Showing papers in "Transportation Research Part C-emerging Technologies in 2019"

The roles of initial trust and perceived risk in public’s acceptance of automated vehicles

Abstract: The purpose of this study was to explore factors affecting users’ acceptance of automated vehicles (AVs, Level 3). A theoretical acceptance model was proposed by extending the Technology Acceptance Model (TAM) with new constructs: initial trust and two types of perceived risk (i.e., perceived safety risk [PSR] and perceived privacy risk [PPR]). It was hypothesized that initial trust was built upon perception factors (i.e., perceived usefulness [PU], perceived ease of use [PEOU], PSR, and PPR) and was a key determinant of AV acceptance. The validity of the model was confirmed with a structure equation modeling analysis based on data collected from 216 survey samples. Results revealed that initial trust was the most critical factor in promoting a positive attitude towards AVs, which, together with PU, determined users’ intention to use AVs. Initial trust could be enhanced by improving PU and reducing PSR associated with AVs. Theoretically, these findings suggest that initial trust offers another and probably more important pathway for other factors to impact consumers’ adoption of systems with uncertainty. Practically, the findings provide guidance for designing interventions aimed at improving public’s acceptance towards AVs.

What have we learned? A review of stated preference and choice studies on autonomous vehicles

Abstract: This paper provides a review of studies published in peer-reviewed journals, conference proceedings, and technical academic and private sector reports on surveys about autonomous vehicles (AVs) from 2012 onward. The studies and respective surveys are categorized in this paper based on the study objectives and methodology applied. More than half of the reviewed studies on AVs focus on capturing individuals’ behavioral characteristics and perceptions. The second most prevalent category includes studies about individuals’ willingness to pay to use AVs. The reviewed studies were also categorized according to the study population. The paper identifies and classifies attitudinal questions in each survey into different components that may affect behavioral intention to ride in AVs and provides information on specific hypotheses that were set in the studies. Moreover, a discussion of the benefits, barriers/concerns, and opportunities related to the deployment of AVs is presented. The paper concludes by summarizing the lessons learned and outlining the research gaps.

Urban traffic signal control with connected and automated vehicles: A survey

Abstract: Inefficient traffic control is pervasive in modern urban areas, which would exaggerate traffic congestion as well as deteriorate mobility, fuel economy and safety. In this paper, we systematically review the potential solutions that take advantage of connected and automated vehicles (CAVs) to improve the control performances of urban signalized intersections. We review the methods and models to estimate traffic flow states and optimize traffic signal timing plans based on CAVs. We summarize six types of CAV-based traffic control methods and propose a conceptual mathematical framework that can be specified to each of six three types of methods by selecting different state variables, control inputs, and environment inputs. The benefits and drawbacks of various CAV-based control methods are explained, and future research directions are discussed. We hope that this review could provide readers with a helpful roadmap for future research on CAV-based urban traffic control and draw their attention to the most challenging problems in this important and promising field.

DeepPF: A deep learning based architecture for metro passenger flow prediction

Abstract: This study aims to combine the modeling skills of deep learning and the domain knowledge in transportation into prediction of metro passenger flow. We present an end-to-end deep learning architecture, termed as Deep Passenger Flow (DeepPF), to forecast the metro inbound/outbound passenger flow. The architecture of the model is highly flexible and extendable; thus, enabling the integration and modeling of external environmental factors, temporal dependencies, spatial characteristics, and metro operational properties in short-term metro passenger flow prediction. Furthermore, the proposed framework achieves a high prediction accuracy due to the ease of integrating multi-source data. Numerical experiments demonstrate that the proposed DeepPF model can be extended to general conditions to fit the diverse constraints that exist in the transportation domain.

Enhancing transportation systems via deep learning: A survey

Abstract: Machine learning (ML) plays the core function to intellectualize the transportation systems. Recent years have witnessed the advent and prevalence of deep learning which has provoked a storm in ITS (Intelligent Transportation Systems). Consequently, traditional ML models in many applications have been replaced by the new learning techniques and the landscape of ITS is being reshaped. Under such perspective, we provide a comprehensive survey that focuses on the utilization of deep learning models to enhance the intelligence level of transportation systems. By organizing multiple dozens of relevant works that were originally scattered here and there, this survey attempts to provide a clear picture of how various deep learning models have been applied in multiple transportation applications.

A Bayesian tensor decomposition approach for spatiotemporal traffic data imputation

Abstract: The missing data problem is inevitable when collecting traffic data from intelligent transportation systems. Previous studies have shown the advantages of tensor completion-based approaches in solving multi-dimensional data imputation problems. In this paper, we extend the Bayesian probabilistic matrix factorization model by Salakhutdinov and Mnih (2008) to higher-order tensors and apply it for spatiotemporal traffic data imputation tasks. In doing so, we care about not only the model configuration but also the representation of data (i.e., matrix, third-order tensor and fourth-order tensor). Using a nine-week spatiotemporal traffic speed data set (road segment × day × time of day) collected in Guangzhou, China, we evaluate the performance of this fully Bayesian model and explore how different data representations affect imputation performance through extensive experiments. The results show the proposed model can produce accurate imputations even under temporally correlated data corruption. Our experiments also show that data representation is a crucial factor for model performance, and a third-order tensor structure outperforms the matrix and fourth-order tensor representations in preserving information in our data set. We hope this work could give insights to practitioners when performing spatiotemporal data imputation tasks.

Multistep speed prediction on traffic networks: A deep learning approach considering spatio-temporal dependencies

Abstract: Multistep traffic forecasting on road networks is a crucial task in successful intelligent transportation system applications. To capture the complex non-stationary temporal dynamics and spatial correlations in multistep traffic-condition prediction, we propose a novel deep learning framework named attention graph convolutional sequence-to-sequence model (AGC-Seq2Seq). In the proposed deep learning framework, spatial and temporal dependencies are modeled through the Seq2Seq model and graph convolution network separately, and the attention mechanism along with a newly designed training method based on the Seq2Seq architecture is proposed to overcome the difficulty in multistep prediction and further capture the temporal heterogeneity of traffic pattern. We conduct numerical tests to compare AGC-Seq2Seq with other benchmark models using two real-world datasets. The results indicate that our model yields the best prediction performance in terms of various prediction error measures. Furthermore, the variations of spatio-temporal correlations of traffic conditions under different perdition steps and road segments are revealed.

An adaptive large neighborhood search metaheuristic for the vehicle routing problem with drones

Abstract: Unmanned Aerial Vehicles, commonly known as drones, have attained considerable interest in recent years due to the potential of revolutionizing transport and logistics. Amazon were among the first to introduce the idea of using drones to deliver goods, followed by several other distribution companies working on similar services. The Traveling Salesman Problem, frequently used for planning last-mile delivery operations, can easily be modified to incorporate drones, resulting in a routing problem involving both the truck and aircraft. Introduced by Murray and Chu (2015) , the Flying Sidekick Traveling Salesman Problem considers a drone and truck collaborating. The drone can be launched and recovered at certain visits on the truck route, making it possible for both vehicles to deliver goods to customers in parallel. This generalization considerably decreases the operational cost of the routes, by reducing the total fuel consumption for the truck, as customers on the routes can be serviced by drones without covering additional miles for the trucks, and hence increase productivity. In this paper a mathematical model is formulated, defining a problem similar to the Flying Sidekick Traveling Salesman Problem, but for the capacitated multiple-truck case with time limit constraints and minimizing cost as objective function. The corresponding problem is denoted the Vehicle Routing Problem with Drones. Due to the difficulty of solving large instances to optimality, an Adaptive Large Neighborhood Search metaheuristic is proposed. Finally, extensive computational experiments are carried out. The tests investigate, among other things, how beneficial the inclusion of the drone-delivery option is compared to delivering all items using exclusively trucks. Moreover, a detailed sensitivity analysis is performed on several drone-parameters of interest.

Detection and tracking of pedestrians and vehicles using roadside LiDAR sensors

Abstract: Light Detection and Ranging (LiDAR) is a remote sensing technology widely used in many areas ranging from making precise medical equipment to creating accurate elevation maps of farmlands. In transportation, although it has been used to assist some design and planning works, the application has been predominantly focused on autonomous vehicles, regardless of its great potential in precise detection and tracking of all road users if implemented in the field. This paper explores fundamental concepts, solution algorithms, and application guidance associated with using infrastructure-based LiDAR sensors to accurately detect and track pedestrians and vehicles at intersections. Based on LiDAR data collected in the field, investigations were conducted in the order of background filtering, object clustering, pedestrian and vehicle classification, and tracking. The results of the analysis include accurate and real-time information of the presence, position, velocity, and direction of pedestrians and vehicles. By studying the data from infrastructure-mounted LiDAR sensors at intersections, this paper offers insights into some critical techniques that are valuable to both researchers and practitioners toward field implementation of LiDAR sensors.

Investigating objective and subjective factors influencing the adoption, frequency, and characteristics of ride-hailing trips

Abstract: Even as ride-hailing has become ubiquitous in most urban areas, its impacts on individual travel are still unclear. This includes limited knowledge of demand characteristics (especially for pooled rides), travel modes being substituted, types of activities being accessed, as well as possible trip induction effects. The current study contributes to this knowledge gap by investigating ride-hailing experience, frequency, and trip characteristics through two multi-dimensional models estimated using data from the Dallas-Fort Worth Metropolitan Area. Ride-hailing adoption and usage are modeled as functions of unobserved lifestyle stochastic latent constructs, observed transportation-related choices, and sociodemographic variables. The results point to low residential location density and people’s privacy concerns as the main deterrents to pooled ride-hailing adoption, with non-Hispanic Whites being more privacy sensitive than individuals of other ethnicities. Further, our results suggest a need for policies that discourage the substitution of short-distance “walkable” trips by ride-hailing, and a need for low cost and well-integrated multi-modal systems to avoid substitution of transit trips by this mode.

An effective spatial-temporal attention based neural network for traffic flow prediction

Abstract: Due to its importance in Intelligent Transport Systems (ITS), traffic flow prediction has been the focus of many studies in the last few decades. Existing traffic flow prediction models mainly extract static spatial-temporal correlations, although these correlations are known to be dynamic in traffic networks. Attention-based models have emerged in recent years, mostly in the field of natural language processing, and have resulted in major progresses in terms of both accuracy and interpretability. This inspires us to introduce the application of attentions for traffic flow prediction. In this study, a deep learning based traffic flow predictor with spatial and temporal attentions (STANN) is proposed. The spatial and temporal attentions are used to exploit the spatial dependencies between road segments and temporal dependencies between time steps respectively. Experiment results with a real-world traffic dataset demonstrate the superior performance of the proposed model. The results also show that the utilization of multiple data resolutions could help improve prediction accuracy. Furthermore, the proposed model is demonstrated to have potential for improving the understanding of spatial-temporal correlations in a traffic network.

A data-driven lane-changing model based on deep learning

Abstract: Lane-changing (LC), which is one of the basic driving behavior, largely impacts on traffic efficiency and safety. Modeling an LC process is challenging due to the complexity and uncertainty of driving behavior. To address this issue, this paper proposes a data-driven LC model based on deep learning models. Deep belief network (DBN) and long short-term memory (LSTM) neural network are employed to model the LC process that is composed of LC decisions (LCD) and LC implementation (LCI). The empirical LC data provided by Next Generation Simulation project (NGSIM) is utilized to train and test the proposed DBN-based LCD model and LSTM-based LCI model. The results indicate that the proposed data-driven model is able to accurately predict the LC process of a vehicle. The sensitivity analysis shows that the most important factor associated with LCD is the relative position of the preceding vehicle in the target lane. This may be the first work that comprehensively models LC using deep learning approaches.

Joint optimization of vehicle trajectories and intersection controllers with connected automated vehicles: Combined dynamic programming and shooting heuristic approach

Abstract: Connected and automated vehicle (CAV) technologies offer promising solutions to challenges that face today’s transportation systems. Vehicular trajectory control and intersection controller optimization based on CAV technologies are two approaches that have significant potential to mitigate congestion, lessen the risk of crashes, reduce fuel consumption, and decrease emissions at intersections. These two approaches should be integrated into a single process such that both aspects can be optimized simultaneously to achieve maximum benefits. This paper proposes an efficient DP-SH (dynamic programming with shooting heuristic as a subroutine) algorithm for the integrated optimization problem that can simultaneously optimize the trajectories of CAVs and intersection controllers (i.e., signal timing and phasing of traffic signals), and develops a two-step approach (DP-SH and trajectory optimization) to effectively obtain near-optimal intersection and trajectory control plans. Also, the proposed DP-SH algorithm can also consider mixed traffic stream scenarios with different levels of CAV market penetration. Numerical experiments are conducted, and the results prove the efficiency and sound performance of the proposed optimization framework. The proposed DP-SH algorithm, compared to the adaptive signal control, can reduce the average travel time by up to 35.72% and save the consumption by up to 31.5%. In mixed traffic scenarios, system performance improves with increasing market penetration rates. Even with low levels of penetration, there are significant benefits in fuel consumption savings. The computational efficiency, as evidenced in the case studies, indicates the applicability of DP-SH for real-time implementation.

Deep reinforcement learning enabled self-learning control for energy efficient driving

Abstract: To address the air pollution problems and reduce greenhouse gas emissions (GHG), plug-in hybrid electric vehicles (PHEV) have been developed to achieve higher fuel efficiency. The Energy Management System (EMS) is a very important component of a PHEV in achieving better fuel economy and it is a very active research area. So far, most of the existing EMS strategies are either just simply following predefined rules that are not adaptive to changing driving conditions; or heavily relying on accurate prediction of future traffic conditions. Deep learning algorithms have been successfully applied to many complex problems and proved to even outperform human beings in some tasks (e.g., play chess) in recent years, which shows the great potential of such methods in practical engineering problems. In this study, a deep reinforcement learning (Deep Q-network or DQN) based PHEV energy management system is designed to autonomously learn the optimal fuel/electricity splits from interactions between the vehicle and the traffic environment. It is a fully data-driven and self-learning model that does not rely on any prediction, predefined rules or even prior human knowledge. The experiment results show that the proposed model is capable of achieving 16.3% energy savings (with the designed PHEV simulation model) on a typical commute trip, compared to conventional binary control strategies. In addition, a dueling Deep Q-network with dueling structure (DDQN) is also implemented and compared with single DQN in particular with respect to the convergence rate in the training process.

What drives the use of ridehailing in California? Ordered probit models of the usage frequency of Uber and Lyft

Abstract: The availability of ridehailing services, such as those provided by Uber and Lyft in the U.S. market, as well as the share of trips made by these services, are continuously growing. Yet, the factors affecting the frequency of use of these services are not well understood. In this paper, we investigate how the frequency of use of ridehailing varies across segments of the California population and under various circumstances. We analyze data from the California Millennials Dataset (N = 1975), collected in fall 2015 through an online survey administered to both millennials and members of the preceding Generation X. We estimate an ordered probit model with sample selection and a zero-inflated ordered probit model with correlated error terms to distinguish the factors affecting the frequency of use of ridehailing from those affecting the adoption of these services. The results are consistent across models: sociodemographic variables are important predictors of service adoption but do not explain much of the variation in the frequency of use. Land use mix and activity density respectively decrease and increase the frequency of ridehailing. The results also confirm that individuals who frequently use smartphone apps to manage other aspects of their travel (e.g. to select a route or check traffic) are more likely to adopt ridehailing and use it more often. This is also true for long-distance travelers, in particular, those who frequently travel by plane for leisure purposes. Individuals with higher willingness to pay to reduce their travel time use ridehailing more often. Those with stronger preferences to own a personal vehicle and those with stronger concerns about the safety/security of ridehailing are less likely to be frequent users. These results provide new insights into the adoption and use of ridehailing that could help to inform planning and forecasting efforts.

A consensus-based distributed trajectory control in a signal-free intersection

Abstract: This paper develops a distributed cooperative control logic to determine conflict-free trajectories for connected and automated vehicles (CAVs) in signal-free intersections. The cooperative trajectory planning problem is formulated as vehicle-level mixed-integer non-linear programs (MINLPs) that aim to minimize travel time of each vehicle and their speed variations, while avoiding near-crash conditions. To push vehicle-level solutions towards global optimality, we develop a coordination scheme between CAVs on conflicting movements. The coordination scheme shares vehicle states (i.e., location) over a prediction horizon and incorporates such information in CAVs’ respective MINLPs. Therefore, the CAVs will reach consensus through an iterative process and select conflict-free trajectories that minimize their travel time. The numerical experiments quantify the effects of the proposed methodology on traffic safety and performance measures in an intersection. The results show that the proposed distributed coordinated framework converges to near-optimal CAV trajectories with no conflicts in the intersection neighborhood. While the solutions are found in real-time, the comparison to a central intersection control logic for CAVs indicates a maximum marginal objective value of 2.30%. Furthermore, the maximum marginal travel time, throughput, and average speed do not exceed 0.5%, 0.1%, and 0.5%, respectively. The proposed control logic reduced travel time by 43.0–70.5%, and increased throughput and average speed respectively by 0.8–115.6% and 59.1–400.0% compared to an optimized actuated signal control, while eliminating all near-crash conditions.

Reducing time headway for platooning of connected vehicles via V2V communication

Abstract: In a platoon of connected vehicles, time headway plays an important role in both traffic capacity and road safety. It is desirable to maintain a lower time headway while satisfying string stability in a platoon, since this leads to a higher traffic capacity and guarantees the disturbance attenuation ability. In this paper, we study a multiple-predecessor following strategy to reduce time headway via vehicle-to-vehicle (V2V) communication. We first introduce a new definition of desired inter-vehicle distances based on the constant time headway (CTH) policy, which is suitable for general communication topologies. By exploiting lower-triangular structures in a time headway matrix and an information topology matrix, we derive a set of necessary and sufficient conditions on feedback gains for internal asymptotic stability. Further, by analyzing the stable region of feedback gains, a necessary and sufficient condition on time headway is also obtained for the string stability specification. It is proved that a platoon can be asymptotically stable and string stable when the time headway is lower bounded. Moreover, this bound can be reduced by increasing the number of predecessors. These results explicitly highlight the benefits of V2V communication on reducing time headway for platooning of connected vehicles.

Understanding consumers’ willingness to use ride-sharing services: The roles of perceived value and perceived risk

Abstract: In order to popularise the sustainable transport innovation of ride-sharing, it is critical for service providers and policymakers to understand the factors affecting ride-sharing willingness of potential users. This research explores the drivers of non-users’ willingness to use ride-sharing services from the perspectives of perceived value and perceived risk, where perceived value and perceived risk are both conceptualised as formative second-order constructs constituted by their first-order value components and risk components. The data was collected in China through an online questionnaire from 378 respondents who had never used a ride-sharing platform. Partial least squares structural equation modelling (PLS-SEM) is used to verify the research model and hypotheses. The empirical results reveal that perceived value is positively associated with consumer willingness to participate in ride-sharing, but perceived risk is negatively related to consumers’ ride-sharing intention. Contrary to expectations, perceived risk positively moderates the effect of perceived value on consumers’ ride-sharing intention. This study contributes to a deeper understanding of the effects of consumers’ value perception and risk perception on their acceptance of internet-based ride-sharing services. Measures to promote ride-sharing include maximising consumers’ value of ride-sharing and their perception of value as well as reducing potential risks in ride-sharing process.

Congestion pricing in a world of self-driving vehicles: An analysis of different strategies in alternative future scenarios

Abstract: The introduction of autonomous (self-driving) and shared autonomous vehicles (AVs and SAVs) will affect travel destinations and distances, mode choice, and congestion. From a traffic perspective, although some congestion reduction may be achieved (thanks to fewer crashes and tighter headways), car-trip frequencies and vehicle miles traveled (VMT) are likely to rise significantly, reducing the benefits of driverless vehicles. Congestion pricing (CP) and road tolls are key tools for moderating demand and incentivizing more socially and environmentally optimal travel choices. This work develops multiple CP and tolling strategies in alternative future scenarios, and investigates their effects on the Austin, Texas network conditions and traveler welfare, using the agent-based simulation model MATSim. Results suggest that, while all pricing strategies reduce congestion, their social welfare impacts differ in meaningful ways. More complex and advanced strategies perform better in terms of traffic conditions and traveler welfare, depending on the development of the mobility landscape of autonomous driving. The possibility to refund users by reinvesting toll revenues as traveler budgets plays a salient role in the overall efficiency of each CP strategy as well as in the public acceptability.

The hybrid vehicle-drone routing problem for pick-up and delivery services

Abstract: This paper presents a mathematical formulation and efficient solution methodology for the hybrid vehicle-drone routing problem (HVDRP) for pick-up and delivery services. The problem is formulated as a mixed-integer program, which minimizes the vehicle and drone routing cost to serve all customers. The formulation captures the vehicle-drone routing interactions during the drone dispatching and collection processes and accounts for drone operation constraints related to flight range and load carrying capacity limitations. A novel solution methodology is developed which extends the classic Clarke and Wright algorithm to solve the HVDRP. The performance of the developed heuristic is benchmarked against two other heuristics, namely, the vehicle-driven routing heuristic and the drone-driven routing heuristic. A set of experiments are conducted to evaluate the performance of the developed heuristics and to illustrate the capability of the developed model in answering a wide variety of questions related to the planning of the vehicle-drone delivery system.

Characterization of ridesplitting based on observed data: A case study of Chengdu, China

Abstract: With the development of mobile internet technology, on-demand ridesourcing services have rapidly spread across the world and have caused debates in the transportation industry. While many researchers have begun to study the characteristics and impacts of ridesourcing, there are few published studies specifically on ridesplitting, a ridesourcing service that matches riders with similar origins or destinations to the same ridesourcing driver and vehicle in real time. This paper aims to explore the characteristics and effects of ridesplitting using observed ridesourcing data provided by DiDi Chuxing that contain complete datasets of the ridesourcing trajectories and orders in the city of Chengdu, China. First, a ridesplitting trip identification (RTI) algorithm is developed to separate the shared rides from the single rides (non-ridesplitting orders) and derive ridesplitting scales. Second, a ridesplitting trajectory reconstruction (RTR) algorithm is proposed to estimate the ridesplitting effects on delays and detours. Then, we analyze and compare the scales, spatiotemporal patterns and travel characteristics between shared rides and single rides, which are very different. The results show that the current percentage of ridesplitting in ridesourcing is still low (6–7%), which may be explained by the extra delay (about 10 min on average), detour (about 1.55 km on average), and degraded travel time reliability caused by ridesplitting. In addition, built environment factors, such as density, diversity, and development, are also correlated with ridesplitting demand and delay. The findings of this study can help better understand the features of ridesplitting and develop strategies for improving its use in emerging ridesourcing services.

Integrating ridesourcing services with public transit: An evaluation of traveler responses combining revealed and stated preference data

Abstract: Inspired by the success of private ridesourcing companies such as Uber and Lyft, transit agencies have started to consider integrating ridesourcing services (i.e. on-demand, app-driven ridesharing services) with public transit. Ridesourcing services may enhance the transit system in two major ways: replacing underutilized routes to improve operational efficiency, and providing last-mile connectivity to extend transit’s catchment area. While an integrated system of ridesourcing services and public transit is conceptually appealing, little is known regarding whether and how consumers might use a system like this and what key service attributes matter the most to them. This article investigates traveler responses to a proposed integrated transit system, named MTransit, at the University of Michigan Ann Arbor campus. We conducted a large-sample survey to collect both revealed preference (RP) and stated preference (SP) data and fit a RP-SP mixed logit model to examine the main determinants of commuting mode choice. The model results show that transfers and additional pickups are major deterrents for MTransit use. We further applied the model outputs to forecast the demand for MTransit under different deployment scenarios. We find that replacing low-ridership bus lines with ridesourcing services could slightly increase transit ridership while reducing operations costs. The service improvements offered by ridesourcing mainly come from reductions in wait time. Though relatively small in our study, another source of improvement is the decrease of in-vehicle travel time. Moreover, we find that when used to provide convenient last-mile connections, ridesourcing could provide a significant boost to transit. This finding verifies a popular notion among transit professionals that ridesourcing services can serve as a complement to public transit by enhancing last-mile transit access.

Optimization of shared autonomous electric vehicles operations with charge scheduling and vehicle-to-grid

Abstract: Shared autonomous electric vehicles, also known as autonomous mobility on demand systems, are expected to become commercially available by the next decade. In this work we propose a methodology for the optimization of their charging with vehicle-to-grid in parallel with optimized routing and relocation. The methodology presented is based on previous work expanded to include charge optimization. The proposed model optimizes transport service and charging at two different time scales by running two model-predictive control optimization algorithms in parallel. Charging is optimized over longer time scales to minimize both approximate waiting times and electricity costs. Routing and relocation are optimized at shorter time scales to minimize waiting times, with the results of the long-time-scale optimization as charging constraints. This approach allows efficient optimization of both aspects of system operation. The problem is solved as a mixed-integer linear program. A case study using transport and electricity price data for Tokyo is used to test the model. Results show that the system can substantially reduce charging costs without significantly affecting waiting times, with cost reduction dependent on electricity price variability. Vehicle-to-grid is shown to be unsuitable for current electricity and battery prices, however offering substantial savings with price profiles with higher variability.

A deep learning approach to real-time parking occupancy prediction in transportation networks incorporating multiple spatio-temporal data sources

Abstract: A deep learning model is adopted for predicting block-level parking occupancy in real time. The model leverages Graph-Convolutional Neural Networks (GCNN) to extract the spatial relations of traffic flow in large-scale networks, and utilizes Recurrent Neural Networks (RNN) with Long-Short Term Memory (LSTM) to capture the temporal features. In addition, the model is capable of taking multiple heterogeneously structured traffic data sources as input, such as parking meter transactions, traffic speed, and weather conditions. The model performance is evaluated through a case study in Pittsburgh downtown area. The GCNN-based model outperforms other baseline methods including multi-layer LSTM and LASSO with an average testing MAPE of 10.6% when predicting block-level parking occupancies 30 min in advance. The case study also shows that, in generally, the prediction model works better for business areas than for recreational locations. We found that incorporating traffic speed and weather information can significantly improve the prediction performance. Weather data is particularly useful for improving predicting accuracy in recreational areas.

Willingness to pay for self-driving vehicles: Influences of demographic and psychological factors

Abstract: Research on willingness to pay (WTP) can provide practical insights for assessing the value of self-driving vehicle (SDV) technology in the vehicle market. Are people willing to pay extra for the technology? What demographic and psychological factors can influence people’s WTP for this technology? These questions are not yet well investigated. We conducted surveys in two cities in China (total N = 1355) and examined WTP and its potential demographic determinants (familiarity, age, gender, education, and income) and psychological determinants (perceived benefit and risk of SDVs, anticipated perceived dread riding in SDVs, and trust in SDVs). About 26.3% of participants were unwilling to pay extra, 39.3% were willing to pay less than $2900, and the remaining 34.3% were willing to pay more than $2900. Younger and highly educated participants with higher-income were willing to pay more. Participants who had heard about SDVs before the survey reported higher WTP and higher trust and perceived higher benefits, lower risks, and lower dread. Trust and perceived benefit were positive predictors of WTP and perceived risk and perceived dread were negative predictors of WTP. Our results may offer practical implications for increasing the public’s acceptance and WTP of SDVs.

Real-time city-scale ridesharing via linear assignment problems

Abstract: In this paper, we propose a novel, computational efficient, dynamic ridesharing algorithm. The beneficial computational properties of the algorithm arise from casting the ridesharing problem as a linear assignment problem between fleet vehicles and customer trip requests within a federated optimization architecture. The resulting algorithm is up to four times faster than the state-of-the-art, even if it is implemented on a less dedicated hardware, and achieves similar service quality. Current literature showcases the ability of state-of-the-art ridesharing algorithms to tackle very large fleets and customer requests in almost near real-time, but the benefits of ridesharing seem limited to centralized systems. Our algorithm suggests that this does not need to be the case. The algorithm that we propose is fully distributable among multiple ridesharing companies. By leveraging two datasets, the New York city taxi dataset and the Melbourne Metropolitan Area dataset, we show that with our algorithm, real-time ridesharing offers clear benefits with respect to more traditional taxi fleets in terms of level of service, even if one considers partial adoption of the system. In fact, e.g., the quality of the solutions obtained in the state-of-the-art works that tackle the whole customer set of the New York city taxi dataset is achieved, even if one considers only a proportion of the fleet size and customer requests. This could make real-time urban-scale ridesharing very attractive to small enterprises and city authorities alike. However, in some cases, e.g., in multi-company scenarios where companies have predefined market shares, we show that the number of vehicles needed to achieve a comparable performance to the monopolistic setting increases, and this raises concerns on the possible negative effects of multi-company ridesharing.

Autonomous vehicles can be shared, but a feeling of ownership is important: Examination of the influential factors for intention to use autonomous vehicles

Abstract: Autonomous vehicles are expected to be commercialized within a few years, and researchers have investigated various factors that influence their adoption. However, only a few studies have considered comparative and psychological perspectives that can affect user-vehicle relationships. Focusing on this limitation, this study investigates influential factors on the use of autonomous vehicles in terms of a technology acceptance model (which considers perceived ease of use, perceived usefulness, and intention to use) and factors for autonomous vehicle use (e.g., perceived risk, relative advantage, self-efficacy, and psychological ownership (i.e., feeling of ownership)). Our results show that self-efficacy positively affects the perceived ease of use and intention to use, while the relative advantage affects perceived usefulness. Psychological ownership affects the intention to use but not the perceived usefulness. This implies that encouraging a consumer to form a psychological bond (i.e., psychological ownership) with an autonomous vehicle may be an effective strategy for promoting the use of autonomous vehicles.

Traffic speed prediction for urban transportation network: A path based deep learning approach

Abstract: Traffic prediction, as an important part of intelligent transportation systems, plays a critical role in traffic state monitoring. While many studies accomplished traffic forecasting task with deep learning models, there is still an open issue of exploiting spatial-temporal traffic state features for better prediction performance, and the model interpretability has not been taken serious. In this study, we propose a path based deep learning framework which can produce better traffic speed prediction at a city wide scale, furthermore, the model is both rational and interpretable in the context of urban transportation. Specifically, we divide the road network into critical paths, which is helpful to mine the traffic flow mechanism. Then, each critical path is modeled through the bidirectional long short-term memory neural network (Bi-LSTM NN), and multiple Bi-LSTM layers are stacked to incorporate temporal information. At the stage of traffic prediction, the spatial-temporal features captured from these processes are fed into a fully-connected layer. Finally, results for each path are ensembled for network-wise traffic speed prediction. In the empirical studies, we compare the proposed model with multiple benchmark methods. Under a series of prediction scenarios (i.e., different input and prediction horizons), the superior performance of the proposed framework is validated. Moreover, by analyzing feature from hidden-layer output, the study explains the physical meaning of the hidden feature and illustrate model’s interpretability.

Sequence to sequence learning with attention mechanism for short-term passenger flow prediction in large-scale metro system

Abstract: The accurate short-term passenger flow prediction is of great significance for real-time public transit management, timely emergency response as well as systematical medium and long-term planning. In this paper, we propose an end-to-end deep learning framework that can simultaneously make multi-step predictions for all stations in a large scale metro system. A sequence to sequence model embedded with the attention mechanism forms the backbone of this framework. The sequence to sequence model consists of an encoder network and a decoder network, making it good at modeling sequential data with varying lengths and the attention mechanism further enhances its ability to capture long-range dependencies. We use the proposed framework to predict the number of passengers alighting at each station in the near future, given the number of passengers boarding at each station in the last few short-term periods. The large quantities of real-world data collected from Singapore’s metro system are used to validate the proposed model. In addition, a set of comparisons made among our model and other classical approaches evidently indicates that the proposed model is more scalable and robust than other baselines in making multi-step and network-wide predictions for short-term passenger flow.

Multistage large-scale charging station planning for electric buses considering transportation network and power grid

Abstract: With the applications of electric buses (e-buses), potential solutions to problems related to infrastructures for charging e-buses are emerging. This study particularly focused on large-scale fast charging-station planning for e-buses in the public transportation electrification process, according to the characteristics of e-bus operation and plug-in fast charging mode. We conducted an interdisciplinary study to optimize planning jointly under the transportation system and power grid. In addition to capturing the spatiality of the e-bus charging service network, we further considered temporality in order to conduct long-term planning in view of the continuously growing e-bus charging demand. A spatial-temporal model, which determines the sites and sizes of e-bus charging stations, was proposed and the strategies for multistage infrastructure planning were put forward. The model was equivalently transformed into a mixed-integer second-order cone programming with high computational efficiency. The model and the multistage planning strategies were justified through a series of numerical experiments. A case study of Shenzhen, China was implemented and the robustness of the model to plan changes was studied.