposed approach over traditional methods. Beyond academic contributions, this research has practical implications for urban mobility planning, pedestrian safety, and intelligent transportation systems. By addressing the limitations of existing pedestrian navigation systems and introducing an adaptive, user-centric approach, this study enhances personalized pedestrian routing, offering a more efficient, flexible, and safer navigation experience.

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

http://hdl.handle.net/10453/190611