IMPROVING THE ACCURACY OF TRAVEL TIME ESTIMATES USING ARCHIVED ITS DATA (original) (raw)
Related papers
Using Archived ITS Data to Generate Improved Freeway Travel Time Estimates
Accurate travel time estimation has become possible with the deployment of advanced traveler management and information systems. Dynamic message signs, websites, and handheld/in-vehicle devices are being increasingly used by public agencies to communicate important travel information to the public such as incidents, road closures and travel times. Travel time estimates are usually derived from roadway sensors, although other technologies such as cell phone matching, license plate matching, automatic vehicle identification and video detection have also been employed. In Oregon, freeway travel time estimates are generated by the Oregon Department of Transportation using data from inductive loop detectors throughout the Portland metropolitan area. These estimates are generated using a simple midpoint algorithm that extrapolates measured speeds over a freeway segment. The objective of this paper is to evaluate the accuracy of the current midpoint algorithm by comparing the derived estimates to ground truth (probe vehicle) travel times. In addition, travel time estimates from a travel time algorithm developed by Coifman were also evaluated for accuracy under varying traffic conditions. Various scenarios were tested using traffic data from both upstream and downstream detector stations. The results indicate that both the midpoint and the Coifman algorithms generate accurate travel time estimates under free flow conditions. The Coifman algorithm using data from the upstream detector provided the best estimate of travel time for a link during congestion as well as in periods after an incident occurred. TRB 2007 Annual Meeting CD-ROM Paper revised from original submittal. Kothuri, Tufte, Ahn and Bertini TRB 2007 Annual Meeting CD-ROM Paper revised from original submittal. Kothuri, Tufte, Ahn and Bertini
Development of an ITS data archive application for improving freeway travel time estimation
2006 IEEE Intelligent Transportation Systems Conference, 2006
The dissemination of travel time information has become crucial with the advent of ATIS. This paper summarizes the results of a comparative analysis between two travel time algorithms applied to archived loop detector data. Travel time estimates derived from the algorithms are compared to ground truth probe vehicle data. Our results indicate that Coifman's algorithm is more accurate for estimating travel times than a standard segment midpoint algorithm. However, the accuracy of the travel time estimates was dependent on the location and spacing of detectors and the location and formation of queues with respect to the detector positioning.
Toward Understanding and Reducing Errors in Real-Time Estimation of Travel Times
Transportation Research Record: Journal of the Transportation Research Board, 2008
In recent years the increased deployment of intelligent transportation systems infrastructure has enabled the provision of real-time traveler information to the public. Many states as well as private contractors are providing real-time travel time estimates to commuters to help improve the quality and efficiency of their trips. Accuracy of travel time estimates is important, as inaccurate estimates can be detrimental. Improving the accuracy of real-time estimates involves identifying and understanding the sources of error. This paper reports on the errors found during the evaluation of real-time travel time estimates in Portland, Oregon and provides solutions for reducing estimation error. The midpoint algorithm used by the Oregon Department of Transportation was used to estimate travel times from speeds obtained from loop detectors. The estimates were assessed for accuracy by comparisons with ground truth probe vehicle runs. The findings from the study indicate that 85% of the travel time runs had errors below 20% and, further, that accuracy varied widely between segments. The evaluation of high-error runs revealed the main causes of errors as transition traffic conditions, failure of detectors and detector spacing. Potential solutions were identified for each source of error. In addition, a method was tested for evaluating the benefits of additional detectors by simulation of virtual detectors. The results indicate that additional detection helps in reducing the mean average percent error in most cases but the location of detectors is critical to error reduction.
Method for the Annual Accuracy Assessment of Freeway Travel Time Systems
Public Works Management & Policy, 2018
Motivated by Title 23 Code of Federal Regulation 511, the U.S. Department of Transportation has recently established real-time systems management information programs to improve the consistency of traveler information provided to the public. Part of these requirements is to review the quality of the information provided to the public. Because limited information is available about current practices for meeting this new regulation, this article presents a method of evaluating real-time travel time information along metropolitan interstate freeways in the context of 23 CFR (Code of Federal Regulations) 511. This article presents a method and a case study of collecting travel time information from multiple sources (such as Google Maps and TravelMidwest.com ) and comparing them to measure accuracy. The findings suggested that the travel time information in the Chicago, Illinois, metropolitan area meets the accuracy requirements of 23 CFR 511, and this study has identified areas for futu...
With recent increases in the deployment of intelligent transportation system (ITS) technologies, traffic management centers have the ability to obtain and archive large amounts of data regarding the traffic system. These data can then be employed in estimations of current conditions and the prediction of future conditions on the roadway network. In this paper, we propose a general solution methodology for the identification of the optimal aggregation interval sizes of loop detector data for four scenarios (i) link travel-time estimation, (ii) corridor / route travel-time estimation, (iii) link traveltime forecasting, and (iv) corridor / route travel-time forecasting. This study applied cross validated mean square error (CVMSE) model for the link and route travel-time estimations, and a forecasting mean square error (FMSE) model for the link and corridor / route travel-time forecasting. These models were applied to loop detector data obtained from the Kyeongbu expressway in Korea. It was found that the optimal aggregation sizes for the travel-time estimation and forecasting were 3 to 5 min and 10 to 20 min, respectively.
Evaluation of travel time estimation based on LWR-v and CTM-v: A case study in Stockholm
2012
Real-time estimations of current and future traffic states are an essential part of traffic management and traffic information systems. Within the Mobile Millennium project considerable effort has been invested in the research and development of a real-time estimation system that can fuse several sources of data collected in California. During the past year this system has been adapted to also handle traffic data collected in Stockholm. This paper provides an overview of the model used for highways and presents results from an initial evaluation of the system. As part of the evaluation process, GPS data collected in an earlier field-test and estimations generated by the existing system used by the TMC in Stockholm, are compared with the estimations generated by the Mobile Millennium system. Given that the Mobile Millennium Stockholm system has not undergone any calibration, the results from the evaluation are considered promising. The estimated travel times correspond well to those measured in the field test. Furthermore, the estimations generated by the Mobile Millennium system can be regarded as superior to those of existing traffic management system in Stockholm. The highway model was found to perform well even with a reduction in the number of sensors providing data. The findings of this study indicate the robustness of the Mobile Millennium system and demonstrate how the system can be migrated to other geographical areas with similar sources of available data.
Arterial Travel Time Estimation for Advanced Traveler Information Systems
… of the 82th Annual Meeting of the …, 2003
While vehicular flows on freeways are often treated as uninterrupted flows, flows on arterials are conceivably much more complicated since vehicles traveling on arterials are not only subject to queuing delay but also to signal delay. Prediction of travel time is potentially more challenging for arterials than for freeways. This paper proposes a simple approach for arterial travel time prediction. The proposed approach decomposes total delay on an arterial into link delay and intersection delay. Intersection delay in the context of arterial travel time prediction is different from the average delay at an intersection. The proposed approach reduces the continuous delay experienced by drivers at each intersection into two distinctive states, a state of zero-delay and a state of nominal delay, coupled with a one-step transition matrix that relates the delay to a through vehicle at an intersection to its delay status at the adjacent upstream intersection. The parameters of the transition matrix are based on three key factors, the flow condition at the intersection, the proportion of net inflows into the arterial from the cross streets, and the signal coordination level. Numerical results show that the model can yield predictions with a reasonable degree of accuracy under various traffic conditions and signal coordination levels.
Survey of Best Practices in Real Time Travel Time Estimation and Prediction
2000
Over the last decade, there has been a push towards the development and deployment of Intelligent Transportation Systems (ITS) because of the many benefits that these systems can provide. One of the important components of ITS is Advanced Traveler Information Systems (ATIS). These systems aim to provide the users with pre-trip or en route travel information so that users can
Comparison of travel time measurement methods along freeway and arterial facilities
Transportation Letters, 2016
Travel time is an important performance measure used to assess traffic operational quality of various types of facilities. Previous efforts to estimate travel time have also compared model-estimated travel times to field-measured travel times using various sources of data. Given the variety and diversity of travel time measurement methods, it is important to evaluate the accuracy of the data obtained by each of them and to develop recommendations regarding their suitability in the validation of travel time estimation models. The research objective for this paper was to collect field data along several freeways and arterials and to evaluate the travel times obtained by STEWARD (Statewide Traffic Engineering Warehouse for Regionally Archived Data), INRIX, BlueTOAD (Bluetooth Traveltime Origination and Destination), and HERE. Benchmark data were collected with the use of an instrumented vehicle at five freeway segments and two arterial segments in Florida. The fieldmeasured travel times were statistically compared with the travel times provided through various methods. The results suggest that the HERE traffic data provide better freeway travel time estimates compared to the remaining methods. In oversaturated conditions, STEWARD, INRIX and BlueTOAD data seem to underestimate travel times, while HERE data were found to be more accurate. For undersaturated freeways, STEWARD, INRIX and BlueTOAD were found to perform better than HERE. At the arterial sites BlueTOAD and HERE travel time data were analyzed and the analysis suggests that none of the methods is accurate, possibly due to the small sample size.
Improved travel time estimation for reliable performance measure development for closed highways
Accurate travel time information not only is valuable for travelers but is critical to transportation agencies for quantifying the performance of their systems. Interest has been increasing in the development of reliable approaches for estimating travel time from various sensor data. Unlike the extensively studied estimation approaches based on point sensor measurements, the use of probe data from closed highway systems has been limited. To complement current understanding, this study developed an approach that used probe data from an electronic toll collection (ETC) system on closed freeways to estimate travel time. This approach differs from studies relying on automatic vehicle identification systems deployed on main lines as well as those estimated from point detectors. The proposed approach breaks down individual journey time into section travel time and fuses the probe data from vehicles that have used the links. The results, which are based on real-world case studies, illustrate the potential of mining ETC data for travel time estimation for both incident-free and incident conditions. In addition, the estimated results capture traffic dynamics better than instantaneous travel time estimates based on point sensor data. More accurate information is thus provided for deriving reliable performance measures to depict travel time reliability.