Showing papers in "Transportation Research Part C-emerging Technologies in 2020"

Shared autonomous vehicle services: A comprehensive review

Abstract: The actions of autonomous vehicle manufacturers and related industrial partners, as well as the interest from policy makers and researchers, point towards the likely initial deployment of autonomous vehicles as shared autonomous mobility services. Numerous studies are lately being published regarding Shared Autonomous Vehicle (SAV) applications and hence, it is imperative to have a comprehensive outlook, consolidating the existing knowledge base. This work comprehensively consolidates studies in the rapidly emerging field of SAV. The primary focus is the comprehensive review of the foreseen impacts, which are categorised into seven groups, namely (i) Traffic & Safety, (ii) Travel behaviour, (iii) Economy, (iv) Transport supply, (v) Land–use, (vi) Environment & (vii) Governance. Pertinently, an SAV typology is presented and the components involved in modelling SAV services are described. Issues relating to the expected demand patterns and a required suitable policy framework are explicitly discussed.

The multiple flying sidekicks traveling salesman problem: Parcel delivery with multiple drones

Abstract: This paper considers a last-mile delivery system in which a delivery truck operates in coordination with a fleet of unmanned aerial vehicles (UAVs, or drones). Deploying UAVs from the truck enables customers located further from the depot to receive drone-based deliveries. The problem is first formulated as a mixed integer linear program (MILP). However, owing to the computational complexity of this problem, only trivially-sized problems may be solved directly via the MILP. Thus, a heuristic solution approach that consists of solving a sequence of three subproblems is proposed. Extensive numerical testing demonstrates that this approach effectively solves problems of practical size within reasonable runtimes. Additional analysis quantifies the potential time savings associated with employing multiple UAVs. The analysis also reveals that additional UAVs may have diminishing marginal returns. An analysis of five different endurance models demonstrates the effects of these models on UAV assignments. The model and heuristic also support anticipated future systems that feature automation for UAV launch and retrieval.

Stacked bidirectional and unidirectional LSTM recurrent neural network for forecasting network-wide traffic state with missing values

Abstract: Short-term traffic forecasting based on deep learning methods, especially recurrent neural networks (RNN), has received much attention in recent years. However, the potential of RNN-based models in traffic forecasting has not yet been fully exploited in terms of the predictive power of spatial–temporal data and the capability of handling missing data. In this paper, we focus on RNN-based models and attempt to reformulate the way to incorporate RNN and its variants into traffic prediction models. A stacked bidirectional and unidirectional LSTM network architecture (SBU-LSTM) is proposed to assist the design of neural network structures for traffic state forecasting. As a key component of the architecture, the bidirectional LSTM (BDLSM) is exploited to capture the forward and backward temporal dependencies in spatiotemporal data. To deal with missing values in spatial–temporal data, we also propose a data imputation mechanism in the LSTM structure (LSTM-I) by designing an imputation unit to infer missing values and assist traffic prediction. The bidirectional version of LSTM-I is incorporated in the SBU-LSTM architecture. Two real-world network-wide traffic state datasets are used to conduct experiments and published to facilitate further traffic prediction research. The prediction performance of multiple types of multi-layer LSTM or BDLSTM models is evaluated. Experimental results indicate that the proposed SBU-LSTM architecture, especially the two-layer BDLSTM network, can achieve superior performance for the network-wide traffic prediction in both accuracy and robustness. Further, comprehensive comparison results show that the proposed data imputation mechanism in the RNN-based models can achieve outstanding prediction performance when the model’s input data contains different patterns of missing values.

Drone-aided routing: A literature review

Abstract: The interest in using drones in various applications has grown significantly in recent years. The reasons are related to the continuous advances in technology, especially the advent of fast microprocessors, which support intelligent autonomous control of several systems. Photography, construction, and monitoring and surveillance are only some of the areas in which the use of drones is becoming common. Among these, last-mile delivery is one of the most promising areas. In this work we focus on routing problems with drones, mostly in the context of parcel delivery. We survey and classify the existing works and we provide perspectives for future research.

Safe, efficient, and comfortable velocity control based on reinforcement learning for autonomous driving

Abstract: A model used for velocity control during car following is proposed based on reinforcement learning (RL). To optimize driving performance, a reward function is developed by referencing human driving data and combining driving features related to safety, efficiency, and comfort. With the developed reward function, the RL agent learns to control vehicle speed in a fashion that maximizes cumulative rewards, through trials and errors in the simulation environment. To avoid potential unsafe actions, the proposed RL model is incorporated with a collision avoidance strategy for safety checks. The safety check strategy is used during both model training and testing phases, which results in faster convergence and zero collisions. A total of 1,341 car-following events extracted from the Next Generation Simulation (NGSIM) dataset are used to train and test the proposed model. The performance of the proposed model is evaluated by the comparison with empirical NGSIM data and with adaptive cruise control (ACC) algorithm implemented through model predictive control (MPC). The experimental results show that the proposed model demonstrates the capability of safe, efficient, and comfortable velocity control and outperforms human drivers in that it 1) has larger TTC values than those of human drivers, 2) can maintain efficient and safe headways around 1.2s, and 3) can follow the lead vehicle comfortably with smooth acceleration (jerk value is only a third of that of human drivers). Compared with the MPC-based ACC algorithm, the proposed model has better performance in terms of safety, comfort, and especially running speed during testing (more than 200 times faster). The results indicate that the proposed approach could contribute to the development of better autonomous driving systems. Source code of this paper can be found at https://github.com/MeixinZhu/Velocity_control .

A graph CNN-LSTM neural network for short and long-term traffic forecasting based on trajectory data

Abstract: Traffic forecasting is an important research area in Intelligent Transportation Systems that is focused on anticipating traffic in order to mitigate congestion. In this work we propose a deep neural network that simultaneously extracts the spatial features of traffic, using graph convolution, and its temporal features by means of Long Short Term Memory (LSTM) cells to make both short-term and long-term predictions. The model is trained and tested using sparse trajectory (GPS) data coming from the ride-hailing service of DiDi in the cities of Xi'an and Chengdu in China. Besides, presenting the deep neural network, we also propose a data-reduction technique based on temporal correlation to select the most relevant road links to be used as input. Combining the suggested approaches, our model obtains better results compared to high-performance algorithms for traffic forecasting, such as LSTM or the algorithms presented in the TRANSFOR19 forecasting competition. The model is capable of maintaining its performance over different time-horizons from 5 min to up to 4 h with multi-step predictions.

On the new era of urban traffic monitoring with massive drone data: The pNEUMA large-scale field experiment

Abstract: The new era of sharing information and “big data” has raised our expectations to make mobility more predictable and controllable through a better utilization of data and existing resources. The realization of these opportunities requires going beyond the existing traditional ways of collecting traffic data that are based either on fixed-location sensors or GPS devices with low spatial coverage or penetration rates and significant measurement errors, especially in congested urban areas. Unmanned Aerial Systems (UAS) or simply “drones” have been proposed as a pioneering tool of the Intelligent Transportation Systems (ITS) infrastructure due to their unique characteristics, but various challenges have kept these efforts only at a small size. This paper describes the system architecture and preliminary results of a first-of-its-kind experiment, nicknamed pNEUMA, to create the most complete urban dataset to study congestion. A swarm of 10 drones hovering over the central business district of Athens over multiple days to record traffic streams in a congested area of a 1.3 km2 area with more than 100 km-lanes of road network, around 100 busy intersections (signalized or not), many bus stops and close to half a million trajectories. The aim of the experiment is to record traffic streams in a multi-modal congested environment over an urban setting using UAS that can allow the deep investigation of critical traffic phenomena. The pNEUMA experiment develops a prototype system that offers immense opportunities for researchers many of which are beyond the interests and expertise of the authors. This open science initiative creates a unique observatory of traffic congestion, a scale an-order-of-magnitude higher than what was available till now, that researchers from different disciplines around the globe can use to develop and test their own models.

Automated vehicle acceptance in China: social influence and initial trust are key determinants

Abstract: Although automated vehicles (AVs) could offer a potentially effective solution to improving road safety, the benefit associated with AVs can be realized only when the public intend to use them. While some efforts have been made to understand why people would use AVs, few of them have investigated the role of social and personal factors in AV acceptance. The present study aimed to fill in this research gap. An AV acceptance model was proposed by extending the Technology Acceptance Model (TAM) with social and personal factors, i.e., initial trust, social influence, and the Big Five personality and sensation seeking traits. The validity of the proposed model was confirmed with a questionnaire survey administrated to 647 drivers in China. Results revealed that at the very beginning of AV commercialization, perception factors (i.e., perceived ease of use and perceived usefulness) from the original TAM showed significant influence on users’ intention to use AVs. But more importantly, it was social influence and initial trust that contributed most to explain whether users would accept AVs or not. Some personality traits also played certain roles in AV usage intention. In particular, sensation seekers and those with a higher openness to experience were more likely to trust AVs and had a higher intention to adopt them. In contrast, neurotic people showed a lower level of trust and were less likely to accept AVs. Practically, these findings suggest that promotion of AVs to influential individuals that could help form good social opinions would have significant downstream effects on AV acceptance at the early state of its marketization.

Battery electric bus infrastructure planning under demand uncertainty

Abstract: The electrification of city bus systems is an increasing trend, with many cities replacing their diesel buses with battery electric buses (BEBs). Due to limited battery capacities, and to random battery discharge rates—which are affected by weather, road and traffic conditions—BEBs often need daytime charging to support their operation for a whole day. The deployment of charging infrastructures, as well as the number of stand-by buses available, has a significant effect on the operational efficiency of electric bus systems. In this work, a stochastic integer program has been developed to jointly optimise charging station locations and bus fleet size under random bus charging demand, considering time-of-use electricity tariffs. The stochastic program is first approximated by its sample average and is solved by a customised Lagrangian relaxation approach. The applicability of the model and solution algorithm is demonstrated by applications to a series of hypothetical grid networks and to a real-world Melbourne City bus network. Managerial insights are also presented.

Acceptance of autonomous delivery vehicles for last-mile delivery in Germany – Extending UTAUT2 with risk perceptions

Abstract: The inevitable need to develop new delivery practices in last-mile logistics arises from the enormously growing business to consumer (B2C) e-commerce and the associated challenges for logistics service providers. Autonomous delivery vehicles (ADVs) are believed to have the potential to revolutionise last-mile delivery in a way that is more sustainable and customer focused. However, if not widely accepted, the introduction of ADVs as a delivery option can be a substantial waste of resources. At present, the research on consumers’ receptivity of innovations in last-mile delivery, such as ADVs, is limited. This study is the first that investigates the users’ acceptance of ADVs in Germany by utilising an extended Unified Theory of Acceptance and Use of Technology (UTAUT2) and adapted it to the context of ADVs in last-mile delivery. Quantitative data was collected through an online survey approach (n = 501) and structural equation modelling was undertaken. The results indicate that price sensitivity is the strongest predictor of behavioural intention (i.e., user acceptance), followed by performance expectancy, hedonic motivation, perceived risk, social influence and facilitating conditions, whereas no effect could be found for effort expectancy. These findings have important theoretical and practical contributions in the areas of technology acceptance and last-mile delivery.

Forecasting road traffic speeds by considering area-wide spatio-temporal dependencies based on a graph convolutional neural network (GCN)

Abstract: The traffic state in an urban transportation network is determined via spatio-temporal traffic propagation. In early traffic forecasting studies, time-series models were adopted to accommodate autocorrelations between traffic states. The incorporation of spatial correlations into the forecasting of traffic states, however, involved a computational burden. Deep learning technologies were recently introduced to traffic forecasting in order to accommodate the spatio-temporal dependencies among traffic states. In the present study, we devised a novel graph-based neural network that expanded the existing graph convolutional neural network (GCN). The proposed model allowed us to differentiate the intensity of connecting to neighbor roads, unlike existing GCNs that give equal weight to each neighbor road. A plausible model architecture that mimicked real traffic propagation was established based on the graph convolution. The domain knowledge was efficiently incorporated into a neural network architecture. The present study also employed a generative adversarial framework to ensure that a forecasted traffic state could be as realistic as possible considering the joint probabilistic density of real traffic states. The forecasting performance of the proposed model surpassed that of the original GCN model, and the estimated adjacency matrices revealed the hidden nature of real traffic propagation.

Trajectory data-based traffic flow studies: A revisit

Abstract: In this paper, we review trajectory data-based traffic flow studies that have been conducted over the last 15 years. Our purpose is to provide a roadmap for readers who have an interest in the latest developments of traffic flow theory that have been stimulated by the availability of trajectory data. We first highlight the critical role of trajectory data (especially the next generation simulation (NGSIM) trajectory dataset) in the recent history of traffic flow studies. Then, we summarize new traffic phenomena/models at the microscopic/mesoscopic/macroscopic levels and provide a unified view of these achievements perceived from different directions of traffic flow studies. Finally, we discuss some future research directions.

An ensemble deep learning approach for driver lane change intention inference

Abstract: With the rapid development of intelligent vehicles, drivers are increasingly likely to share their control authorities with the intelligent control unit. For building an efficient Advanced Driver Assistance Systems (ADAS) and shared-control systems, the vehicle needs to understand the drivers’ intent and their activities to generate assistant and collaborative control strategies. In this study, a driver intention inference system that focuses on the highway lane change maneuvers is proposed. First, a high-level driver intention mechanism and framework are introduced. Then, a vision-based intention inference system is proposed, which captures the multi-modal signals based on multiple low-cost cameras and the VBOX vehicle data acquisition system. A novel ensemble bi-directional recurrent neural network (RNN) model with Long Short-Term Memory (LSTM) units is proposed to deal with the time-series driving sequence and the temporal behavioral patterns. Naturalistic highway driving data that consists of lane-keeping, left and right lane change maneuvers are collected and used for model construction and evaluation. Furthermore, the driver's pre-maneuver activities are statistically analyzed. It is found that for situation-aware, drivers usually check the mirrors for more than six seconds before they initiate the lane change maneuver, and the time interval between steering the handwheel and crossing the lane is about 2 s on average. Finally, hypothesis testing is conducted to show the significant improvement of the proposed algorithm over existing ones. With five-fold cross-validation, the EBiLSTM model achieves an average accuracy of 96.1% for the intention that is inferred 0.5 s before the maneuver starts.

A two-phase optimization model for the demand-responsive customized bus network design

Abstract: This paper proposes a new optimization model for the network design problem of the demand-responsive customized bus (CB). The proposed model consists of two phases: inserting passenger requests dynamically in an interactive manner (dynamic phase) and optimizing the service network statically based on the overall demand (static phase). In the dynamic phase, we propose a hierarchical decision-making model to describe the interactive manner between operator and passengers. The CB network design problem is formulated in a mixed-integer program with the objective of maximizing operator’s revenue. The CB passenger’s travel behavior is measured by a discrete choice model given the trip plan provided by the operator. A dynamic insertion method is developed to address the proposed model in the dynamic phase. For the network design problem in the static phase, the service network is re-optimized based on the confirmed passengers with strict time deviation constraints embedded in the static multi-vehicle pickup and delivery problem. An exact solution method is developed based on the branch-and-bound (B&B) algorithm. Numerical examples are conducted to verify the proposed models and solution algorithms.

Mobility-on-demand: An empirical study of internet-based ride-hailing adoption factors, travel characteristics and mode substitution effects

Abstract: Ride-hailing services are shaping travel behaviours and emergent urban mobility patterns. From their initial diffusion centres in North America and Europe, these on-demand mobility services are increasingly becoming available in developing countries. Yet, empirical research from these contexts on the impact of ride-hailing services is lacking. To address this gap, this paper examines the factors driving the adoption of ride-hailing and the associated travel characteristics and mode substitution effects in Ghana, Sub-Saharan Africa. Using data from a large sample survey (N = 1188) of commuters in a multi-variable structural equation model, the paper shows that socio-demographic factors, perceived benefits and ease of use of ride-hailing, perceived safety risks and car-dependent lifestyles influence adoption and use of ride-hailing services. Similar to other contexts, individuals’ reference ride-hailing trips were mainly for ‘special occasion’ purposes (51%), but work and school journeys were also high (41%). Shorter travel times (≤30 min) and single passenger journeys within inner-suburban and outer-suburban localities typify ride-hailing trips. This contrasts with other contexts where ride-hailing is used frequently by urban dwellers and less so by those in the suburbs. Ride-hailing use replaced conventional taxis (51%), public transport (36%), private car (10%) and walking (1%), suggesting mode substitution effects for individuals’ reference trips. Further exploration of a full day’s travel mode choices also revealed that individuals use other available modes of transport in addition to ride-hailing services. However, multi-modal integration is weak, suggesting that ride-hailing tends to be used alone for full door-to-door journeys, instead of complementing other existing modes in serving first/last mile access for example. The implications of the findings for sustainable mobility are discussed.

Truck-drone team logistics: A heuristic approach to multi-drop route planning

Abstract: Recently there have been significant developments and applications in the field of unmanned aerial vehicles (UAVs). In a few years, these applications will be fully integrated into our lives. The practical application and use of UAVs presents several problems that are of a different nature to the specific technology of the components involved. Among them, the most relevant problem deriving from the use of UAVs in logistics distribution tasks is the so-called “last mile” delivery. In the present work, we focus on the resolution of the truck-drone team logistics problem. The problems of tandem routing have a complex structure and have only been partially addressed in the scientific literature. The use of UAVs raises a series of restrictions and considerations that did not appear previously in routing problems; most notably, aspects such as the limited power-life of batteries used by the UAVs and the determination of rendezvous points where they are replaced by fully-charged new batteries. These difficulties have until now limited the mathematical formulation of truck-drone routing problems and their resolution to mainly small-size cases. To overcome these limitations we propose an iterated greedy heuristic based on the iterative process of destruction and reconstruction of solutions. This process is orchestrated by a global optimization scheme using a simulated annealing (SA) algorithm. We test our approach in a large set of instances of different sizes taken from literature. The obtained results are quite promising, even for large-size scenarios.

Joint optimization of customer location clustering and drone-based routing for last-mile deliveries

Abstract: With growing consumer demand and expectations, companies are attempting to achieve cost-efficient and faster delivery operations. The integration of autonomous vehicles, such as drones, in the last-mile network design can curtail many operational challenges and provide a competitive advantage. This paper deals with the problem of delivering orders to a set of customer locations using multiple drones that operate in conjunction with a single truck. To take advantage of the drone fleet, the delivery tasks are parallelized by concurrently dispatching the drones from a truck parked at a focal point (ideal drone launch location) to the nearby customer locations. Hence, the key decisions to be optimized are the partitioning of delivery locations into small clusters, identifying a focal point per cluster, and routing the truck through all focal points such that the customer orders in each cluster are fulfilled either by a drone or truck. In contrast to prior studies that tackle this problem using multi-phase sequential procedures, this paper presents mathematical programming models to jointly optimize all the decisions involved. We also consider two polices for choosing a cluster focal point - (i) restricting it to one of the customer locations, and (ii) allowing it to be anywhere in the delivery area (i.e., a customer or non-customer location). Since the models considering unrestricted focal points are computationally expensive, an unsupervised machine learning-based heuristic algorithm is proposed to accelerate the solution time. Initially, we treat the problem as a single objective by independently minimizing either the total cost or delivery completion time. Subsequently, the two conflicting objectives are considered together for obtaining the set of best trade-off solutions. An extensive computational study is conducted to investigate the impacts of restricting the focal points, and the influence of adopting a joint optimization method instead of a sequential approach. Finally, several key insights are obtained to aid the logistics practitioners in decision making.

GE-GAN: A novel deep learning framework for road traffic state estimation

Abstract: Traffic state estimation is a crucial elemental function in Intelligent Transportation Systems (ITS) However, the collected traffic state data are often incomplete in the real world In this paper, a novel deep learning framework is proposed to use information from adjacent links to estimate road traffic states First, the representation of the road network is realized based on graph embedding (GE) Second, with this representation information, the generative adversarial network (GAN) is applied to generate the road traffic state information in real-time Finally, two typical road networks in Caltrans District 7 and Seattle area are adopted as cases study Experimental results indicate that the estimated road traffic state data of the detectors have higher accuracy than the data estimated by other models

Analyzing the impact of automated vehicles on uncertainty and stability of the mixed traffic flow

Abstract: This paper proposes a stochastic model for mixed traffic flow with human-driven vehicles (HVs) and automated vehicles (AVs). The model is formulated in Lagrangian coordinates considering the heterogeneous behavior of human drivers. We further derive a first and second order approximation of the stochastic model describing the mean and the covariance dynamics, respectively, under different combinations of HVs and AVs in the traffic stream (e.g., randomly distributed in the stream, at the front of the stream, in the middle of the stream and in the rear of the stream). The proposed model allows us to explicitly investigate the interaction between AVs and HVs considering the uncertainty of human driving behavior. Six performance metrics are proposed to measure the impact of AVs on the uncertainty of HVs’ behavior, as well as on the stability of the system. The numerical experiment results show that AVs have significant impact on the uncertainty and stability of the mixed traffic flow system. Larger AV penetration rates can reduce the uncertainty inherent in HV behavior and improve the stability of the mixed flow substantially. Whereas AVs’ reaction time only has subtle impact on the uncertainty of the mixed stream; as well as the position of AVs in the traffic stream has marginal influence in terms of reducing uncertainty and improving stability.

A variational autoencoder solution for road traffic forecasting systems: Missing data imputation, dimension reduction, model selection and anomaly detection

Abstract: Efforts devoted to mitigate the effects of road traffic congestion have been conducted since 1970s. Nowadays, there is a need for prominent solutions capable of mining information from messy and multidimensional road traffic data sets with few modeling constraints. In that sense, we propose a unique and versatile model to address different major challenges of traffic forecasting in an unsupervised manner. We formulate the road traffic forecasting problem as a latent variable model, assuming that traffic data is not generated randomly but from a latent space with fewer dimensions containing the underlying characteristics of traffic. We solve the problem by proposing a variational autoencoder (VAE) model to learn how traffic data are generated and inferred, while validating it against three different real-world traffic data sets. Under this framework, we propose an online unsupervised imputation method for unobserved traffic data with missing values. Additionally, taking advantage of the low dimension latent space learned, we compress the traffic data before applying a prediction model obtaining improvements in the forecasting accuracy. Finally, given that the model not only learns useful forecasting features but also meaningful characteristics, we explore the latent space as a tool for model and data selection and traffic anomaly detection from the point of view of traffic modelers.

Real-time crash prediction on expressways using deep generative models

Abstract: Real-time crash prediction is essential for proactive traffic safety management. However, developing an accurate prediction model is challenging as the traffic data of crash and non-crash cases are extremely imbalanced. Most of the previous studies undersampled non-crash cases to balance the data, which may not capture the heterogeneity of the full non-crash data. This study aims to use the emerging deep learning method called deep convolutional generative adversarial network (DCGAN) model to fully understand the traffic data leading to crashes. With the full understanding of the traffic data of crashes, the DCGAN model could generate more synthetic data related to crashes to balance the dataset. All non-crash data could be used for developing the prediction models. To capture the correlations between different variables, the data are augmented to 2-D matrix as the input for the DCGAN model. The suggested model is evaluated based on data from expressways and compared to two counterparts: (1) synthetic minority over-sampling technique (SMOTE); (2) random undersampling technique. The results suggest that the DCGAN could better understand the crash data characteristics by generating data with better fit of the real data distribution. Four different crash prediction algorithms (i.e., logistic regression model, support vector machine, artificial neural network, and convolutional neural network) are developed based on each balanced data and totally twelve models were estimated. The results indicate that the convolutional neural network model based on the DCGAN balanced data could provide the best prediction accuracy, validating that the proposed oversampling method could be used for the data balance. Besides, compared to other two models, only the DCGAN-based model could identify the significant effects of speed difference between the upstream and downstream locations which could help guide traffic management strategies. With the prediction model developed based on the balanced data by DCGAN, it is expected that more crashes could be predicted and prevented with more appropriate proactive traffic safety management strategies such as Variable Speed Limits (VSL) and Dynamic Message Signs (DMS).

Yard crane and AGV scheduling in automated container terminal: A multi-robot task allocation framework

Abstract: The efficiency of automated container terminals primarily depends on the synchronization of automated-guided vehicles (AGVs) and automated cranes. Accordingly, we study the integrated rail-mounted yard crane and AGV scheduling problem as a multi-robot coordination and scheduling problem in this paper. Based on a discretized virtualized network, we propose a multi-commodity network flow model with two sets of flow balance constraints for cranes and AGVs. In addition, two side constraints are introduced to deal with inter-robot constraints to reflect the complex interactions among terminal agents accurately. The Alternating Direction Method of Multipliers (ADMM) method is adopted in this study as a market-driven approach to dualize the hard side constraints; therefore, the original problem is decomposed into a set of crane-specific and vehicle-specific subtasks. The cost-effective solutions can be obtained by iteratively adjusting both the primal and dual costs of each subtask. We also compare the computational performance of the proposed solution framework with that of the resource-constrained project scheduling problem (RCPSP) model using commercial solvers. Comparison results indicate that our proposed approach could efficiently find solutions within 2% optimality gaps. Illustrative and real-world instances show that the proposed approach effectively serves the accurate coordination of AGVs and cranes in automated terminals.

A nonconvex low-rank tensor completion model for spatiotemporal traffic data imputation

Abstract: Sparsity and missing data problems are very common in spatiotemporal traffic data collected from various sensing systems. Making accurate imputation is critical to many applications in intelligent transportation systems. In this paper, we formulate the missing data imputation problem in spatiotemporal traffic data in a low-rank tensor completion (LRTC) framework and define a novel truncated nuclear norm (TNN) on traffic tensors of location × day × time of day. In particular, we introduce an universal rate parameter to control the degree of truncation on all tensor modes in the proposed LRTC-TNN model, and this allows us to better characterize the hidden patterns in spatiotemporal traffic data. Based on the framework of the Alternating Direction Method of Multipliers (ADMM), we present an efficient algorithm to obtain the optimal solution for each variable. We conduct numerical experiments on four spatiotemporal traffic data sets, and our results show that the proposed LRTC-TNN model outperforms many state-of-the-art imputation models with missing rates/patterns. Moreover, the proposed model also outperforms other baseline models in extreme missing scenarios.

Joint optimization of vehicle-group trajectory and signal timing: Introducing the white phase for mixed-autonomy traffic stream

Abstract: This study develops a novel mixed-integer non-linear program to control the trajectory of mixed connected-automated vehicles (CAVs) and connected human-driven vehicles (CHVs) through signalized intersections. The trajectory of CAVs is continuously optimized via a central methodology, while a new “white” phase is introduced to enforce CHVs to follow their immediate front vehicle. The movement of CHVs is incorporated in the optimization framework utilizing a customized linear car-following model. During the white phase, CAVs lead groups of CHVs through an intersection. The proposed formulation determines the optimal signal indication for each lane-group in each time step. We have developed a receding horizon control framework to solve the problem. The case study results indicate that the proposed methodology successfully controls the mixed CAV-CHV traffic under various CAV market penetration rates and different demand levels. The results reveal that a higher CAV market penetration rate induces more frequent white phase indication compared to green-red signals. The proposed program reduces the total delay by 19.6%–96.2% compared to a fully-actuated signal control optimized by a state-of-practice traffic signal timing optimization software.

Passenger comfort and trust on first-time use of a shared autonomous shuttle vehicle

Abstract: Autonomous Vehicles (AV) may become widely diffused as a road transport technology around the world. However, two conditions of successful adoption of AVs are that they must be synchronously shared, to avoid negative transport network and environmental consequences, and that high levels of public acceptance of the technology must exist. The implications of these two conditions are that travellers must accept sharing rides with unfamiliar others in Shared Autonomous Vehicles (SAV). Two factors that have been identified as being positive influencers of acceptance are comfort and trust. The present paper undertakes a novel examination as to how comfort and trust ratings are affected by specific attributes of the ride experience of travelling in a fully-automated real-world, shared vehicle. To this end, 55 participants experienced riding in an SAV shuttle under experimental conditions at a test facility. Each experimental run involved two unrelated participants, accompanied by a safety operative and a researcher, undertaking four trips in the SAV, during which two conditions were presented for each of the independent variables of ‘direction of face’ (forwards/backwards) and ‘maximum vehicle speed’ (8/16 km/h). Order of presentation was varied between pairs of participants. After each run, participants rated the dependent variables ‘trust’ and ‘comfort’ (the latter variable comprised by six comfort factors). Expected and evaluative ratings were also obtained during pre-experimental orientation and debriefing sessions. Statistically significant relationships (p

Value of time and reliability for urban pooled on-demand services

Abstract: The uptake of on-demand services is increasing rapidly all over the world. However, the market share of their pooled version (ridesharing, e.g., UberPOOL or LyftLine) is still low, despite its potential in addressing the mobility challenges that dense urban cities are facing. In this research, we analyse user preferences towards pooled on-demand services regarding their time-reliability-cost trade-offs. We study, via stated preference experiments, the value of time (VOT) and value of reliability (VOR) of the different trip stages (waiting stage, in-vehicle stage, and transfer stage when combined with line-based public transport). We target urban Dutch individuals (N = 1006), and address commuting and leisure trips. Results show in-vehicle VOT for pooled on-demand services to amount to 7.88–10.80 €/h. These values are somewhat higher than known values of traditional public transport. We also find waiting VOT (both before the trip and during the transfer stage) to be lower than values previously reported in literature. In general, we find VOR to be lower than VOT: the reliability ratio (VOR/VOT ratio) for both the waiting stage and the in-vehicle stage being around 0.5. In order to understand different preferences, we also estimate latent class choice models. The analysis shows that the main difference between classes pertains to the overall time-cost and reliability-cost trade-offs (VOT and VOR values) rather than in different valuations of the reliability ratio. In addition to serving as input for demand forecasting models such as macroscopic static assignment and agent-based simulation models, our findings can support service providers in developing their strategy when designing pooled on-demand services.

Mitigate the range anxiety: Siting battery charging stations for electric vehicle drivers

Abstract: This study addresses the location problem of electric vehicle charging stations considering drivers’ range anxiety and path deviation. The problem is to determine the optimal locations of EV charging stations in a network under a limited budget that minimize the accumulated range anxiety of concerned travelers over the entire trips. A compact mixed-integer nonlinear programming model is first developed for the problem without resorting to the path and detailed charging pattern pre-generation. After examining the convexity of the model, we propose an efficient outer-approximation method to obtain the e-optimal solution to the model. The model is then extended to incorporate the charging impedance, e.g., the charging time and cost. Numerical experiments in a 25-node benchmark network and a real-life Texas highway network demonstrate the efficacy of the proposed models and solution method and analyze the impact of the battery capacity, path deviation tolerance, budget and the subset of OD pairs on the optimal solution and the performance of the system.

Field experiments on longitudinal characteristics of human driver behavior following an autonomous vehicle

Abstract: Although mixed traffic, including both autonomous vehicles (AV) and human-driven vehicles (HV), is expected to prevail in the foreseeable future, our current understanding of the longitudinal characteristics of mixed traffic is limited and, in particular, lacks evidence from field experiments. To bridge this gap, we designed and conducted a set of field experiments to reveal differences in car-following behaviors between a human driver following-AV and following-HV on both constant speed traffic characteristics with discrete speeds ({10,20,…,60}km/h) and dynamic car-following behaviors with continuous speeds (within 0–60 km/h) in both the indifferentiable and differentiable appearance settings of the AV. We recruited 10 drivers for the experiment (14 runs for each driver and collected position and speed data of the tested vehicles along their complete trajectories based on vehicle gaps, headways, and standard deviations of vehicle speed. A K-means clustering algorithm was applied to classify drivers based on their responses in following-AV vs. following-HV with both constant speed and dynamic speed characteristics. The analyses of the differentiable appearance setting show that different drivers exhibit different behaviors in following-AV vs. following-HV: some are AV-believers, some are AV-skeptics, and the others are insensitive. Yet in the indifferentiable appearance setting, there is no significant difference between following a lead AV and following a lead HV. This reveals that drivers’ response to the lead vehicle depends on their subjective trusts on AV technologies rather than the actual driving behavior. The results suggest that, depending on the characteristics and composition of the drivers, classic car-following behavior in pure HV traffic may need to be updated for modeling mixed traffic in the near future.

Examining the effects of emotional valence and arousal on takeover performance in conditionally automated driving

Abstract: In conditionally automated driving, drivers have difficulty in takeover transitions as they become increasingly decoupled from the operational level of driving. Factors influencing takeover performance, such as takeover lead time and the engagement of non-driving-related tasks, have been studied in the past. However, despite the important role emotions play in human-machine interaction and in manual driving, little is known about how emotions influence drivers’ takeover performance. This study, therefore, examined the effects of emotional valence and arousal on drivers’ takeover timeliness and quality in conditionally automated driving. We conducted a driving simulation experiment with 32 participants. Movie clips were played for emotion induction. Participants with different levels of emotional valence and arousal were required to take over control from automated driving, and their takeover time and quality were analyzed. Results indicate that positive valence led to better takeover quality in the form of a smaller maximum resulting acceleration and a smaller maximum resulting jerk. However, high arousal did not yield an advantage in takeover time. This study contributes to the literature by demonstrating how emotional valence and arousal affect takeover performance. The benefits of positive emotions carry over from manual driving to conditionally automated driving while the benefits of arousal do not.

Cooperative merging control via trajectory optimization in mixed vehicular traffic

Abstract: A major challenging issue related to the emerging mixed traffic vehicular system, composed of connected and automated vehicles (CAVs) together with human-driven vehicles, is the lack of adequate modeling and control framework, especially at traffic bottlenecks such as highway merging areas. A hierarchical control framework for merging areas is first outlined, where we assume that the merging sequence is decided by a higher control level. The focus of this paper is the lower level of the control framework that establishes a set of control algorithms for cooperative CAV trajectory optimization, defined for different merging scenarios in the presence of mixed traffic. To exploit complete cooperation flexibility of the vehicles, we identify six scenarios, consisting of triplets of vehicles, defined based on the different combinations of CAVs and conventional vehicles. For each triplet, different consecutive movement phases along with corresponding desired distance and speed set-points are designed. Through the movement phases, the CAVs engaged in the triplet cooperate to determine their optimal trajectories aiming at facilitating an efficient merging maneuver, while complying with realistic constraints related to safety and comfort of vehicle occupants. Distinct models are considered for each triplet, and a Model Predictive Control scheme is employed to compute the cooperative optimal control inputs, in terms of acceleration of CAVs, accounting also for human-driven vehicles’ uncertainties, such as drivers’ reaction time and desired speed tracing error. Simulation investigations demonstrate that the proposed cooperative merging algorithms ensure efficient and smooth merging maneuvers while satisfying all the prescribed constraints.