test Browse by Author Names Browse by Titles of Works Browse by Subjects of Works Browse by Issue Dates of Works

Advanced Search
& Collections
Issue Date   
Sign on to:   
Receive email
My Account
authorized users
Edit Profile   
About T-Space   

T-Space at The University of Toronto Libraries >
School of Graduate Studies - Theses >
Doctoral >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1807/17251

Title: MILATRAS: MIcrosimulation Learning-based Approach to TRansit ASsignment
Authors: Wahba, Mohamed Medhat Amin Abdel-Latif
Advisor: Shalaby, Amer Saïd
Department: Civil Engineering
Keywords: Public Transportation
Intelligent Transportation Systems
Reinforcement Learning
Transit Assignment
Traveller Behaviour
Issue Date: 26-Feb-2009
Abstract: Public transit is considered a cost-effective alternative to mitigate the effects of traffic gridlock through the implementation of innovative service designs, and deploying new smart systems for operations control and traveller information. Public transport planners use transit assignment models to predict passenger loads and levels of service. Existing transit assignment approaches have limitations in evaluating the effects of information technologies, since they are neither sensitive to the types of information that may be provided to travellers nor to the traveller’s response to that information. Moreover, they are not adequate for evaluating the impacts of Intelligent Transportation Systems (ITS) deployments on service reliability, which in turn affect passengers’ behaviour. This dissertation presents an innovative transit assignment framework, namely the MIcrosimulation Learning-based Approach to TRansit ASsignment – MILATRAS. MILATRAS uses learning and adaptation to represent the dynamic feedback of passengers’ trip choices and their adaptation to service performance. Individual passengers adjust their behaviour (i.e. trip choices) according to their experience with the transit system performance. MILATRAS introduces the concept of ‘mental model’ to maintain and distinguish between the individual’s experience with service performance and the information provided about system conditions. A dynamic transit path choice model is developed using concepts of Markovian Decision Process (MDP) and Reinforcement Learning (RL). It addresses the departure time and path choices with and without information provision. A parameter-calibration procedure using a generic optimization technique (Genetic Algorithms) is also proposed. A proof-of-concept prototype has been implemented; it investigates the impact of different traveller information provision scenarios on departure time and path choices, and network performance. A large-scale application, including parameter calibration, is conducted for the Toronto Transit Commission (TTC) network. MILATRAS implements a microsimulation, stochastic (nonequilibrium-based) approach for modelling within-day and day-to-day variations in the transit assignment process, where aggregate travel patterns can be extracted from individual choices. MILATRAS addresses many limitations of existing transit assignment models by exploiting methodologies already established in the areas of traffic assignment and travel behaviour modeling. Such approaches include the microsimulation of transportation systems, learning-based algorithms for modelling travel behaviour, agent-based representation for travellers, and the adoption of Geographical Information Systems (GIS). This thesis presents a significant step towards the advancement of the modelling for the transit assignment problem by providing a detailed operational specification for an integrated dynamic modelling framework – MILATRAS.
URI: http://hdl.handle.net/1807/17251
Appears in Collections:Doctoral
Department of Civil Engineering - Doctoral theses

Files in This Item:

File Description SizeFormat
Wahba_Mohamed_M_200811_PhD_thesis.pdf21.52 MBAdobe PDF

This item is licensed under a Creative Commons License
Creative Commons

Items in T-Space are protected by copyright, with all rights reserved, unless otherwise indicated.