Search

In this study, we develop an innovative data-driven optimization approach to solve the drone delivery service planning problem with online demand. Drone-based logistics are expected to improve operations by enhancing flexibility and reducing congestion effects induced by last-mile deliveries. With rising digitalization and urbanization, however, logistics service providers are constantly grappling with the challenge of uncertain real-time demand. This study investigates the problem of planning drone delivery service through an urban air traffic network to fulfil online and stochastic demand. Customer requests, if accepted, generate profit and are serviced by individual drone flights as per request origins, destinations and time windows. We cast this stochastic optimization problem as a Markov decision process. We present a novel data-driven optimization approach which generates predictive prescriptions of parameters of a surrogate optimization formulation. Our solution method consists of synthesizing training data via lookahead simulations to train a supervised machine learning model for predicting relative link priority based on the state of the network. This knowledge is then leveraged to selectively create weighted reserve capacity in the network and via a surrogate objective function that controls the trade-off between reserve capacity and profit maximization to maximize the cumulative profit earned. Using numerical experiments based on benchmarking transportation networks, the resulting data-driven optimization policy is shown to outperform a myopic policy. Sensitivity analyses on learning parameters reveal insights into the design of efficient policies for drone delivery service planning with online demand.

With technological advances, mobility has been moving from a product (i.e., traditional modes and vehicles), to a service (i.e., Mobility as a Service, MaaS). However, as observed in other fields (e.g. cloud computing resource management) we argue that mobility will evolve from a service to a resource (i.e., Mobility as a Resource, MaaR). Further, due to increasing scarcity of shared mobility spaces across traditional and emerging modes, the transition must be viewed within the critical need for ethical and equitable solutions for the traveling public (i.e., research is needed to avoid hyper-market driven outcomes for society). The evolution of mobility into a resource requires novel conceptual frameworks, technologies, processes and perspectives of analysis. A key component of the future MaaR system is the technological capacity to observe, allocate and manage (in real-time) the smallest envisionable units of mobility (i.e., atomic units of mobility capacity) while providing prioritized attention to human movement and ethical metrics related to access, consumption and impact. To facilitate research into the envisioned future system, this paper proposes initial frameworks which synthesize and advance methodologies relating to highly dynamic capacity reservation systems. Future research requires synthesis across transport network management, demand behavior, mixed-mode usage, and equitable mobility.

Macroscopic link-based flow models are efficient for simulating flow propagation in urban road networks. Existing link-based flow models described traffic states of a link with two state variables of link inflow and outflow and assumed homogeneous traffic states within a whole link. Consequently, the turn-level queue length change within the link can not be captured, resulting in underrepresented queue spillback. Moreover, a constant link free-flow speed was assumed to formulate models, restricting their applicability in modeling phenomena involving time-varying free-flow speed. This study proposed a new link-based flow model by introducing an additional state variable of link queue inflow and adapting the link outflow to be free-flow speed-dependent. In our model, the vehicle propagation within each link is described by the link inflow, queue inflow, and outflow, which depends on the link free-flow speed changes. A node model is further defined to capture the presence of signal control and potential queue spillback, which estimates the constrained flow propagation between adjacent road segments. Simulation experiments were conducted on a single intersection and a network with consecutive intersections to verify the proposed model performance. Results demonstrate the predictive power of the proposed model in predicting traffic operations of intersections with multiple turning movements and time-varying free-flow speed. Our model outperforms the baseline link-based flow model and preserves the computational tractability property of link-based flow models.

Transportation is the backbone of the economy and urban development. Improving the efficiency, sustainability, resilience, and intelligence of transportation systems is critical and also challenging. The constantly changing traffic conditions, the uncertain influence of external factors (e.g., weather, accidents), and the interactions among multiple travel modes and multi-type flows result in the dynamic and stochastic natures of transportation systems. The planning, operation, and control of transportation systems require flexible and adaptable strategies in order to deal with uncertainty, non-linearity, variability, and high complexity. In this context, Reinforcement Learning (RL) that enables autonomous decision-makers to interact with the complex environment, learn from the experiences, and select optimal actions has been rapidly emerging as one of the most useful approaches for smart transportation. This paper conducts a bibliometric analysis to identify the development of RL-based methods for transportation applications, typical journals/conferences, and leading topics in the field of intelligent transportation in recent ten years. Then, this paper presents a comprehensive literature review on applications of RL in transportation by categorizing different methods with respect to the specific application domains. The potential future research directions of RL applications and developments are also discussed.

In 2022, Ukraine is suffering an invasion which has resulted in acute impacts playing out over time and geography. This paper examines the impact of the ongoing disruption on traffic behavior using analytics as well as zonal-based network models. The methodology is a data-driven approach that utilizes obtained travel-time conditions within an evolutionary algorithm framework which infers origin-destination demand values in an automated process based on traffic assignment. Because of the automation of the implementation, numerous daily models can be approximated for multiple cities. The novelty of this paper versus the previously published core methodology includes an analysis to ensure the obtained data is appropriate since some data sources were disabled due to the ongoing disruption. Further, novelty includes a direct linkage of the analysis to the timeline of disruptions to examine the interaction in a new way. Finally, specific network metrics are identified which are particularly suited for conceptualizing the impact of conflict disruptions on traffic network conditions. The ultimate aim is to establish processes, concepts and analysis to advance the broader activity of rapidly quantifying the traffic impacts of conflict scenarios.

Considering the multimodal nature of transport systems and potential cross-modal correlations, there is a growing trend of enhancing demand forecasting accuracy by learning from multimodal data. These multimodal forecasting models can improve accuracy but be less practical when different parts of multimodal datasets are owned by different institutions who cannot directly share data among them. While various institutions may can not share their data with each other directly, they may share forecasting models trained by their data, where such models cannot be used to identify the exact information from their datasets. This study proposes an Unsupervised Knowledge Adaptation Demand Forecasting framework to forecast the demand of the target mode by utilizing a pre-trained model based on data of another mode, which does not require direct data sharing of the source mode. The proposed framework utilizes the potential shared patterns among multiple transport modes to improve forecasting performance while avoiding the direct sharing of data among different institutions. Specifically, a pre-trained forecasting model is first learned based on the data of a source mode, which can capture and memorize the source travel patterns. Then, the demand data of the target dataset is encoded into an individual knowledge part and a sharing knowledge part which will extract travel patterns by individual extraction network and sharing extraction network, respectively. The unsupervised knowledge adaptation strategy is utilized to form the sharing features for further forecasting by making the pre-trained network and the sharing extraction network analogous. Our findings illustrate that unsupervised knowledge adaptation by sharing the pre-trained model to the target mode can improve the forecasting performance without the dependence on direct data sharing.

Mobility-as-a-Service (MaaS) is an emerging business model driven by the concept of "Everything-as-a-Service" and enabled through mobile internet technologies. In the context of economic deregulation, a MaaS system consists of a typical two-sided market, where travelers and transportation service providers (TSPs) are two groups of agents interacting with each other through a MaaS platform. In this study, we propose a modeling and optimization framework for the regulation of two-sided MaaS markets. We consider a name-your-own-price (NYOP)-auction mechanism where travelers submit purchase-bids to accommodate their travel demand via MaaS platform, and TSPs submit sell-bids to supply mobility resources for the MaaS platform in exchange for payments. We cast this problem as a single-leader multi-follower game (SLMFG) where the leader is the MaaS regulator and two groups of follower problems represent the travelers and the TSPs. The MaaS regulator aims to maximize its profits by optimizing operations. In response to the MaaS regulator's decisions, travelers (resp. TSPs) adjust their participation level in the MaaS platform to minimize their travel costs (resp. maximize their profits). We analyze cross-group network effects in the MaaS market, and formulate SLMFGs without and with network effects leading to mixed-integer linear bilevel programming and mixed-integer quadratic bilevel programming problems, respectively. We propose customized branch-and-bound algorithms based on strong duality reformulations to solve these SLMFGs. Extensive numerical experiments conducted on large scale simulation instances generated from realistic mobility data highlight that the performance of the proposed algorithms is significantly superior to a benchmarking approach, and provide meaningful managerial insights for the regulation of two-sided MaaS markets in practice.

The classic Dial-A-Ride Problem (DARP) aims at designing the minimum-cost routing that accommodates a set of user requests under constraints at an operations planning level, where users' preferences and revenue management are often overlooked. In this paper, we present a mechanism for accepting/rejecting user requests in a Demand Responsive Transportation (DRT) context based on the representative utilities of alternative transportation modes. We consider utility-maximizing users and propose a mixed-integer programming formulation for a Chance Constrained DARP (CC-DARP), that captures users' preferences in the long run via a Logit model. We further introduce class-based user groups and consider various pricing structures for DRT services. A customised local search based heuristic is developed to solve the proposed CC-DARP. We report numerical results for both DARP benchmarking instances and a realistic case study based on New York City yellow taxi trip data. Computational experiments performed on 105 benchmarking instances with up to 96 nodes yield an average optimality gap of 2.69% using the proposed local search heuristic. The results obtained on the realistic case study reveal that a zonal fare structure is the best strategy in terms of optimising revenue and ridership. The proposed CC-DARP formulation provides a new decision-support tool to inform on revenue and fleet management for DRT systems at a strategic planning level.

Routing controllability of connected and autonomous vehicles (CAVs) has been shown to reduce the adverse effects of selfish routing on the network efficiency. However, the assumption that CAV owners would readily allow themselves to be controlled externally by a central agency for the good of the system is unrealistic. In this paper, we propose a joint routing and pricing control scheme that aims to incentivize CAVs to seek centrally controlled system-optimal (SO) routing by saving on tolls while user equilibrium (UE) seeking human-driven vehicles (HVs) are subject to a congestion charge. The problem is formulated as a bi-level optimization program where the upper level optimizes the dynamic toll rates using the network fundamental diagram (NFD) and the lower level is a mixed equilibrium simulation-based dynamic traffic assignment model (SBDTA) considering different combinations of SO-seeking CAVs. We apply a feedback-based controller to solve for the optimal spatially differentiated distance-based congestion charge from which SO-seeking CAVs are exempt; but UE-seeking HVs are subject to the charge for entering the city center. To capture the distinct microscopic behavior of CAVs in the mixed autonomy traffic, we also implement an adaptive link fundamental diagram (FD) within the SBDTA model. The proposed joint control scheme encourages CAV owners to seek SO routing resulting in less total system travel time. It also discourages UE-seeking HVs from congesting the city center. We demonstrate the performance of the proposed scheme in both a small network and a large-scale network of Melbourne, Australia.

In the context of `Everything-as-a-Service', the transportation sector has been evolving towards user-centric business models in which customized services and mode-agnostic mobility resources are priced in a unified framework. Yet, in the vast majority of studies on Mobility as a Service (MaaS) systems, mobility resource pricing is based on segmented travel modes, e.g. private vehicle, public transit and shared mobility services. This study attempts to address this research gap by introducing innovative auction-based online MaaS mechanisms where users can bid for any amount of mode-agnostic mobility resources based on their willingness to pay and preferences. We take the perspective of a MaaS regulator which aims to maximize social welfare by allocating mobility resources to users. We propose two mechanisms which allow users to either pay for the immediate use of mobility service (pay-as-you-go), or to subscribe to mobility service packages (pay-as-a-package). We cast the proposed auction-based mechanisms as online resource allocation problems where users compete for MaaS resources and bid for travel time per trip. We propose (integer-) linear programming formulations to accommodate user bids based on available mobility resources in an online optimization approach. We show that the proposed MaaS mechanisms are incentive-compatible, develop customized online algorithms and derive performance bounds based on competitive analysis. Extensive numerical simulations are conducted on large scale instances generated from realistic mobility data, which highlight the benefits of the proposed MaaS mechanisms and the effectiveness of the proposed online optimization approaches.

Accurate demand forecasting of different public transport modes(e.g., buses and light rails) is essential for public service operation.However, the development level of various modes often varies sig-nificantly, which makes it hard to predict the demand of the modeswith insufficient knowledge and sparse station distribution (i.e.,station-sparse mode). Intuitively, different public transit modes mayexhibit shared demand patterns temporally and spatially in a city.As such, we propose to enhance the demand prediction of station-sparse modes with the data from station-intensive mode and designaMemory-Augmented Multi-taskRecurrent Network (MATURE)to derive the transferable demand patterns from each mode andboost the prediction of station-sparse modes through adaptingthe relevant patterns from the station-intensive mode. Specifically,MATUREcomprises three components: 1) a memory-augmentedrecurrent network for strengthening the ability to capture the long-short term information and storing temporal knowledge of eachtransit mode; 2) a knowledge adaption module to adapt the rele-vant knowledge from a station-intensive source to station-sparsesources; 3) a multi-task learning framework to incorporate all theinformation and forecast the demand of multiple modes jointly.The experimental results on a real-world dataset covering four pub-lic transport modes demonstrate that our model can promote thedemand forecasting performance for the station-sparse modes., Comment: 10 pages, 6 figures

Automated vehicles (AV) have the potential to provide cost-effective mobility options along with overall system-level benefits in terms of congestion and vehicular emissions. Additional resource allocation at the network level, such as AV-exclusive lanes, can further foster the usage of AVs rendering this mode of travel more attractive than legacy vehicles (LV). However, it is necessary to find the crucial locations in the network where providing these dedicated lanes would reap the maximum benefits. In this study, we propose an integrated mixed-integer programming framework for optimal AV-exclusive lane design on freeway networks which accounts for commuters' demand split among AVs and LVs via a logit model incorporating class-based utilities. We incorporate the link transmission model (LTM) as the underlying traffic flow model due to its computational efficiency for system optimum dynamic traffic assignment. The LTM is modified to integrate two vehicle classes namely, LVs and AVs with a lane-based approach. The presence of binary variables to represent lane design and the logit model for endogenous demand estimation results in a nonconvex mixed-integer nonlinear program (MINLP) formulation. We propose a Benders' decomposition approach to tackle this challenging optimization problem. Our approach iteratively explores possible lane designs in the Benders' master problem and, at each iteration, solves a sequence of system-optimum dynamic traffic assignment (SODTA) problems which is shown to converge to fixed-points representative of logit-compatible demand splits. Further, we prove that the proposed solution method converges to a local optima of the nonconvex problem and identify under which conditions this local optima is a global solution. The proposed approach is implemented on three hypothetical freeway networks with single and multiple origins and destinations.

In this paper, a novel transport planning model system (TPMS) is formulated which is built on the concepts of supernetworks, multi-modality, integrity and calibration. In the proposed formulation, activity travel pattern (ATP) choice facets including the choices of activity, activity sequence, mode, departure time, and parking location, are all unified into a time-dependent supernetwork. The proposed model accounts for the dynamicity of the network, including time-of-day and congestion effects. These help capturing the interdependencies among all different attributes of a full transport planning system. Moreover, the proposed TPMS explicitly formulates an operating capacitated public transport system. To allow visiting locations multiple times and to alleviate the complexity of the proposed supernetwork, a novel multi-visit vehicle routing problem is proposed which does not enumerate the node and link visits. In order to calibrate the model based on the major travel attributes of the travel survey data, a set of splitting ratios are introduced to distribute trips on the supernetwork. The model uses the splitting ratios to integrate the supernetwork and the traffic assignment model in a unified TPMS structure. At last, numerical examples are provided to demonstrate the advantages of the proposed approach., Comment: 37 pages, 12 Figures, This paper has been submitted to a journal to be reviewed and considered for publication

The spread of traffic jams in urban networks has long been viewed as a complex spatio-temporal phenomenon that often requires computationally intensive microscopic models for analysis purposes. In this study, we present a framework to describe the dynamics of congestion propagation and dissipation of traffic in cities using a simple contagion process, inspired by those used to model infectious disease spread in a population. We introduce two novel macroscopic characteristics of network traffic, namely congestion propagation rate \b{eta} and congestion dissipation rate {\mu}. We describe the dynamics of congestion propagation and dissipation using these new parameters, \b{eta}, and {\mu}, embedded within a system of ordinary differential equations, analogous to the well-known Susceptible-Infected-Recovered (SIR) model. The proposed contagion-based dynamics are verified through an empirical multi-city analysis, and can be used to monitor, predict and control the fraction of congested links in the network over time., Comment: 10 pages, 8 figures

Toll optimization in a large-scale dynamic traffic network is typically characterized by an expensive-to-evaluate objective function. In this paper, we propose two toll level problems (TLPs) integrated with a large-scale simulation-based dynamic traffic assignment (DTA) model of Melbourne, Australia. The first TLP aims to control the pricing zone (PZ) through a time-varying joint distance and delay toll (JDDT) such that the network fundamental diagram (NFD) of the PZ does not enter the congested regime. The second TLP is built upon the first TLP by further considering the minimization of the heterogeneity of congestion distribution in the PZ. To solve the two TLPs, a computationally efficient surrogate-based optimization method, i.e., regressing kriging (RK) with expected improvement (EI) sampling, is applied to approximate the simulation input-output mapping, which can balance well between local exploitation and global exploration. Results show that the two optimal TLP solutions reduce the average travel time in the PZ (entire network) by 29.5% (1.4%) and 21.6% (2.5%), respectively. Reducing the heterogeneity of congestion distribution achieves higher network flows in the PZ and a lower average travel time or a larger total travel time saving in the entire network., Comment: 16 pages, 7 figures

The MAPS direct geometry time-of-flight chopper spectrometer at the ISIS pulsed neutron and muon source has been in operation since 1999 and its novel use of a large array of position-sensitive neutron detectors paved the way for a later generations of chopper spectrometers around the world. Almost two decades of experience of user operations on MAPS, together with lessons learned from the operation of new generation instruments, led to a decision to perform three parallel upgrades to the instrument. These were to replace the primary beamline collimation with supermirror neutron guides, to install a disk chopper, and to modify the geometry of the poisoning in the water moderator viewed by MAPS. Together these upgrades were expected to increase the neutron flux substantially, to allow more flexible use of repetition rate multiplication and to reduce some sources of background. Here we report the details of these upgrades, and compare the performance of the instrument before and after their installation, as well as to Monte Carlo simulations. These illustrate that the instrument is performing in line with, and in some respects in excess of, expectations. It is anticipated that the improvement in performance will have a significant impact on the capabilities of the instrument. A few examples of scientific commissioning are presented to illustrate some of the possibilities., Comment: 17 pages, 15 figures