Value of Information in Dispatching Shared Autonomous Mobility-on-demand Systems
Value of Information in Dispatching Shared Autonomous Mobility-on-demand Systems

Author: Jian Wen (S. M.)

Publisher:

Published: 2018

Total Pages: 91

ISBN-13:

DOWNLOAD EBOOK

The concept of shared mobility-on-demand (MoD) systems describes an innovative mode of transportation in which rides are tailored as per the immediate requests in a shared manner. Convenience of hailing, ease of transactions, and economic efficiency of crowd-sourcing the rides have made these services very attractive today. It is anticipated that autonomous vehicle (AV) technology may further improve the economics of such services by reducing the operational costs. The design and operation of such an shared autonomous mobility-on-demand (AMoD) system is therefore an important research direction that requires significant investigation. This thesis mainly addresses three issues revolving around the dispatching strategies of shared AMoD systems. First, it responds to the special dispatching need that is critical for effective AMoD operation. This includes a dynamic request-vehicle assignment heuristic and an optimal rebalancing policy. In addition, the dispatching strategies also reflect transit-oriented designs in two ways: (a) the objective function embodies the considerations of service availability and equity through the support of various hailing policies; and (b), the service facilitates first-mile connections to public transportation. Second, this thesis models the interaction between demand and supply through simulation. Using the level of service as interface, this mechanism enables feedback between operators and travelers to more closely represent the choices of both parties. A fixed-point approach is then applied to reach balance iteratively, estimating both the demand volume and the system performance at equilibrium. The results from the simulation support decision-making with regard to comprehensive system design problems such as fleet sizing, vehicle capacities and hailing policies. Third, the thesis evaluates the value of demand information through simulation experiments. To quantify the system performance gain that can be derived from the demand information, this thesis proposes to study two dimensions, level of information and value of information, and builds up the relationship between them. The numerical results help rationalize the efforts operators should spend on data collection, information inference and advanced dispatching algorithms. This thesis also implements an agent-based modeling platform, amod-abm, for simulating large-scale shared AMoD applications. Specifically, it models individual travelers and vehicles with demand-supply interaction and analyzes system performance through various metrics of indicators. This includes wait time, travel time, detour factor and service rate at the traveler's side, as well as vehicle distance traveled, load and profit at the operator's side. A case study area in London is selected to support the presentation of methodology. Results show that encouraging ride-sharing and allowing in-advance requests are powerful tools to enhance service efficiency and equity. Demand information from in-advance requests also enables the operator to plan service ahead of time, which leads to better performance and higher profit. The thesis concludes that the demand-supply interaction can be effective for defining and assessing the roles of AV technology in our future transportation systems. Combining efficient dispatching strategies and demand information management tools is also important for more affordable and efficient services.

Shared Mobility on Demand System Design
Shared Mobility on Demand System Design

Author: Mohammad Abdollahi (Industrial engineer)

Publisher:

Published: 2021

Total Pages: 0

ISBN-13:

DOWNLOAD EBOOK

Tomorrows mobility will be radically different. Connected, Autonomous, Shared, and Electric Mobility are four main developments that are dramatically altering the automobile industry. We study the shared centralized class of mobility problems which considers a platform of self driving cars. There are new challenges with these systems such as how to balance the idle vehicle, how to price the shared autonomous system, and etc. We are attempting to address the question of how to share passengers ride to maximize satisfaction for riders, and the platform itself. Besides that, to have a good ETA estimate for trips, we develop a data-driven travel time prediction algorithm which can be used in our platform to get a good estimate for scheduling and routing the rides. Finally, we also study the pricing mechanism of these systems using a deep reinforcement learning agent that simulates the rides in New York. We start by studying both static and dynamic (real-time) ride pooling problem with time windows, multiple homogeneous/heterogeneous vehicles, passenger convenience and other business considerations. First, the problems under consideration is modeled as two different static MILP for homogeneous/heterogeneous fleet of vehicles, and also a constraint programming counterpart is provided for the heterogeneous vehicles case. Also to improve the linear relaxation of these models, several pre-processing steps and lifting inequalities are applied. While appealing, exact formulations have integer variables which render them as non-convex optimization problems. Thus, while this approach offers the benefit of system optimality, its formulation here is NP-hard, making it not viable for real world problems. To find a good quality solution, a heuristic decomposition algorithm based on constraint programming and branch and price is proposed to solve static model within a reasonable time for implementation in a real-world situation. Computational results show that the heuristic algorithms are superior compared to the exact algorithms in terms of the calculation time as the problem size (in terms of the number of requests) increases. In phase 2 of this dissertation, we propose a travel time predictive model by developing a integrated multi-step approach to learn the feature space. This multi stage algorithm is initiated by pre-processing task. Subsequently, the feature set is obtained by incorporating some publicly available information. Moreover, a feature engineer ing path is proposed to improve the feature space. This path includes Principal Component Analysis (PCA), geospatial features analysis, and unsupervised learning methods like K-Means and stacked autoencoders. Finally we apply a customized gradient boosting method to estimate travel times and comparing our results with LSTM network which shows superiority of our method in terms of capturing dynamics of traffic through time. Although more data with rare events need to be added in case of experiencing heavy snow or other events which magnifies travel times. Lastly, we developed a fleet management simulation platform where we model pricing problem as a partially observable Markov decision process (POMDP), and DQN agent is developed to estimate fares as a function of real-time interaction with the environment. Fare prices are considered to be continuous and stochastic variables, but for simplicity we have price adjustment in discrete units, and we determine them using a deep neural network (DNN). We compare our algorithm with the one for ride hailing system and see if our pricing mechanism can decrease rejections and cancellation and increase system objective as well as passengers0́9 utility. We illustrate the usefulness of our algorithm by applying it to real-world transportation problem and show that it learns fare estimates to minimize total travel time, maximize revenue, and other weighted objectives. Collectively, this work can be used for designing a ride sharing system of autonomous vehicles in which a controller module with many different predictive and prescriptive analytics engines dispatches vehicles and broadcasts ride fares to optimize system and riders utility.

Simulation-based Design of Integrated Public Transit and Shared Autonomous Mobility-on-demand Systems
Simulation-based Design of Integrated Public Transit and Shared Autonomous Mobility-on-demand Systems

Author: Yu Xin Leo Chen

Publisher:

Published: 2018

Total Pages: 97

ISBN-13:

DOWNLOAD EBOOK

The autonomous vehicle (AV) is poised to be one of the most disruptive technologies in the transportation industry. The advent of three major trends in transportation: automation, on-demand mobility and ride-sharing, are set to revolutionize the way we travel. The forthcoming adoption and commercialization of AVs are expected to have extensive impacts on our road networks, congestion, safety, land use, public transportation (PT) and more. Rapid advances in AV technology are convincing many that AV services will play a significant role in future transportation systems. The advancement of AVs presents both opportunities and threats to transportation. It has the potential to significantly impact traffic congestion, traffic accidents, parking and VMT (vehicle miles traveled), especially for people that are not able to drive such as children and elderly people. Motivated by the potential of autonomous vehicles, authorities around the world are preparing for this revolution in transport and deems this an important research direction that requires significant investigation. This thesis tackled and contributed to three main research questions related to the impact of autonomous vehicles on transportation systems. First, this thesis proposes a simulation-based approach to the design and evaluation of integrated autonomous vehicle and public transportation systems. We highlight the transit-orientation by respecting the social-purpose considerations of transit agencies (such as maintaining service availability and ensuring equity) and identifying the synergistic opportunities between AV and PT. Specifically, we identified that AV has a strong potential to serve first-mile connections to the PT stations and provide efficient and affordable shared mobility in low-density suburban areas that are typically inefficient to serve by conventional fixed-route PT services. The design decisions reflect the interest of multiple stakeholders in the system. Second, the interaction between travelers (demand) and operators (supply) is modeled using a system of equations that is solved as a fixed-point problem through an iterative procedure. In this, we developed demand and supply as two sub-problems. The demand will be predicted using a nested logit model to estimate the volume for different modes based on modal attributes. The supply will use a simulation platform capable of incorporating critical operational decisions on factors including fleet sizes, vehicle capacities, sharing policies, fare schemes and hailing strategies such as in-advance and on-demand requests. Using feedback between demand and supply, we enable interactions between the decisions of the service operator and those of the travelers, in order to model the choices of both parties. Finally, this thesis systematically optimizes service design variables to determine the best outcome in accordance to AV+PT stakeholder goals. Optimization objective functions can be formulated to reflect the different objectives of different stakeholders. In this paper, we specifically propose and develop a simulation-based service design method where we quantify various benefits and costs to reflect the objectives of key AV+PT stakeholders. We simulate the service with different sets of system settings and identify the highest performing set. We employ a case study of regional service contracting to showcase the ability of this method to inform AV+PT service design. We tested our approach with a case study area in a major European city on an agent-based simulation platform, amod-abm. Agent-based simulation has the advantage of capturing individual (agent) behaviors and the interactions of the various individual agents in a realistic synthetic environment where the intent is to re-create a complex phenomenon of mobility on demand service delivered by AV. Although this thesis will focus on a major European city, the general framework and methodologies proposed here can be widely applicable. The thesis concludes that the demand-supply interaction can be effective for designing and assessing the role of AV technology in our mobility systems. Moreover, simulation-based optimization can be an effective method for transit agencies to make decisions that support their overall AV related transport strategy as well as operational planning.

Progress in Artificial Intelligence
Progress in Artificial Intelligence

Author: Goreti Marreiros

Publisher: Springer Nature

Published: 2022-09-12

Total Pages: 818

ISBN-13: 3031164741

DOWNLOAD EBOOK

This book constitutes the proceedings of the 21st EPIA Conference on Artificial Intelligence, EPIA 2022, which took place in Lisbon, Portugal, in August/September 2022. The 64 papers presented in this volume were carefully reviewed and selected from 85 submissions. They were organized in topical sections as follows: AI4IS - Artificial Intelligence for Industry and Societies; AIL - Artificial Intelligence and Law; AIM - Artificial Intelligence in Medicine; AIPES - Artificial Intelligence in Power and Energy Systems; AITS - Artificial Intelligence in Transportation Systems; AmIA - Ambient Intelligence and Affective Environments; GAI - General AI; IROBOT - Intelligent Robotics; KDBI - Knowledge Discovery and Business Intelligence; KRR - Knowledge Representation and Reasoning; MASTA - Multi-Agent Systems: Theory and Applications; TeMA - Text Mining and Applications.

The Multi-Agent Transport Simulation MATSim
The Multi-Agent Transport Simulation MATSim

Author: Andreas Horni

Publisher: Ubiquity Press

Published: 2016-08-10

Total Pages: 620

ISBN-13: 190918876X

DOWNLOAD EBOOK

The MATSim (Multi-Agent Transport Simulation) software project was started around 2006 with the goal of generating traffic and congestion patterns by following individual synthetic travelers through their daily or weekly activity programme. It has since then evolved from a collection of stand-alone C++ programs to an integrated Java-based framework which is publicly hosted, open-source available, automatically regression tested. It is currently used by about 40 groups throughout the world. This book takes stock of the current status. The first part of the book gives an introduction to the most important concepts, with the intention of enabling a potential user to set up and run basic simulations. The second part of the book describes how the basic functionality can be extended, for example by adding schedule-based public transit, electric or autonomous cars, paratransit, or within-day replanning. For each extension, the text provides pointers to the additional documentation and to the code base. It is also discussed how people with appropriate Java programming skills can write their own extensions, and plug them into the MATSim core. The project has started from the basic idea that traffic is a consequence of human behavior, and thus humans and their behavior should be the starting point of all modelling, and with the intuition that when simulations with 100 million particles are possible in computational physics, then behavior-oriented simulations with 10 million travelers should be possible in travel behavior research. The initial implementations thus combined concepts from computational physics and complex adaptive systems with concepts from travel behavior research. The third part of the book looks at theoretical concepts that are able to describe important aspects of the simulation system; for example, under certain conditions the code becomes a Monte Carlo engine sampling from a discrete choice model. Another important aspect is the interpretation of the MATSim score as utility in the microeconomic sense, opening up a connection to benefit cost analysis. Finally, the book collects use cases as they have been undertaken with MATSim. All current users of MATSim were invited to submit their work, and many followed with sometimes crisp and short and sometimes longer contributions, always with pointers to additional references. We hope that the book will become an invitation to explore, to build and to extend agent-based modeling of travel behavior from the stable and well tested core of MATSim documented here.

Transforming Urban Transport
Transforming Urban Transport

Author: Diane E. Davis

Publisher:

Published: 2019

Total Pages: 337

ISBN-13: 0190875704

DOWNLOAD EBOOK

Transforming Urban Transport brings into focus the origins and implementation pathways of significant urban transport innovations that have recently been adopted in major, democratically governed world cities that are seeking to advance sustainability aims. It documents how proponents of new transportation initiatives confronted a range of administrative, environmental, fiscal, and political obstacles by using a range of leadership skills, technical resources, and negotiation capacities to move a good idea from the drawing board to implementation. The book's eight case studies focus on cities of great interest across the globe--Los Angeles, Mexico City, New York, Paris, San Francisco, Seoul, Stockholm, and Vienna--many of which are known for significant mayor leadership and efforts to rescale power from the nation to the city. The cases highlight innovations likely to be of interest to transport policy makers from all corners, such as strengthening public transportation services, vehicle and traffic management measures, repurposing roads and other urban spaces away from their initial function as vehicle travel corridors, and turning sidewalks and city streets into more pedestrian-friendly places for walking, cycling, and leisure. Aside from their transformative impacts in transportation terms, many of the policy innovations examined here have altered planning institutions, public-private sector relations, civil society commitments, and governance mandates in the course of implementation. In bringing these cases to the fore, Transforming Urban Transport advances understanding of the conditions under which policy interventions can expand institutional capacities and governance mandates, particularly linked to urban sustainability. As such, it is an essential contribution to larger debates about what it takes to make cities more environmentally sustainable and the types of strategies and tactics that best advance progress on these fronts in both the short- and the long-term.

Software Technologies
Software Technologies

Author: Marten van Sinderen

Publisher: Springer Nature

Published: 2021-07-20

Total Pages: 263

ISBN-13: 3030830071

DOWNLOAD EBOOK

This book constitutes the thoroughly refereed proceedings of the 15th International Conference on Software Technologies, ICSOFT 2020, which was held virtually due to the Covid-19 pandemic. The 12 revised full papers were carefully reviewed and selected from 95 submissions. The papers deal with the following topics: business process modelling; IT service management; interoperability and service-oriented architecture; project management software; scheduling and estimating; software metrics; requirements elicitation and specification; software and systems integration among others.