Travel Time Estimation Research Articles

Travel Time Estimation for Optimal Planning in Internal Transportation

Optimal planning depends on precise and exact estimation of the operation costs of mobile robots. Unfortunately, determining the current and future state of a vehicle implies identifying all the parameters in its model. Rather than broadening the number of factors, in this work we adopt the approach of using a higher-level abstraction model to identify only a few cost parameters. Based on the observation that arc travel times accurately reflect the effect of physical states, this work proposes using them as the key parameters to compute accurate path traversal costs in the context of indoor transportation. This approach eliminates the need to model all factors in order to derive the cost for every robot. The resulting model organizes those parameters in a bilinear state-space form and includes the evolution of actual travel times with changing states. We show that the proposed model accurately estimates arc travel times with respect to actual observations gathered from real robots traversing a few arcs of a traffic network until battery exhaustion. We experimentally obtained minimum-cost paths from random origin and destination nodes when using heuristics and the “closer-to-reality” (bilinear-state version of our model) path costs, finding that it can save an average of 15% in transportation time compared to conventional methods.

Leader–follower identification with vehicle-following calibration for non-lane-based traffic

Most car-following models were originally developed for lane-based traffic. Over the past two decades, efforts have been made to calibrate car-following models for non-lane-based traffic. However, traffic conditions with varying vehicle dimensions, intermittent following, and multiple leaders often occur, making subjective Leader–Follower (LF) pair identification challenging. In this study, we analyze Vehicle Following (VF) behavior in traffic with a lack of lane discipline using high-resolution microscopic trajectory data collected in Chennai, India. The paper’s main contributions are threefold. Firstly, three criteria are used to identify LF pairs from the driver’s perspective, taking into account the intermittent following, lack of lane discipline due to consideration of lateral separation, and the presence of in-between vehicles. Secondly, the psycho-physical concept of the regime in the Wiedemann-99 model is leveraged to determine the traffic-dependent “influence zone” for LF identification. Thirdly, a joint and consistent framework is proposed for identifying LF pairs and estimating VF parameters. The proposed methodology outperforms other heuristic-based LF identification methods from the literature in terms of quantitative and qualitative performance measures. The proposed approach can enable robust and more realistic LF identification and VF parameter calibration with practical applications such as level of service (LOS) analysis, capacity, and travel time estimation.

Cross-View Location Alignment Enhanced Spatial-Topological Aware Dual Transformer for Travel Time Estimation

Cross-View Location Alignment Enhanced Spatial-Topological Aware Dual Transformer for Travel Time Estimation

Personalized origin–destination travel time estimation with active adversarial inverse reinforcement learning and Transformer

Travel time estimation is important for instant delivery, vehicle routing, and ride-hailing. Most studies estimate the travel time of specified routes, and only a few studies pay attention to origin–destination travel time estimation (OD-TTE) without a specified route. Moreover, most of these studies on OD-TTE ignore the personalized route preference and the cost of data annotation. To fill this research gap, we analyze the individual route preference and propose a personalized origin–destination travel time estimation method based on active adversarial inverse reinforcement learning (AA-IRL) and Transformer. To analyze the personalized route preference, we integrate adversarial inverse reinforcement learning with active learning, which effectively reduces the cost of sample annotation. After inferring the possible routes, we propose AdaBoost multi-fusion graph convolutional Transformer network (AMGC-Transformer) for travel time estimation. Numerical experiments conducted on ride-hailing and online food delivery trajectories in China validate the advantage of our method. Compared to relevant studies, our approach can improve F1-score of route inference by 2.50–3.35% and reduce the mean absolute error of OD-TTE by 7.44–11.66%.

Is Centralisation of Cancer Services Associated With Under-Treatment of Patients With High-Risk Prostate Cancer?-A National Population-Based Study.

Centralising prostate cancer surgical and radiotherapy services, requires some patients to travel longer to access treatment, but its impact on actual treatment utilisation and outcomes is unknown. Using national cancer registry records linked to administrative hospital data, we identified all patients with high risk and locally advanced prostate cancer diagnosed between 1 April 2019 and 31 March 2020 in the English National Health Service (n = 15,971). Estimated travel times from the patient residential areas to the nearest hospital providing surgery or radiotherapy were estimated for journeys by car and by public transport. Multivariable logistic regression was used to model relationships between travel time and receipt of care with adjustment for patient characteristics. 10,693 (67%) men received radical surgery or radiotherapy (RT) within 12 months of diagnosis. Average travel time to the nearest hospital providing prostatectomy or RT was 23.2 min by private car and 58.2 min by public transport. We found no association between travel time, either by car or public transport and the likelihood of receiving curative treatment. Patients living in the most socially deprived areas, those aged over 70, those with two or more comorbidities, and those of black ethnic origin, were less likely to receive curative treatment (p& =& 0.001 for all associations). The current configuration of national prostate cancer services is not associated with the likelihood of receiving curative treatment. Further increases in capacity will unlikely improve utilisation rates beyond addressing sociodemographic barriers.

The Burden of Plastic Surgery in Rural Kenya: The Kapsowar Hospital Experience.

Both governmental and nongovernmental training programs are expanding efforts to train the next generation of plastic surgeons who will work in low- and middle-income countries (LMICs). Sufficient training is dependent on acquiring the appropriate skillset for these contexts. Few studies have characterized the spectrum of practice of plastic surgeons in LMICs and their relative disparity. We performed a retrospective review on all patients who received plastic surgery at a single institution in rural western Kenya from 2021 to 2023. Data such as diagnoses, procedures, and home village/town of residence were collected. Patient home location was geomapped using an open-access distance matrix application programming interface to estimate travel time based on terrain and road quality, assuming patient access to a private vehicle and ideal traveling conditions. Descriptive statistics were performed. A total of 296 patients received surgery. Common procedures included treatment of cleft lip/palate (CLP), burn reconstruction, and reconstruction for benign tumors of the head and neck. The average distance to treatment was 159.2 minutes. Increased travel time was not associated with time to CLP repair (P > 0.05). Increased travel time was associated with delayed treatment for burns (P = 0.005), maxillofacial trauma (P = 0.032), and hand trauma (P = 0.016). Training programs for plastic surgeons in LMICs should ensure competency in CLP, flaps, burn reconstruction, and head and neck reconstruction. Our novel use of an application programming interface indicates that international partnerships have been more successful in decreasing treatment delays for CLP patients, but not other reconstructive procedure patients. Expanded commitment from international partners to address these reconstructive burdens in LMICs is warranted.

Large scale multi-GPU based parallel traffic simulation for accelerated traffic assignment and propagation

Traffic simulation is a critical tool for congestion analysis, travel time estimation, and route optimization in urban planning, benefiting navigation apps, transportation network companies, and state agencies. Traditionally, traffic micro-simulation frameworks are based on road segments and can only support a limited number of main roads. Efficient traffic simulation on a regional scale remains a significant challenge due to the complexity of urban mobility and the large scale of spatiotemporal data. This paper introduces a Large Scale Multi-GPU Parallel Computing based Regional Scale Traffic Simulation Framework (LPSim), which leverages graphical processing unit (GPU) parallel computing to address these challenges. LPSim utilizes a multi-GPU architecture to simulate extensive and dynamic traffic networks with high fidelity and reduced computation time. Using the parallel processing capabilities of GPUs, LPSim can perform tens of millions of individual vehicle dynamics simulations simultaneously, significantly outperforming traditional CPU-based approaches. The framework is designed to be scalable and can easily accommodate the increasing complexity of traffic simulations. We present the theory behind GPU-based traffic simulation, the architecture of single- and multi-GPU based simulations, and the graph partition strategies that enhance computation resource load balance. Our experimental results demonstrate the effectiveness of LPSim in simulating large-scale traffic scenarios. LPSim is capable of completing simulations of 2.82 million trips in just 6.28 min on a single GPU machine equipped with 5120 CUDA cores (Tesla V100-SXM2). Furthermore, utilizing a Google Cloud instance with two NVIDIA V100 GPUs, which collectively offer 10240 CUDA cores, LPSim successfully simulates 9.01 million trips within 21.16 min. We further tested our simulator with the same demand on dual NVIDIA A100-PCIE-40GB GPUs, which finished the simulation in 0.0398 h, approximately 113 times faster than the same simulation scenario running on an Intel(R) Xeon(R) Gold 6326 CPU @ 2.90 GHz, which takes 4.49 h to complete. This performance not only demonstrates its speed and scalability advantages over traditional simulation techniques but also highlights LPSim’s unique position as the first traffic simulation framework that is scalable for both single- and multiple-GPU configurations. Consequently, LPSim provides an invaluable tool for individuals and extensive research teams alike, enabling the acquisition of large-scale traffic simulation results in a time-efficient manner. LPSim code is available at: https://github.com/Xuan-1998/LPSim

Investigation of Traffic System with Traffic Restriction Scheme in the Presence of Automated and Human-Driven Vehicles

In the context of transportation development, the simultaneous emergence of automated vehicles (AVs) and human-driven vehicles (HDVs) can lead to varied traffic system performance. For the purpose of improving traffic systems, this paper proposes a traffic restriction scheme only for HDVs. We develop a variational inequality (VI) model to describe travel mode and route choices under this restriction scheme and design an algorithm to solve the model. The proposed model and algorithm are applied to a Sioux Falls network example to evaluate the effects of the traffic restriction scheme. Our findings indicate that the scheme improves overall social welfare, with a higher proportion of restricted travelers leading to greater social welfare as well as increased travel demand due to changes in capacity. However, some lower exogenous monetary factors lead to negative social welfare, as the presence of AVs may exacerbate road congestion. Additionally, advancements in technology are needed to adjust the weightings of travel time and congestion level estimates to further enhance social welfare. These results offer valuable insights for traffic demand management in traffic systems with a mix of AVs and HDVs.

Estimation of vessel link-level travel time distribution: A directed network-driven approach

Accurate vessel travel time estimation is essential for operational efficiency and route optimization. Despite the prevalent use of the automatic identification system (AIS) in garnering multifaceted real-time data, ambiguities and inaccuracies in travel time predictions persist. It leads to planning uncertainties, inefficient resource allocations, and heightened operational costs in maritime logistics. To addresses these issues, this paper proposed a nuanced method to enhance the precision and reliability of vessel travel time estimations. Firstly, a directed maritime network is constructed by extracting essential information from AIS-based historical vessel trajectories. This lays the foundation for the subsequent analytical processes. Secondly, the non-parametric kernel density estimation (KDE) is applied to this constructed network, enabling the estimation of vessel travel time distributions across various network links. The non-parametric KDE is used in combination with AIS data, which improves the specificity and accuracy of the travel time estimations at the link level. Finally, this paper employs cellular automata (CA) simulations to validate the accuracy of the KDE-based estimations. Comparison between the simulation results and real-world data reveals a high degree of accuracy in the proposed method, confirming its applicability and effectiveness in estimating vessel travel times.

Differential Phase Analysis for Volcanic Tremor Detection and Source Location

AbstractWe present observations showing that during episodes of volcanic tremors, the phase of inter‐station cross‐correlations becomes stable. We propose a new quantity, the phase coherence, to identify the differential phase stability in recordings obtained from a single pair of stations, which is extrapolated to the seismic network. Then, we present a new approach based on the estimation of differential travel times through the differential phase measurements, to locate the sources of tremors occurring at the end of 2015 at the Klyuchevskoy Volcanic Group in Kamchatka, Russia. We present evidence supporting the existence of two types of activity happening simultaneously during the tremor episode: the main tremor source, originating from a region located between 7 and 9 km depth under the main volcanoes, and the widespread occurrence of weak low‐frequency earthquakes occurring at random locations. We show how the phase coherence and the differential phases can be used to provide information on the stability of the tremor source position and to estimate its location.

GT-TTE: Modeling Trajectories as Graphs for Travel Time Estimation

GT-TTE: Modeling Trajectories as Graphs for Travel Time Estimation

Spatio-temporal Dual Graph Neural Networks for Travel Time Estimation

Travel time estimation is one of the core tasks for the development of intelligent transportation systems. Most previous works model the road segments or intersections separately by learning their spatio-temporal characteristics to estimate travel time. However, due to the continuous alternations of the road segments and intersections in a path, the dynamic features are supposed to be coupled and interactive. Therefore, modeling one of them limits further improvement in accuracy of estimating travel time. To address the above problems, a novel graph-based deep learning framework for travel time estimation is proposed in this article, namely, Spatio-temporal Dual Graph Neural Networks (STDGNN). Specifically, we first establish the node-wise and edge-wise graphs to, respectively, characterize the adjacency relations of intersections and that of road segments. To extract the joint spatio-temporal correlations of the intersections and road segments, we adopt the spatio-temporal dual graph learning approach that incorporates multiple spatial-temporal dual graph learning modules with multi-scale network architectures for capturing multi-level spatial-temporal information from the dual graph. Finally, we employ the multi-task learning approach to estimate the travel time of a given whole route, each road segment and intersection simultaneously. We conduct extensive experiments to evaluate our proposed model on three real-world trajectory datasets, and the experimental results show that STDGNN significantly outperforms several state-of-art baselines.

A singular, broadly-applicable model for estimating on- and off-path walking travel rates using airborne lidar data

Accurate prediction of walking travel rates is central to wide-ranging applications, including modeling historical travel networks, simulating evacuation from hazards, evaluating military ground troop movements, and assessing risk to wildland firefighters. Most of the existing functions for estimating travel rates have focused on slope as the sole landscape impediment, while some have gone a step further in applying a limited set of multiplicative factors to account for broadly defined surface types (e.g., “on-path” vs. “off-path”). In this study, we introduce the Simulating Travel Rates In Diverse Environments (STRIDE) model, which accurately predicts travel rates using a suite of airborne lidar-derived metrics (slope, vegetation density, and surface roughness) that encompass a continuous spectrum of landscape structure. STRIDE enables the accurate prediction of both on- and off-path travel rates using a single function that can be applied across wide-ranging environmental settings. The model explained more than 80% of the variance in the mean travel rates from three separate field experiments, with an average predictive error less than 16%. We demonstrate the use of STRIDE to map least-cost paths, highlighting its propensity for selecting logically consistent routes and producing more accurate yet considerably greater total travel time estimates than a slope-only model.

Multi-Faceted Route Representation Learning for Travel Time Estimation

Multi-Faceted Route Representation Learning for Travel Time Estimation

GPU-accelerated parallel all-pair shortest path routing within stochastic road networks

All-pair shortest path routing within stochastic road networks is often more complicated and computationally challenging than routing in deterministic networks because uncertainties in travel time are introduced. We develop and test a GPU-enabled approach to resolve this computational challenge. This approach is based on a simulation framework that includes four steps: simulation of road networks impedances, computation of candidate paths using an all-pair shortest path algorithm, travel time estimation across candidate paths, and all-pair optimal path calculations. We developed GPU algorithms to accelerate the second and third steps, which are computationally demanding for large road networks. We used the road network of Wuhan, China as a case study. Our experiments indicate that the GPU approach leads to thousands of times in improvement of acceleration, which makes all-pair shortest path routing within stochastic road networks computationally feasible.

The Impedance of East Jakarta Road Network to Estimate Fire Station Service Areas

Urban fires, prevalent in densely populated areas, pose significant risks by increasing deaths and injuries. Fire departments must navigate challenging access routes to manage these incidents effectively. This study analyzes the service coverage of fire stations in East Jakarta, considering road network, width, speed, and travel time. The study utilizes secondary data from the DKI Jakarta Provincial Fire and Rescue Service, road network data from local government sources, and traffic data from Google Maps. Additionally, a field survey was conducted to validate road conditions and accessibility. Using graph theory-based network analysis, the study assesses connectivity, flows, directions, and destinations to determine the coverage extent. The optimal route, defined by road class, width, and condition, exhibits the lowest impedance. Google Maps’ estimated travel times, incorporating traffic conditions, are used to assess travel times, with a 5-minute travel time set as the standard barrier for coverage. Results reveal that the current service coverage of East Jakarta fire stations is only 66.57%. This disparity indicates an inadequate number of fire stations relative to their required service areas. The findings underscore the need for strategic placement of additional fire stations and potential improvements in road infrastructure to enhance response times. Traffic dynamics often affect travel times, demonstrating that shorter distances do not always result in faster arrivals according to real-time data.

Bayesian Modeling of Travel Times on the Example of Food Delivery: Part 1—Spatial Data Analysis and Processing

Online food delivery services are rapidly growing in popularity, making customer satisfaction critical for company success in a competitive market. Accurate delivery time predictions are key to ensuring high customer satisfaction. While various methods for travel time estimation exist, effective data analysis and processing are often overlooked. This paper addresses this gap by leveraging spatial data analysis and preprocessing techniques to enhance the data quality used in Bayesian models for predicting food delivery times. We utilized the OSRM API to generate routes that accurately reflect real-world conditions. Next, we visualized these routes using various techniques to identify and examine suspicious results. Our analysis of route distribution identified two groups of outliers, leading us to establish an appropriate boundary for maximum route distance to be used in future Bayesian modeling. A total 3% of the data were classified as outliers, and 15% of the samples contained invalid data. The spatial analysis revealed that these outliers were primarily deliveries to the outskirts or beyond the city limits. Spatial analysis shows that the Indian OFD market has similar trends to the Chinese and English markets and is concentrated in densely populated areas. By refining the data quality through these methods, we aim to improve the accuracy of delivery time predictions, ultimately enhancing customer satisfaction.

Accounting for taxi service conditions in estimating route travel time from floating car data using Markov chain model

Recognising the variations in driving behaviour between taxis in the empty and carry conditions is pivotal for enhancing the accuracy of route travel time estimations using floating car data. However, existing methods largely overlook this distinction. In light of this, this study aims to harness these variations for more precise estimations. Utilising taxi data, we segmented the information by service conditions and executed distinct estimations for each segment. The route travel time was deduced through convolutional operation, complemented by a Markov chain model to discern correlations between travel times across various links. Our innovative approach realised a substantial enhancement in accuracy. Notably, when accounting for distinct service conditions, there was a reduction of 51.44% in mean absolute error and a 46.83% decline in maximum percentage error. By providing more accurate and reliable travel time predictions, our methodology enables better-informed traffic management decisions. Accurate travel time estimations are essential for optimising traffic signal timings, planning efficient routing strategies, and managing road network usage. These improvements in traffic management can lead to smoother traffic flow, reduced travel times, and ultimately, diminished congestion in urban areas.

Wildland Firefighter Estimated Ground Evacuation Time Modeling to Support Risk-Informed Decision-Making

Wildland firefighters often work in remote settings with multiple hazards that can cause life-threatening injuries. Prompt access to medical care is key to reducing injury consequences. For the last decade, a spatial model of wildland firefighter estimated ground evacuation time (GET) has been used when developing operational response strategies in the contiguous United States (CONUS). This paper describes our updated and improved GET model and the resulting decision support spatial data representing the estimated time to evacuate to a hospital from anywhere within the CONUS using ground transportation only. The new GET model leverages updated input datasets and has improved off-road travel time estimation methods that incorporate the latest science on how terrain slope influences pedestrian travel rates. It also accounts for a novel set of landscape variables not previously considered, including minor roads and trails, streams, woody debris, cliffs, and an improved handling of shrub cover. When compared to a set of recent safety incidents, the reported evacuation times were correlated with the model predictions. The spatial patterns of GET from the new model are similar to the old product; however, we found that, on average, the new version of GET yields slightly faster evacuation times, but with regional variation in this trend.

Where should we go - Estimating travel times for modelling accessibility to 24-hour emergency departments in Canada

Estimating travel time to 24-hour emergency services is an important component to modelling accessibility of health services, particularly for rural areas. However, methods used to estimate travel time vary significantly, are not representative of the residential population, and are not openly validated. This makes the assessment of travel-based accessibility metrics between studies incomparable. To address this issue and develop a standardized measurement of emergency service access, this study utilized small geographic units (Dissemination Areas – DA) and geographical boundaries representative of municipal equivalents (Census Subdivision – CSD). Estimated travel times between the centroid of an inhabited DA to each 24-hr emergency department was computed with population-weighted travel times generated for each CSD. This dataset provides a nationally consistent measurement of proximity to emergency services accounting for travel pathing and population distribution. This methodology can be extended to generate estimated shortest travel routes for other healthcare resources or develop actual travel routes based on individuals’ experiences with the healthcare system.