The increasing adoption of electric vehicles underscores the urgent need for efficient and reliable charging infrastructure. Fixed charging stations are crucial for meeting surging demand and ensuring convenient access, yet accurately predicting demand remains highly challenging, because charging patterns change in response to where stations are placed, which creates a cyclical dilemma for planning. However, mobile charging stations (MCSs) offer a novel solution by flexibly relocating across urban areas, they can both deliver energy and act as dynamic probes to collect real-time data on charging demand. Existing studies, however, typically assume prior knowledge of demand distributions, which is rarely available in emerging EV markets or where privacy concerns limit data access. This paper proposes a Deep Reinforcement Learning (DRL) approach, formulated as a Partially Observable Markov Decision Process (POMDP), to optimize the relocation of MCSs in conjunction with fixed charging stations, while simultaneously uncovering latent demand patterns. We employ an Advantage Actor–Critic (A2C) algorithm with Long Short-Term Memory (LSTM) networks to capture temporal dependencies and adapt to stochastic demand. A dynamic Mixed-Integer Programming (MIP) model is developed as a benchmark that represents an idealized case with perfect foresight of demand. We compare the DRL agent against this optimization model in two settings: (i) a synthetic toy environment for controlled testing, and (ii) a realistic simulation of the Frederiksberg municipality in Denmark, calibrated with real charging data. The results show that the DRL framework effectively adapts to stochastic demand, outperforms the optimization baseline under uncertainty, and scales efficiently to larger problem instances. Beyond methodological contributions, the findings highlight how MCSs can serve a dual role as infrastructure supplements and as demand-discovery tools, offering valuable insights for data-driven and adaptive EV charging planning.

Optimization problems over dynamic networks have been extensively studied and widely used in the past decades to formulate numerous real-world problems. However, (1) traditional optimization-based approaches do not scale to large networks, and (2) the design of good heuristics or approximation algorithms often requires significant manual trial-and-error. In this work, we argue that data-driven strategies can automate this process and learn efficient algorithms without compromising optimality. To do so, we present network control problems through the lens of reinforcement learning and propose a graph network-based framework to handle a broad class of problems. Instead of naively computing actions over high-dimensional graph elements, e.g., edges, we propose a bi-level formulation where we (1) specify a desired next state via RL, and (2) solve a convex program to best achieve it, leading to drastically improved scalability and performance. We further highlight a collection of desirable features to system designers, investigate design decisions, and present experiments on real-world control problems showing the utility, scalability, and flexibility of our framework.

Knowledge of passenger flow underpins any optimal public transport application, such as new facilities design and operations. The interactions between passengers and sensors may provide the foundation to measure this flow and dismiss users and staff from the measures’ validation loop. Removing humans and their errors may impact significantly and improve measures’ cost and quality. The literature considered smartphones the leading enabler due to market penetration and embodied sensors. Smartphones allow users’ localization, identification, authentication, and billing. Via Bluetooth, smartphones detect short-range implicit interactions, device-to-device. We model passenger states on buses, either be-in or be-out (BIBO). The BIBO use case identifies a fundamental building block of continuously-valued passenger flow, which this paper describes through a Human-Computer interaction experimental setting involving two autonomous buses and a proprietary smartphone-Bluetooth sensing platform. The resulting dataset of 14,000 observations/sensors contains two ground-truth levels: the first is the passengers’ validation; the second is validation by video cameras surveilling buses and tracks. This study verifies separately classification based on Bluetooth and GPS signals, as well as an inertial navigation system, evaluating signals and related machine learning (ML) classifiers against measurement and ground-truth noise. The paper contributes a Monte Carlo simulation of labels-flip to emulate human errors in the labeling process, as in smartphone surveys, and a novel unsupervised variational auto-encoder classifier. Experimental results indicate error-free human validation is unlikely. The impact of mistakes on model performance bias can be significant. This use case supports the potential substitution of human validation with independent Bluetooth validation.

Autonomous Mobility-on-Demand (AMoD) systems represent an attractive alternative to existing transportation paradigms, currently challenged by urbanization and increasing travel needs. By centrally controlling a fleet of self-driving vehicles, these systems provide mobility service to customers and are currently starting to be deployed in a number of cities around the world. Current learning-based approaches for controlling AMoD systems are limited to the single-city scenario, whereby the service operator is allowed to take an unlimited amount of operational decisions within the same transportation system. However, real-world system operators can hardly afford to fully re-train AMoD controllers for every city they operate in, as this could result in a high number of poor-quality decisions during training, making the single-city strategy a potentially impractical solution. To address these limitations, we propose to formalize the multi-city AMoD problem through the lens of meta-reinforcement learning (meta-RL) and devise an actor-critic algorithm based on recurrent graph neural networks. In our approach, AMoD controllers are explicitly trained such that a small amount of experience within a new city will produce good system performance. Empirically, we show how control policies learned through meta-RL are able to achieve near-optimal performance on unseen cities by learning rapidly adaptable policies, thus making them more robust not only to novel environments, but also to distribution shifts common in real-world operations, such as special events, unexpected congestion, and dynamic pricing schemes.

The bias-variance trade-off is a well-known problem in machine learning that only gets more pronounced the less available data there is. In active learning, where labeled data is scarce or difficult to obtain, neglecting this trade-off can cause inefficient and non-optimal querying, leading to unnecessary data labeling. In this paper, we focus on active learning with Gaussian Processes (GPs). For the GP, the bias-variance trade-off is made by optimization of the two hyperparameters: the length scale and noise-term. Considering that the optimal mode of the joint posterior of the hyperparameters is equivalent to the optimal bias-variance trade-off, we approximate this joint posterior and utilize it to design two new acquisition functions. The first one is a Bayesian variant of Query-by-Committee (B-QBC), and the second is an extension that explicitly minimizes the predictive variance through a Query by Mixture of Gaussian Processes (QB-MGP) formulation. Across six simulators, we empirically show that B-QBC, on average, achieves the best marginal likelihood, whereas QB-MGP achieves the best predictive performance. We show that incorporating the bias-variance trade-off in the acquisition functions mitigates unnecessary and expensive data labeling.

Shared mobility services require accurate demand models for effective service planning. On the one hand, modeling the full probability distribution of demand is advantageous because the entire uncertainty structure preserves valuable information for decision-making. On the other hand, demand is often observed through the usage of the service itself, so that the observations are censored, as they are inherently limited by available supply. Since the 1980s, various works on Censored Quantile Regression models have performed well under such conditions. Further, in the last two decades, several papers have proposed to implement these models flexibly through Neural Networks. However, the models in current works estimate the quantiles individually, thus incurring a computational overhead and ignoring valuable relationships between the quantiles. We address this gap by extending current Censored Quantile Regression models to learn multiple quantiles at once and apply these to synthetic baseline datasets and datasets from two shared mobility providers in the Copenhagen metropolitan area in Denmark. The results show that our extended models yield fewer quantile crossings and less computational overhead without compromising model performance.

Specifying utility functions is a key step towards applying the discrete choice framework for understanding the behaviour processes that govern user choices. However, identifying the utility function specifications that best model and explain the observed choices can be a very challenging and time-consuming task. This paper seeks to help modellers by leveraging the Bayesian framework and the concept of automatic relevance determination (ARD), in order to automatically determine an optimal utility function specification from an exponentially large set of possible specifications in a purely data-driven manner. Based on recent advances in approximate Bayesian inference, a doubly stochastic variational inference is developed, which allows the proposed MNL-ARD model to scale to very large and high-dimensional datasets. Using semi-artificial choice data, the proposed approach is shown to be able to accurately recover the true utility function specifications that govern the observed choices. Moreover, when applied to real choice data, MNL-ARD is able discover high quality specifications that can outperform previous ones from the literature according to multiple criteria, thereby demonstrating its practical applicability.

For practical reasons, surveys that aim for a large number of respondents tend to restrict themselves to closed-ended responses. Despite potentially bringing richer insights, the use of open-ended questions poses great challenges in terms of extracting useful information while significantly increasing the analysis time. Nevertheless, automatic text analysis techniques speed up the analysis of open-ended responses. In this research, we explore the potential to use techniques in topic modelling [Latent Dirichlet Allocation (LDA) and Supervised LDA (sLDA)] to extract information from open-ended responses. This is compared to the information obtained from closed-ended responses, accomplished using a questionnaire that measures the intention to use shared autonomous vehicles (SAVs). Two versions of the questionnaire- Ver_OE and Ver_Lk were used, with open-ended and Likert scales measuring the same attitudes in the alternative versions. Factors were extracted for closed-ended questions. For questions common to both versions of the questionnaire, respondents answering Ver_OE had a higher positive attitude towards autonomous vehicles. These attitudinal questions were placed after the open-ended questions. When evaluating the performance of the models that predict the intention to use SAVs, models estimated using Ver_OE performed better. This increased further with the inclusion of the information extracted from the open-ended responses using both, the unsupervised (LDA) and supervised (sLDA) methods. No improvement was observed in the model for Ver_Lk. These indicate the potential for the use of open-ended questions to measure attitudes and topic modelling to extract information from these responses.

In transportation, nature, economy, environment, and many other settings, there are multiple simultaneous phenomena happening that are of interest to model and predict. Over the last few years, the traffic data that we have at our disposal have significantly increased, and we have truly entered the era of big data for transportation. Most existing travel demand prediction methods mainly focus on capturing recurrent mobility trends that relate to habitual/routine behavior, and on exploiting short-term correlations with recent observation patterns. However, valuable information that is often available in the form of unstructured data is neglected when attempting to improve forecasting results. Particularly, under non-recurrent conditions, such as large events, or incidents, we need much better models. In this paper, we explore time-series data and semantic information combinations using machine learning and deep learning techniques in the context of creating a prediction model that is able to capture in real-time future stressful situations of the studied transportation system. We apply the proposed approaches in event areas in New York using publicly available taxi data. We empirically show that the proposed models are able to significantly reduce the error in the forecasts. The importance of semantic information is highlighted in all presented methods and the final mean absolute error of our prediction is decreased by 23.8% for a three months testing period.

Spatiotemporal problems are ubiquitous and of vital importance in many research fields. Despite the potential already demonstrated by deep learning methods in modeling spatiotemporal data, typical approaches tend to focus solely on conditional expectations of the output variables being modeled. In this article, we propose a multioutput multiquantile deep learning approach for jointly modeling several conditional quantiles together with the conditional expectation as a way to provide a more complete "picture" of the predictive density in spatiotemporal problems. Using two large-scale data sets from the transportation domain, we empirically demonstrate that, by approaching the quantile regression problem from a multitask learning perspective, it is possible to solve the embarrassing quantile crossings problem while simultaneously significantly outperforming state-of-the-art quantile regression methods. Moreover, we show that jointly modeling the mean and several conditional quantiles not only provides a rich description about the predictive density that can capture heteroscedastic properties at a neglectable computational overhead but also leads to improved predictions of the conditional expectation due to the extra information and the regularization effect induced by the added quantiles.

Traffic speed data imputation is a fundamental challenge for data-driven transport analysis. In recent years, with the ubiquity of GPS-enabled devices and the widespread use of crowdsourcing alternatives for the collection of traffic data, transportation professionals increasingly look to such user-generated data for a good deal of analysis, planning, and decision support applications. However, due to the mechanics of the data collection process, crowdsourced traffic data such as probe-vehicle data is highly prone to missing observations, making accurate imputation crucial for the success of any application that makes use of that type of data. In this paper, we propose the use of multi-output Gaussian processes (GPs) to model the complex spatial and temporal patterns in crowdsourced traffic data. While the Bayesian nonparametric formalism of GPs allows us to model observation uncertainty, the multi-output extension based on convolution processes effectively enables us to capture complex spatial dependencies between nearby road segments. Using six months of crowdsourced traffic speed data or “probe vehicle data” for several locations in Copenhagen, the proposed approach is empirically shown to significantly outperform popular state-of-the-art imputation methods.

Over the last few years, deep learning has revolutionized the field of machine learning by dramatically improving the state-of-the-art in various domains. However, as the size of supervised artificial neural networks grows, typically so does the need for larger labeled datasets. Recently, crowdsourcing has established itself as an efficient and cost-effective solution for labeling large sets of data in a scalable manner, but it often requires aggregating labels from multiple noisy contributors with different levels of expertise. In this paper, we address the problem of learning deep neural networks from crowds. We begin by describing an EM algorithm for jointly learning the parameters of the network and the reliabilities of the annotators. Then, a novel general-purpose crowd layer is proposed, which allows us to train deep neural networks end-to-end, directly from the noisy labels of multiple annotators, using only backpropagation. We empirically show that the proposed approach is able to internally capture the reliability and biases of different annotators and achieve new state-of-the-art results for various crowdsourced datasets across different settings, namely classification, regression and sequence labeling.

Urban environments are systems of overwhelming complexity and dynamism, involving numerous variables and idiosyncrasies which not usually easy to model from a functional perspective. Simulation modeling is a common and well-accepted approach to study such systems, specially those that prove to be too complex to be analyzed by standard analytic methods. However, such urban simulation models can become computationally very expensive to run. To address this drawback, simulation metamodels can be employed to approximate the underlying simulation function. In this paper, we propose a batch-mode active learning strategy based on Gaussian Processes metamodeling that searches for the most informative data points in batches with respect to their corresponding predictive variances. These points are selected in such a way that they originate from different high variance neighborhoods. Eventually, this allows us to analyze the simulation output behavior with fewer simulation requests. Using an illustrative traffic simulation example, the results show that the proposed restricted batch-mode strategy is able to increase the simulation input space exploration efficiency in comparison with standard batch-mode strategies.

Simulation modeling is a well-known and recurrent approach to study the performance of urban systems. Taking into account the recent and continuous transformations within increasingly complex and multidimensional cities, the use of simulation tools is, in many cases, the only feasible and reliable approach to analyze such dynamic systems. However, simulation models can become very time consuming when detailed input-space exploration is needed. To tackle this problem, simulation metamodels are often used to approximate the simulators' results. In this paper, we propose an active learning algorithm based on the Gaussian process (GP) framework that gathers the most informative simulation data points in batches, according to both their predictive variances and to the relative distance between them. This allows us to explore the simulators' input space with fewer data points and in parallel, and thus in a more efficient way, while avoiding computationally expensive simulation runs in the process. We take advantage of the closeness notion encoded into the GP to select batches of points in such a way that they do not belong to the same high-variance neighborhoods. In addition, we also suggest two simple and practical user-defined stopping criteria so that the iterative learning procedure can be fully automated. We illustrate this methodology using three experimental settings. The results show that the proposed methodology is able to improve the exploration efficiency of the simulation input space in comparison with non-restricted batch-mode active learning procedures.

Public special events, like sports games, concerts and festivals are well known to create disruptions in transportation systems, often catching the operators by surprise. Although these are usually planned well in advance, their impact is difficult to predict, even when organisers and transportation operators coordinate. The problem highly increases when several events happen concurrently. To solve these problems, costly processes, heavily reliant on manual search and personal experience, are usual practice in large cities like Singapore, London or Tokyo. This paper presents a Bayesian additive model with Gaussian process components that combines smart card records from public transport with context information about events that is continuously mined from the Web. We develop an efficient approximate inference algorithm using expectation propagation, which allows us to predict the total number of public transportation trips to the special event areas, thereby contributing to a more adaptive transportation system. Furthermore, for multiple concurrent event scenarios, the proposed algorithm is able to disaggregate gross trip counts into their most likely components related to specific events and routine behavior. Using real data from Singapore, we show that the presented model outperforms the best baseline model by up to 26 percent in R2 and also has explanatory power for its individual components.

The growing need to analyze large collections of documents has led to great developments in topic modeling. Since documents are frequently associated with other related variables, such as labels or ratings, much interest has been placed on supervised topic models. However, the nature of most annotation tasks, prone to ambiguity and noise, often with high volumes of documents, deem learning under a single-annotator assumption unrealistic or unpractical for most real-world applications. In this article, we propose two supervised topic models, one for classification and another for regression problems, which account for the heterogeneity and biases among different annotators that are encountered in practice when learning from crowds. We develop an efficient stochastic variational inference algorithm that is able to scale to very large datasets, and we empirically demonstrate the advantages of the proposed model over state-of-the-art approaches.

Arrival time predictions for the next available bus or train are a key component of modern traveler information systems (TISs). A great deal of research has been conducted within the intelligent transportation system community in developing an assortment of different algorithms that seek to increase the accuracy of these predictions. However, the inherent stochastic and nonlinear nature of these systems, particularly in the case of bus transport, means that these predictions suffer from variable sources of error, stemming from variations in weather conditions, bus bunching, and numerous other sources. In this paper, we tackle the issue of uncertainty in bus arrival time predictions using an alternative approach. Rather than endeavor to develop a superior method for prediction, we take existing predictions from a TIS and treat the algorithm generating them as a black box. The presence of heteroscedasticity in the predictions is demonstrated and then a metamodel approach is deployed, which augments existing predictive systems using quantile regression to place bounds on the associated error. As a case study, this approach is applied to data from a real-world TIS in Boston. This method allows bounds on the predicted arrival time to be estimated, which give a measure of the uncertainty associated with the individual predictions. This represents to the best of our knowledge the first application of methods to handle the uncertainty in bus arrival times that explicitly takes into account the inherent heteroscedasticity. The metamodel approach is agnostic to the process generating the predictions, which ensures the methodology is implementable in any system.

The growing need to analyze large collections of documents has led to great developments in topic modeling. Since documents are frequently associated with other related variables, such as labels or ratings, much interest has been placed on supervised topic models. However, the nature of most annotation tasks, prone to ambiguity and noise, often with high volumes of documents, deem learning under a single-annotator assumption unrealistic or unpractical for most real-world applications. In this paper, we propose a supervised topic model that accounts for the heterogeneity and biases among different annotators that are encountered in practice when learning from crowds. We develop an efficient stochastic variational inference algorithm that is able to scale to very large datasets, and we empirically demonstrate the advantages of the proposed model over state of the art approaches.

Public transport smartcard data can be used for detection of large crowds. By comparing statistics on habitual behavior (e.g., average by time of day), one can specifically identify nonhabitual crowds, which are often very problematic for transport systems. While habitual overcrowding (e.g., peak hour) is well understood both by traffic managers and travelers, nonhabitual overcrowding hotspots can become even more disruptive and unpleasant because they are generally unexpected. By quickly understanding such cases, a transport manager can react and mitigate transport system disruptions. We propose a probabilistic data analysis model that breaks each nonhabitual overcrowding hotspot into a set of explanatory components. The potential explanatory components are initially retrieved from social networks and special events websites and then processed through text-analysis techniques. Finally, for each such component, the probabilistic model estimates a specific share in the total overcrowding counts. We first validate with synthetic data and then test our model with real data from the public transport system (EZLink) of Singapore, focused on three case study areas. We demonstrate that it is able to generate explanations that are intuitively plausible and consistent both locally (correlation coefficient, i.e., CC, from 85% to 99% for the three areas) and globally (CC from 41.2% to 83.9%). This model is directly applicable to any other domain sensitive to crowd formation due to large social events (e.g., communications, water, energy, waste).

GPS localization drains battery aggressively if it is done continuously on a smartphone. This high battery drainage could be reduced by lowering the sampling rate of GPS. However, to fill the reception gaps introduced by low sampling rate, other methods need to be explored. The sensors available in the smartphones allow incremental positioning based on dead reckoning. Even though dead reckoning is a widely researched topic in navigation and walking based localization, it still lacks research on smartphone low-quality sensor based localization for vehicular motion. Therefore this paper describes a dead reckoning system design and implementation for vehicular motion on Android smartphones. It adapts and presents currently used methods for each system step (i.e. filtering, gravity removal, heading estimation and velocity/displacement integration). It also presents new research finding on accelerometer filtering process (i.e. the relationship between acceleration/deceleration to main frequency components of the motion).

Learning from multiple annotators took a valuable step towards modelling data that does not fit the usual single annotator setting. However, multiple annotators sometimes offer varying degrees of expertise. When disagreements arise, the establishment of the correct label through trivial solutions such as majority voting may not be adequate, since without considering heterogeneity in the annotators, we risk generating a flawed model. In this paper, we extend GP classification in order to account for multiple annotators with different levels expertise. By explicitly handling uncertainty, Gaussian processes (GPs) provide a natural framework to build proper multiple-annotator models. We empirically show that our model significantly outperforms other commonly used approaches, such as majority voting, without a significant increase in the computational cost of approximate Bayesian inference. Furthermore, an active learning methodology is proposed, which is able to reduce annotation cost even further.

In transport modeling and prediction, trip purposes play an important role. The most particular case is activity-based modeling, whereby mobility choices (e.g. mode, path, and departure time) are made in order to carry out specific activities. A current challenge, however, lies on getting appropriate data that relates observed trips with their purpose. Recently, a Smartphone-based travel survey (the Future Mobility Survey, FMS) was conducted in Singapore that collected location data from 793 participants. Each FMS user was required to collect data for at least 14 days and validate at least 5 of them. This dataset presents diverse opportunities in terms of developing machine learning models for the future versions of FMS, where the validation process is intelligent and easy to use (e.g. having pre-filled activities associated to the user traces). This paper proposes a learning model that, given a stop location, identifies the most likely activity associated to it. Our data often contains errors or noise due to limited functionality of physical sensors in a dense area, and human mistakes in the validation process. To alleviate this effect, we generate heterogeneous features by different spatial quantization techniques and apply ensemble learning for a good generalization performance.

This paper presents a methodology for estimating the upper and lower bounds of a real-time traffic prediction system, i.e., its prediction interval. Without a very complex implementation work, our model is able to complement any preexisting prediction system with extra uncertainty information such as the 5% and 95% quantiles. We treat the traffic prediction system as a black box that provides a feed of predictions. Having this feed together with observed values, we then train conditional quantile regression methods that estimate the upper and lower quantiles of the error. The goal of conditional quantile regression is to determine a function, i.e., dτ(x), that returns the specific quantile r of a target variable d, given an input vector x. Following Koenker, we implement two functional forms of dτ(x): locally weighted linear, which relies on value on the neighborhood of x, and splines, a piecewise defined smooth polynomial function. We demonstrate this methodology with three different traffic prediction models applied to two freeway data sets from Irvine, CA, and Tel Aviv, Israel. We contrast the results with a traditional confidence intervals approach that assumes that the error is normally distributed with constant (homoscedastic) variance. We apply several evaluation measures based on earlier literature and contribute two new measures that focus on relative interval length and balance between accuracy and interval length. For the available data set, we verified that conditional quantile regression outperforms the homoscedastic baseline in the vast majority of the indicators.

The UrbanMobSense is a mobility sensing system designed to collect the travel patterns of people for transportation planning purposes. This system makes use of smartphones with various built-in sensors to capture human mobility automatically in a non-intrusive manner. To improve the user experience of smartphone users, the system is designed to be user-centric to address energy conservation and privacy preservation issues. The UrbanMobSense has been deployed in Singapore to support the Land Transport Authority (LTA)'s household travel survey.

Transportation activity surveys investigate when, where and how people travel in urban areas to provide information necessary for urban transportation planning. In Singapore, the Land Transport Authority (LTA) carries out such a survey amongst households every four years. The survey is conducted through conventional questionnaires and travel diaries. However, the conventional surveys are problematic and error-prone. We are developing a smartphone-based transportation activity survey system to replace the traditional household surveys, which can potentially be used by LTA in future.

The traditional relationship between the car, driver, and city can be described as waypoint navigation with additional traffic and maintenance information. The car can receive and store waypoint information, find the shortest route to these waypoints, integrate traffic information, find points-of-interest, and alert the driver of a pre-programmed set of maintenance issues related to the car. Here, we propose a new route system that is multi-goal-centric rather than waypoint-centric. Instead of focusing on determining the route to a specified waypoint, as done in commercially available navigation systems, the system will analyze the driver's behavior in order to extract the potential set(s) of goals that the driver would like to achieve. The system must also understand the city on a number of levels: physical, social, and commercial. This provides the foundation for a social and intelligent driving assistant, that helps the driver achieve his goals and helps the city perform better through interaction between both entities.