Accurate and timely alerts for drivers or automated systems to unfolding collisions remains a challenge in road safety, particularly in highly interactive urban traffic. Existing approaches require labour-intensive annotation of sparse risk, struggle to consider varying contextual factors, or are useful only in the scenarios they are designed for. To address these limits, this study introduces the generalised surrogate safety measure (GSSM), a new approach that learns exclusively from naturalistic driving without crash or risk labels. GSSM captures the patterns of normal driving and estimates the extent to which a traffic interaction deviates from the norm towards unsafe extreme. Utilising neural networks, normal interactions are characterised by context-conditioned distributions of multi-directional spacing between road users. In the same interaction context, a spacing closer than normal entails higher risk of potential collision. Then a context-adaptive risk score and its associated probability can be calculated based on the theory of extreme values. Any measurable factors, such as motion kinematics, weather, lighting, can serve as part of the context, allowing for diverse coverage of safety-critical interactions. Multiple public driving datasets are used to train GSSMs, which are tested with 2,591 real-world crashes and near-crashes reconstructed from the SHRP2 NDS. A vanilla GSSM using only instantaneous states achieves AUPRC of 0.9 and secures a median time advance of 2.6 seconds to prevent potential collisions. Additional data and contextual factors provide further performance gains. Across various interaction types such as rear-end, merging, and crossing, the accuracy and timeliness of GSSM consistently outperforms existing baselines. GSSM therefore establishes a scalable, context-aware, and generalisable foundation to proactively quantify collision risk in traffic interactions.

Integrating renewable energy sources, such as solar and wind, challenges grid stability due to their intermittent nature. Vehicle-to-grid (V2G) technology provides a promising solution by utilizing electric vehicles (EVs) as decentralized energy storage systems, enabling the storage of surplus energy during low demand and its release during peak demand. The effectiveness of V2G depends critically on car usage patterns. Data from the Netherlands Mobility Panel (MPN) of 2022, comprising travel diaries from 2,505 households, was analyzed to explore this. A methodology was developed to create car usage profiles based on parking durations and locations, distinguishing weekday and weekend patterns. The analysis shows that vehicles are predominantly parked at home, with weekday profiles reflecting work-related parking and weekend profiles highlighting increased leisure activity. Households with shared cars showed higher driving activity and shorter parking durations than households with a 1:1 car-to-license ratio or surplus vehicles. Six distinct car usage clusters were identified for weekdays and four for weekends.

Among real-time traffic control methods, max-pressure (MP) control stands out due to its simplicity, decentralized nature, and robust theoretical foundation. Besides, advancements in connected vehicle (CV) technology have motivated a significant amount of research into traffic signal control based on CVs. Nevertheless, few studies have been dedicated to MP control in partially CV environments and meanwhile consider multi-modal traffic flows. To fill this research gap, this study proposes CV-based multi-modal MP control (CV-MMP), which calculates the pressure based on travel time information of CVs weighted by vehicle occupancy. Therefore, a hierarchical multi-modal traffic signal priority controller is achieved in a soft manner. Besides, adapting to the requirements of practical applications, CV-MMP is extended to fuse detector data and consider phase switching lost time and cyclic phase sequence. The evaluation results based on a toy network simulation demonstrate that CV-MMP can significantly reduce transit delay with a small increase in private vehicle delay, resulting in a significant reduction in average person delay. In addition, approximately 75% of CBs pass through the network without experiencing delays due to stopping. Therefore, our method can achieve effective transit signal priority and even transit signal coordination under single transit requests.

The effectiveness of neural network models largely relies on learning meaningful latent patterns from data, where self-supervised learning of informative representations can enhance model performance and generalisability. However, self-supervised representation learning for spatially characterised time series, which are ubiquitous in transportation domain, poses unique challenges due to the necessity of maintaining fine-grained spatio-temporal similarities in the latent space. In this study, we introduce two structure-preserving regularisers for the contrastive learning of spatial time series: one regulariser preserves the topology of similarities between instances, and the other preserves the graph geometry of similarities across spatial and temporal dimensions. To balance the contrastive learning objective and the need for structure preservation, we propose a dynamic weighting mechanism that adaptively manages this trade-off and stabilises training. We validate the proposed method through extensive experiments, including multivariate time series classification to demonstrate its general applicability, as well as macroscopic and microscopic traffic prediction to highlight its particular usefulness in encoding traffic interactions. Across all tasks, our method preserves the similarity structures more effectively and improves state-of-the-art task performances. This method can be integrated with an arbitrary neural network model and is particularly beneficial for time series data with spatial or geographical features. Furthermore, our findings suggest that well-preserved similarity structures in the latent space indicate more informative and useful representations. This provides insights to design more effective neural networks for data-driven transportation research. Our code is made openly accessible with all resulting data at this https URL: https://github.com/yiru-jiao/spclt

Large-scale prediction of trip production is essential for origin–destination (OD) demand estimation and prediction. One of the main challenges in predicting trip production patterns lies in addressing spatial-temporal correlations and variations. Whereas many studies focus on temporal correlations, very few consider spatial adjacency between traffic analysis zones (TAZ) as explanatory variables. This research proposes a method that integrates a graph convolutional neural network (GCN) into a long short-term memory network (LSTM) to do exactly that. By introducing a nationwide graph that encodes the adjacency of TAZs, spatial heterogeneity is considered in the prediction process, and a single prediction model is trained for the entire network, thereby avoiding the need to train multiple separate models and potentially reducing overall training overhead, while increasing the prediction accuracy. Moreover, with this model, we investigate the effect of spatial scale on spatial uncertainty and prediction accuracy and analyze prediction errors, residual patterns, and their associations with socio-spatial features at different spatial scales. The findings of this research have important implications for improving OD demand prediction models and provide valuable insights into the role of spatial scale and socio-spatial features in travel demand prediction.

To understand why ridesourcing markets may be prone to evolve towards potentially socially undesirable equilibrium states, we conceptualize the network effects present in ridesourcing provision. In addition, we propose an agent-based model that allows simulating the effect of market conditions and platform strategies on system performance, accounting for such network effects. This day-to-day model captures sequential decentralized processes characterizing both sides of the two-sided ridesourcing market, i.e. information diffusion, platform registration, platform participation, and learning based on experience. We apply the model on a case representing Amsterdam, the Netherlands. Our simulation results suggest that a profit-maximizing ridesourcing platform may trade-off market transaction volume for higher earnings on successful transactions, a strategy that is harmful to the interests of travellers and drivers, and possibly of (very) limited benefit to the platform. Moreover, we find that ridesourcing operations may be viable even when potential supply and demand in an area are limited.

Conditionally automated driving requires drivers to resume vehicle control within constrained time budgets upon receiving takeover requests. Accurately predicting drivers’ takeover time (ToT) is essential for dynamically adjusting time budgets to individual needs across scenarios. This study addresses enduring challenges in reliability and interpretability of ToT prediction models by optimizing predictor selection. Using a driving simulator experiment, we examine the relationship between ToT, driver characteristics, and perceived Spare Capacity (pSC, a cognitive construct from Task-Capability Interface theory) using Category Boosting models. Results show that (i) incorporating 13 additional driver characteristics does not significantly improve prediction accuracy when pSC is already considered; and (ii) individual characteristics influence how drivers cognitively process takeover scenarios, and their predictive contribution likely overlaps with pSC. These findings suggest that monitoring cognitive states may be more effective for ToT prediction than extensive profiling of driver characteristics. This study provides a critical first step toward predictive frameworks for adaptive takeover strategies and offers guidance for designing personalized human–vehicle interactions.

With the increased deployment of autonomous vehicles (AVs) in mixed traffic flow, ensuring safe and efficient interactions between AVs and human road users is important. In urban environments, intersections have various conflicts that can greatly affect driving safety and traffic efficiency. This study uses road test data to examine the possible safety and efficiency impacts of intersection conflict resolution involving AVs. The contribution comprises two main aspects. Firstly. we prepare and open a high-quality lateral conflict resolution dataset derived from the Argoverse-2 data, specifically targeting urban intersections. A rigorous data processing pipeline is applied to extract pertinent scenarios, rectify anomalies, enhance data quality, and annotate conflict regimes. This effort yields 5000+ AV-involved and 16000 AV-free cases, covering rich conflict regimes and balanced traffic states. Secondly, we employ surrogate safety measures to assess the safety impact of AVs on human-driven vehicles (HVs) and pedestrians. In addition, a novel concept of Minimum Recurrent Clearance Time (MRCT) is proposed to quantify the traffic efficiency impacts of AVs during conflict resolution. The results show that, for AV–HV and HV–HV conflict resolution processes, the differences in selected safety and efficiency measures for human drivers are statistically insignificant. In contrast, pedestrians demonstrate diverse behaviour adjustments. Some pedestrians behave more conservatively when interacting with AVs than with HVs. Notably, the efficiency of AV-involved conflict resolution is significantly lower than in AV-free instances due to the conservative driving style of AVs. This efficiency gap is particularly large when AVs pass through the conflict point after human drivers in unprotected left turns. These observations offer a perspective on how AVs potentially affect the safety and efficiency of mixed traffic. The processed dataset is openly available via https://github.com/RomainLITUD/conflict_resolution_dataset.

Limited available market share data seems to suggest that ridesourcing platforms benefit from, even thrive on, socio-economic inequality. We suspect that this is associated with high levels of socio-economic inequality allowing for cheap labour as well as increasing the share of travellers with a considerably above-average willingness to pay for travel time savings and comfort. We test the relation between inequality and system performance by means of an agent-based simulation model representing within-day and day-to-day supply-demand interaction in the ridesourcing market. The model captures travellers’ mode choice with a heterogeneous perception of relevant time components, as well as job seekers’ participation choice with heterogeneous reservation wage. Our experiments cover scenarios for the entire spectrum ranging from perfect equality to extreme inequality. For several of such scenarios, we explore alternative platform pricing strategies. Our analysis shows a strong, positive relationship between socio-economic inequality and ridesourcing market share. This is the outcome of the combination of cheap labour and time-sensitive ridesourcing users, reinforced by network effects inherent to ridesourcing markets. We find that driver earnings are minimal in urban areas with large socio-economic inequality. In such contexts, drivers are likely to face a high platform commission, and yet, fierce competition for passengers.

Integrating Automated Vehicles (AVs) into existing traffic systems holds the promise of enhanced road safety, reduced congestion, and more sustainable travel. Effective integration of AVs requires understanding the interactions between AVs and Human-driving Vehicles (HVs), especially during the transition period in which AVs and HVs coexist in a mixed traffic environment. Numerous recent empirical studies find reduced headways of human drivers following an AV compared to following an HV, and attribute this reduction to behavioural changes of drivers when they follow AVs. However, more factors may be at play due to the inherent inconsistencies between the comparison conditions of HV-following-AV and HV-following-HV. This study scrutinises three alternative explanations for the observed reduction in headways: (1) systematic differences in car-following states during data collection, (2) systematic differences in driving variability between leading AVs and HVs, and (3) systematic differences in driving characteristics of leading AVs versus HVs. We use a large-scale dataset extracted from Lyft AV motion data and examine each of these explanations through data stratification and simulation. Our results show that all three mechanisms contribute to the observed reduction in headways of human drivers following AVs. In addition, our findings highlight the importance of driving homogeneity and stability in achieving reliably shorter headways. Thereby, this study offers a more comprehensive understanding on the difference between HV–AV and HV–HV interactions in mixed traffic, and is expected to promote more effective integration of AVs into human traffic.

Safety is the cornerstone of L2+ autonomous driving and one of the fundamental tasks is forward collision warning that detects potential rear-end collisions. Potential collisions are also known as conflicts, which have long been indicated using Time-to-Collision with a critical threshold to distinguish safe and unsafe situations. Such indication, however, focuses on a single scenario and cannot cope with dynamic traffic environments. For example, TTC-based crash warning frequently misses potential collisions in congested traffic, and issues false alarms during lane-changing or parking. Aiming to minimise missed and false alarms in conflict detection, this study proposes a more reliable approach based on vehicle spacing patterns. To test this approach, we use both synthetic and real-world conflict data. Our experiments show that the proposed approach outperforms single-threshold TTC unless conflicts happened in the exact way that TTC is defined, which is rarely true. When conflicts are heterogeneous and when the information of conflict situation is incompletely known, as is the case with real-world conflicts, our approach can achieve less missed and false detection. This study offers a new perspective for conflict detection, and also a general framework allowing for further elaboration to minimise missed and false alarms. Less missed alarms will contribute to fewer accidents, meanwhile, fewer false alarms will promote people's trust in collision avoidance systems. We thus expect this study to contribute to safer and more trustworthy autonomous driving.

The substantial increase in traffic data offers new opportunities to inspect traffic congestion dynamics from different perspectives. This paper presents a novel framework for the interpretable representation and customizable retrieval of traffic congestion patterns using causal relation graphs, which harnesses many of these opportunities. By integrating domain knowledge with innovative data management techniques, we address the challenges of effectively handling and retrieving the growing volume of traffic data for diverse analytical purposes. The framework leverages causal graphs to encode traffic congestion patterns, capturing fundamental phenomena and their spatiotemporal relationships, thus facilitating an interpretable high-level view of traffic dynamics. Moreover, a customizable similarity measurement function is introduced based on inexact graph matching, allowing users to tailor the retrieval process to specific requirements. This framework’s capability to retrieve customizable and interpretable congestion patterns is demonstrated through extensive experiments with real-world highway traffic data in the Netherlands, highlighting its value in supporting diverse data-driven studies and applications.

Traffic conflict detection is essential for proactive road safety by identifying potential collisions before they occur. Existing methods rely on surrogate safety measures tailored to specific interactions (e.g., car-following, side-swiping, or path-crossing) and require varying thresholds in different traffic conditions. This variation leads to inconsistencies and limited adaptability of conflict detection in evolving traffic environments, particularly as the integration of autonomous driving systems adds complexity. Consequently, there is an increasing need for consistent detection of traffic conflicts across interaction contexts. To address this need, we propose a unified probabilistic approach in this study. The proposed approach establishes a unified framework of traffic conflict detection, where traffic conflicts are formulated as context-dependent extreme events of road user interactions. The detection of conflicts is then decomposed into a series of statistical learning tasks: representing interaction contexts, inferring proximity distributions, and assessing extreme collision risk. The unified formulation accommodates diverse hypotheses of traffic conflicts and the learning tasks enable data-driven analysis of factors such as motion states of road users, environment conditions, and participant characteristics. Jointly, this approach supports consistent and comprehensive evaluation of the collision risk emerging in road user interactions. We demonstrate the proposed approach by experiments using real-world trajectory data. A unified metric for indicating conflicts is first trained with lane-change interactions on German highways, and then compared with existing metrics using near-crash events from the U.S. 100-Car Naturalistic Driving Study. Our results show that the unified metric provides effective collision warnings, generalises across distinct datasets and traffic environments, covers a broad range of conflict types, and captures a long-tailed distribution of conflict intensity. In summary, this study provides an explainable and generalisable approach that enables traffic conflict detection across varying interaction contexts. The findings highlight its potential to enhance the safety assessment of traffic infrastructures and policies, improve collision warning systems for autonomous driving, and deepen the understanding of road user behaviour in safety–critical interactions.

Conditionally automated driving enables drivers to engage in non-driving-related activities, with the responsibility to take over vehicle control upon request. This takeover process increases the risk of collisions, especially when drivers fail to safely complete takeovers within limited time budgets (i.e., the time offered by automation for takeovers). This phenomenon underlines the significance of providing time budgets that sufficiently accommodate drivers' takeover time (i.e., the time required by drivers to resume conscious control of vehicles). Considering that drivers' takeover time varies significantly across scenarios, this study centres on understanding the role of driver perception in takeover time using the Task-Capability Interface (TCI) theory. The TCI theory suggests that drivers adjust their behaviours based on their perceived task demands and driver capabilities. Accordingly, in a driving simulator experiment featuring diverse traffic densities and distractions, we investigated drivers' takeover time while capturing their perceived task demands and capabilities through a takeover-oriented questionnaire based on established instruments. The results show that drivers generally have longer takeover time as their perceived task demand rises, perceived driver capability diminishes, and perceived spare capacity (perceived driver capability minus perceived task demand) decreases. These patterns fluctuate under conditions of low perceived task demand or high perceived driver capability. When both conditions coincide, drivers necessitate a considerably longer time to regain vehicle control. Our findings on takeover time contribute to the development of strategies aimed at predicting drivers' takeover time, optimizing time budgets, fostering human-centred vehicle design, and enhancing the safety of conditionally automated driving.

The in-vehicle communication provides promising opportunities to improve the road safety and traffic efficiency. Previous studies demonstrated that the professional drivers have better driving skills than the non-professional drivers who allocate more attention to secondary tasks. However, they may not be sensitive to the new in-vehicle technology. In addition, these qualitative studies failed to elaborate on the visual and response behavior differences among different driver groups (professional drivers such as taxi, bus, motorcoach, and non-professional drivers), and lacked the quantitative analysis of driving patterns in a new environment. This paper explores the differences in visual interaction, response characteristics, driving performance, and behavior patterns between the professional and non-professional drivers in the connected environment through a case study of intersection-approaching behavior using a driving simulator. More precisely, two driving scenarios (baseline and human–machine interface (HMI)) were designed in the driving simulator, and 65 participants, including 34 professional drivers and 31 non-professional drivers, completed the experiment. In the HMI scenario, the driver was provided with the signal light phase and phase transition remaining time of the current intersection. This paper also proposes a driving pattern extraction model based on the Bayesian non-parametric method combined with a text clustering algorithm to perform a quantitative description of the driving patterns. The results show that the professional drivers tend to interact less with the HMI compared with the non-professional drivers. Moreover, the professional drivers’ first gaze at the HMI occurs and responds earlier. The proposed driving model can effectively describe 7 patterns of intersection-approaching behavior. The connected information can significantly improve the efficiency of the intersection traffic and the driving behavior. However, the professional drivers are more responsive and behave more consistently. This study can provide insights into the development of personalized assisted driving systems, as the two driving populations differ in their interactions, responses, and behavioral patterns.

The relationship between real-world traffic and pavement raveling is unclear and subject to ongoing debates. This research proposes a novel approach that extends beyond traditional correlation analyses to explore causal mechanisms between mixed traffic and raveling. This approach incorporates the causal discovery method, and is applied to five Dutch porous asphalt (PA) highway sites that have substantial data sets. Findings indicate a nonlinear relationship between traffic volume and raveling, with road age emerging as a shared contributor. The results also suggest that the degree to which different vehicle types contribute as a causal factor for raveling varies with carriageway configurations and lane characteristics. This underlines the need for targeted maintenance strategies. Challenges remain due to confounding correlations among traffic variables, necessitating further development of causal discovery models. This study may not conclusively resolve the debate on to what extent traffic contributes to raveling, but we argue we provide sufficient evidence against rejecting this hypothesis.

Predicting the trajectories of road agents is fundamental for self-driving cars. Trajectory prediction contains many sources of uncertainty in data and modelling. A thorough understanding of this uncertainty is crucial in a safety-critical task like auto-piloting a vehicle. In practice, it is necessary to distinguish between the uncertainty caused by partial observability of all factors that may affect a driver's near-future decisions, the so-called aleatoric uncertainty, and the uncertainty of deploying a model in new scenarios that are possibly not present in the training set, the so-called epistemic uncertainty. They reflect the trade-off between data collection and model improvement In this paper, we propose a new framework to systematically quantify both sources of uncertainty. Specifically, to approximate the spatial distribution of an agent's future position, we propose a 2D histogram-based deep learning model combined with deep ensemble techniques for measuring aleatoric and epistemic uncertainty by entropy-based quantities. The proposed Uncertainty Quantification Network (UQnet) employs a causal part to enhance its generalizability so rare driving behaviours can be effectively identified. Experiments on the INTERACTION dataset show that UQnet is able to give more robust predictions in generalizability tests compared to the correlation-based models. Further analysis presents that high aleatoric uncertainty cases are mainly caused by heterogeneous driving behaviours and unknown intended directions. Based on this aleatoric uncertainty component, we estimate the lower bounds of mean-square-error and final-displacement-error as indicators for the predictability of trajectories. Furthermore, the analysis of epistemic uncertainty illustrates that domain knowledge of speed-dependent driving behaviour is essential for adapting a model from low-speed to high-speed situations. Our paper contributes to motion forecasting with a new framework, that recasts the problem of accuracy improvement in a way that focuses on differentiating between unpredictable components and rare cases for which more and different data should be collected.

Traffic condition forecasting is fundamental for Intelligent Transportation Systems. Besides accuracy, many services require an estimate of uncertainty for each prediction. Uncertainty quantification must consider the inherent randomness in traffic dynamics, the so-called aleatoric uncertainty, and the additional distrust caused by data shortage, the so-called epistemic uncertainty. They together depict how predictable macroscopic traffic is. This study uses deep ensembles of graph neural networks to estimate both types of uncertainty in network-level speed forecasting. Experimental results given by the used model reveal that, although rare congestion patterns arise randomly, the short-term predictability of traffic states is mainly restricted by the irreducible stochasticity in traffic dynamics. The predicted future state bifurcates into congested or free-flowing cases. This study suggests that the potential for improving prediction models through expanding speed and flow data is limited while diversifying data types is crucial.

Resolving predicted conflicts is vital for safe and efficient autonomous vehicles (AV). In practice, vehicular motion prediction faces inherent uncertainty due to heterogeneous driving behaviours and environments. This spatial uncertainty increases non-linearly with prediction time horizons, leading AVs to perceive more road space occupied by conflicting vehicles. Reacting early to resolve predicted conflicts can ensure safety but may adversely affect traffic efficiency. Therefore, determining how far ahead AVs should start resolving predicted conflicts based on safety and traffic efficiency constraints is crucial. To answer this question, this study proposes a novel approach to explore the trade-off between safety and traffic efficiency considering prediction uncertainty. Firstly, a continuous-time motion prediction framework is proposed for estimating the spatial probability distribution of a vehicle's future position at any moment within the maximum time horizon. Subsequently, average driver space and the corresponding traffic flow are derived from the safety settings of AV and prediction uncertainty. As such, the safety-efficiency trade-off can be quantified. Experiments show that mandatory decision points, high speeds, and traffic state transitions usually cause fast-increasing prediction uncertainty. A case study of Intelligent Driver Models (IDM) shows that traffic efficiency drops rapidly when AVs resolve predicted conflicts longer than 1.5 seconds ahead. AVs can act earlier on motorways for efficiency concerns but must be myopic at urban intersections. Prediction uncertainty fundamentally constrains the safety-efficiency performance of AVs. These findings are instructive for designing traffic-compatible AVs.

This paper presents a novel approach to data-driven time-dependent origin–destination (OD) estimation using a joint origin–destination-path choice formulation, inspired by the well-known equivalence of doubly constraint gravity models and multinomial logit models for joint O–D choice. This new formulation provides a theoretical basis and generalizes an earlier contribution. Although including path choice increases the dimensionality of the problem, it also dramatically improves the quality of the data one can directly use to solve it (e.g. measured path travel times versus coarse centroid-to-centroid travel times); and opens up possibilities to combine different assimilation techniques in a single framework: (1) fast shortest path set computation using static (e.g. road type) and dynamic (speed, travel time) link properties; (2) predicting a “prior OD matrix” using the resulting path-shares and (estimated or measured) production and attraction totals; and (3) scaling/constraining this prior using link flows (informative of demand). If the resulting system of equations has insufficient rank, we use principal component analysis to reduce the dimensionality, solve this reduced problem, and transform that solution back to a full OD matrix. Comprehensive tests and sensitivity analysis on 7 networks with different sizes and characteristics give an empirical underpinning of the extended equivalence principle; demonstrate good accuracy and reliability of the OD estimation method overall; and suggest that the method is robust with respect to major assumptions and contributing factors.