<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Research in Progress (RIP)</title>
    <link>https://rip.trb.org/</link>
    <atom:link href="https://rip.trb.org/Record/RSS?s=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" rel="self" type="application/rss+xml" />
    <description></description>
    <language>en-us</language>
    <copyright>Copyright © 2026. National Academy of Sciences. All rights reserved.</copyright>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <managingEditor>tris-trb@nas.edu (Bill McLeod)</managingEditor>
    <webMaster>tris-trb@nas.edu (Bill McLeod)</webMaster>
    <image>
      <title>Research in Progress (RIP)</title>
      <url>https://rip.trb.org/Images/PageHeader-wTitle-RIP.jpg</url>
      <link>https://rip.trb.org/</link>
    </image>
    <item>
      <title>Machine Vision Toolkit for Automated Fleet Composition Assessment and Reporting</title>
      <link>https://rip.trb.org/View/2691665</link>
      <description><![CDATA[State Departments of Transportation (DOTs) and Metropolitan Planning Organizations (MPOs) employ fleet composition data (e.g., passenger vehicles, single-unit trucks, and combination trucks) in a variety of planning, economic, roadway performance, and safety applications. Accurate fleet composition data is essential for pavement management, safety analysis, and fuel consumption modeling. However, traditional methods are labor-intensive, costly, and often lack the temporal or spatial resolution required to capture variations between freeways, arterials, and managed lanes vs. general-purpose lanes. Using machine vision tools to quickly, efficiently, and accurately capture on-road percentages of light-duty vehicle, light-duty truck, medium-duty truck, and a variety of heavy-duty truck classifications will enhance analytical and modeling accuracy and reduce state DOT data management costs. Building upon prior National Center for Sustainable Transportation (NCST) research that developed machine vision algorithms for vehicle identification, this project will package those research findings into a deployable, open-source Automated Fleet Classification Toolkit for practitioners and researchers. The research team will develop and release comprehensive Standard Operating Procedures (SOPs) and software tools allowing agencies to convert standard roadside or overpass video feeds into high-resolution fleet composition data. The toolkit will utilize advanced object detection (e.g., YOLO architectures) to automate the identification of vehicle classes (aligning with FHWA 13-category schemes where possible) and propulsion types based on visual vehicle features. The system is designed to distinguish traffic conditions on complex roadway geometries, allowing users to generate separate classification profiles for managed lanes vs. general-purpose lanes, and separating freeway mainlines from adjacent arterial service roads. The project focuses on technology transfer: providing the "how-to" manuals, open-source code, and data processing protocols so that State DOTs, consultants, university partners and research institutes can replicate the data collection and extraction without relying on proprietary "black box" services.]]></description>
      <pubDate>Sun, 12 Apr 2026 23:29:28 GMT</pubDate>
      <guid>https://rip.trb.org/View/2691665</guid>
    </item>
    <item>
      <title>Are Automonous Vehicles Safer Drivers than Humans? Comparing performance in San Francisco</title>
      <link>https://rip.trb.org/View/2625584</link>
      <description><![CDATA[This research project seeks to determine if automated vehicles (AVs) are safer drivers than humans by comparing their pedestrian interaction behaviors and yielding performance in real-world conditions in San Francisco. The study will be framed by the city's "Focus on Five" strategy, which targets the five moving violations most commonly associated with traffic fatalities. Researchers will conduct evaluations of two focus violations, with the first being a comparison of the compliance of AVs and human drivers in yielding to pedestrians in a crosswalk. To gather data, the team will install high-resolution video cameras at two or more crosswalks with no traffic control for a period of one to three weeks to passively record vehicle-pedestrian interactions. Machine learning-based computer vision methods will then be used to automatically classify vehicles as either automated or human-driven. Following this classification, researchers will review the footage to code each interaction, noting if the vehicle yielded to the pedestrian. Finally, the performance of the two groups will be compared using two-sample t-tests to determine if any observed differences are statistically significant. A parallel analysis will be conducted for a second violation, to be determined.]]></description>
      <pubDate>Tue, 18 Nov 2025 15:14:24 GMT</pubDate>
      <guid>https://rip.trb.org/View/2625584</guid>
    </item>
    <item>
      <title>Real Time Classification of Vehicle Types and Modes using Image Analysis and Data Fusion</title>
      <link>https://rip.trb.org/View/2353426</link>
      <description><![CDATA[Description: The goal of this project is to conduct a feasibility study on the development of software and selection of hardware that will measure multiple transportation modes and classify vehicles by their Federal Highway Administration (FHWA) classification. The research team will install several combined computer/camera systems to monitor the multi-modal traffic in the proximity of the University of South Carolina campus. This area has multiple transportation users, including pedestrians, mopeds, bicycles, motorcycles, passenger cars, trucks, trains and buses. Along with the video data, additional traffic collection sources such as pneumatic tubes and Bluetooth will be used. Multiple cameras will allow three dimensional data of the environment to be constructed in the software. The video data will be combined with other data using statistical updating methods (Bayesian) to produce final multi-modal traffic information. We will also explore counting traffic in non-typical locations, such as counting the number of pedestrians in/outside of cross walks in the roadway or pedestrians crossing stopped trains.

Intellectual Merit: (1) Image subtractions from successive images will be used to identify objects in the area of interest. (2) A discriminate function based on the object geometry and image texture will be used to classify objects. (3) The development of the object discriminant function as well as utilization of digital image correlation or other video object motion determination approaches will be the major contribution of this research.

Broader Impacts: Broader Impacts: The collection and analysis of integrated multimodal movement of people and goods will provide transportation planners with better quantitative information about the existing system. Beyond providing raw counts, an integrated video based system could provide information about unsafe practices of pedestrians and moped users that could be used to improve safety for these users.]]></description>
      <pubDate>Mon, 25 Mar 2024 15:48:19 GMT</pubDate>
      <guid>https://rip.trb.org/View/2353426</guid>
    </item>
    <item>
      <title>Implementing Inductive Loop Signature Technology for Vehicle Classification Counts</title>
      <link>https://rip.trb.org/View/2134838</link>
      <description><![CDATA[This study evaluates recent technology that uses inductive loop detectors, traditionally used for collecting traffic volume and speed data, to provide vehicle classification data by examining the high-resolution signature produced when a vehicle passes over the sensor. The project aimed to verify the accuracy of the new classification system, collect additional heavy vehicle data to help improve system accuracy, and familiarize MnDOT staff with the technology through training and the development of a field deployment manual. Through collaboration with MnDOT and the technology vendor CLR Analytics, Inc., the VSign vehicle classification system was installed at five sites in Minnesota with preexisting loop detection systems. The final sites were chosen to be representative of MnDOT facilities, feature a mix of heavy vehicle traffic, and provide accessibility for deployment staff.

Data from the VSign system was compared with manually verified ground-truth data collected from video under both the FHWA and HPMS classification schemes. The system demonstrated high accuracy for passenger vehicles but varying accuracy for different classes of heavy vehicles, though performance improved under the HPMS classification scheme. The VSign system was also evaluated against the video-based iTHEIA™ system at one site, which VSign outperformed in both classification accuracy and detection rate. The results suggest that the VSign system is more effective at locations where vehicles maintain consistent speeds and are centered in the lane due to the negative effects of variations in speed and lateral position on the consistency of vehicle signatures read by the detector.]]></description>
      <pubDate>Tue, 07 Mar 2023 14:11:11 GMT</pubDate>
      <guid>https://rip.trb.org/View/2134838</guid>
    </item>
    <item>
      <title>Vehicle Classification Technologies for Toll Collection</title>
      <link>https://rip.trb.org/View/1948960</link>
      <description><![CDATA[Toll facilities (roads, bridges and tunnels) are used primarily for revenue generation to repay for
long-term debt issued to finance construction, capacity expansion, operations and maintenance
of these facilities. Tolls are one form of a broad concept known as road pricing. In addition to
revenue generation, road pricing is used for other reasons including transportation demand
management to reduce peak hour travel and the recurring traffic congestion on some corridors.
Tolling technologies have evolved rapidly in the past two decades and today offer many solutions
for toll collection. Traditional (mostly cash) tolling has been gradually replaced by electronic toll
collection (ETC) that enables users to go through toll lanes without stopping. In addition to
improving traffic safety and enhancing the efficient use of the existing infrastructure, ETC results
in reduction in toll collection costs.
The three most important components of ETC are user account identification, vehicle
classification (where vehicles are charged differently according to class), and determination of the
distance traveled. Most of the tolling agencies in Region-6 (and most of the U.S.) determine the
user fee based on the number of axles. The latter is often identified using induction loop sensors
buried in the pavement and energized by low-voltage electrical currents that produce
electromagnetic fields above the roadway. Vehicles traveling through these fields produce digital
signatures that are used to identify the number of axles. The loop sensors used by many tolling
authorities in the U.S. are manufactured by TransCore, Inc. and are known as “Intelligent Vehicle
Identification System (IVIS).
The IVIS sensors have high accuracy rate in classifying vehicles. However, loop detectors
present several problems including the intrusive nature of their installation and maintenance
(disruptive lane closures), high failure rate, sensitivity to rebar in concrete pavements, and their
undermining of the structural health of the surrounding pavement. Loop failure can result
because of several reasons including cracks across saw cuts, broken loop or lead-in wires, and
sealant failure.
The aim of this study is to provide tolling authorities in Region-6 with detailed analysis of the
fitness of various non-pavement-intrusive vehicle classification technologies (imaging, radar,
Lidar, thermal profiling, etc.) under different roadway, traffic, and environmental conditions to
inform decision-makers of the accuracy, performance, and lifecycle-cost of these technologies.
Toll facilities have multiple lane configurations including highways with multiple lanes at highway
speeds and ramps at reduced speed. The classification technology must be accurate at high
speed, low speed, single lane facilities, multiple lane facilities, and all kinds of weather. The
study involves in-depth review of available non-pavement-intrusive vehicle classification
technologies; gathering and analyzing data on the performance and cost of available
technologies from manufacturers and toll facility operators; and making presentations to the
tolling industry in Region-6.]]></description>
      <pubDate>Mon, 09 May 2022 06:49:06 GMT</pubDate>
      <guid>https://rip.trb.org/View/1948960</guid>
    </item>
    <item>
      <title>Automatic Extraction of Vehicle, Motorcycle, Bicycle, and Pedestrian Traffic from Video Data</title>
      <link>https://rip.trb.org/View/1691991</link>
      <description><![CDATA[The objective of this research is to develop image processing algorithms to automatically extract vehicle counts and classifications, as well as counts of motorcycles, bicycles, and pedestrians from real-time and offline videos. An easy-to-use graphical user interface will enable SCDOT staff to obtain multimodal traffic data accurately, safely, and cost-effectively to use for HPMS reporting and prioritize infrastructure design improvements and investments.]]></description>
      <pubDate>Mon, 09 Mar 2020 07:35:30 GMT</pubDate>
      <guid>https://rip.trb.org/View/1691991</guid>
    </item>
    <item>
      <title>Exploring Non-Traditional Methods to Obtain Vehicle Volume and Class Data</title>
      <link>https://rip.trb.org/View/1632286</link>
      <description><![CDATA[The objective of this pooled fund project is to develop and deploy methods and approaches to obtain vehicle volume and classification data with passively collected data.   Volume data refers to the annual average daily traffic (AADT) for all vehicles (both passenger and trucks) covering all roadway functional classes by traffic link or finer levels of segmentation with emphasis on functional classes of minor arterials, collectors, and local roads.  Volume data on high volume urban interstates is also highly desired as there is a greater risk for collecting this data in these environments because maintenance of traffic is more expensive and these activities can disrupt normal traffic patterns.]]></description>
      <pubDate>Mon, 01 Jul 2019 18:52:36 GMT</pubDate>
      <guid>https://rip.trb.org/View/1632286</guid>
    </item>
    <item>
      <title>An Update of the Green Book Design Vehicles Requirements</title>
      <link>https://rip.trb.org/View/1516155</link>
      <description><![CDATA[Design vehicle classification, dimensions, and turning path templates have been an important part of AASHTO’s A Policy on Geometric Design of Highways and Streets, 7th Edition (Green Book) for over 40 years. Due to limited or nonexistent supporting data and research documentation, these design vehicle dimensions and minimum turning radii are difficult to support and verify. Also, with the increased value of right-of-ways and increased usage of modern roundabout designs and alternative intersection treatments (e.g., thru-turn, continuous flow, and displaced-left turn intersections), accurate vehicle steering angles and swept paths are of the utmost importance.

The Green Book turning path templates do not provide sufficient data for vehicle turn simulation software and computer-aided design (CAD) software to faithfully reproduce them. Critical dimensions for determining a vehicle’s swept path are its front overhang, rear overhang, wheelbase, steering angle, vehicle width, and, in the case of multi-part vehicles, the inter-vehicle angles and kingpin and hitch locations. Rear overhang and mirror widths have also generated safety concerns in the design of bus passenger platforms. Further, with industry movement toward 3D design, loaded ground clearances and heights of the key design vehicles are desirable.


The objective of this research was to develop design vehicle material for the 8th Edition of the Green Book that realistically represents the critical vehicles that influence geometric designs. The research provided conclusions for: (1) Critical dimensions and specifications (or ranges thereof) for design vehicles that can be applied to the design of intersection right and left-turn lanes, roundabout elements, and other roadway elements; (2) Guidance on using this dimensional information in design, including a selection of design vehicle(s) for a project, determination of when to allow large vehicles to encroach upon other lanes, and discussion on balancing the needs of different modes (e.g., trucks and pedestrians); and
(3) An appropriate number of turning path templates that reflect a reasonable range of variability among design vehicles and guidance on when and how they should be applied.
The final report documents the research objectives, methodology, findings, conclusions, and recommendations. Other final deliverables will include a Microsoft Excel® spreadsheet with the dimensional data for design vehicles. 

]]></description>
      <pubDate>Mon, 18 Jun 2018 19:33:12 GMT</pubDate>
      <guid>https://rip.trb.org/View/1516155</guid>
    </item>
    <item>
      <title>Quantifying the Effects of Implements of Husbandry on Pavements</title>
      <link>https://rip.trb.org/View/1439867</link>
      <description><![CDATA[The size, geometry, weight, and other features of farm equipment, known as implements of husbandry (IoH), have increased and changed significantly to meet the needs of the modern agricultural industry. While intended primarily for use on the farm or in the field, frequently IoH travel on roads and bridges. Highway pavements are generally designed for traffic loadings and configurations defined by 13 vehicle classes using FHWA classifications. However, the configurations, weight and size, and other features of IoH differ substantially from the FHWA 13 vehicle classes and, therefore, may result in different forms of pavement distress and damage than those caused by truck traffic. Although a great deal of research has been performed on the effects of truck traffic on pavement performance, limited research has dealt with the procedures of quantifying the influence of IoH on pavement performance and there are no nationally accepted procedures to estimate these effects. There is a need to identify the procedures currently available for quantifying the effects of IoH on pavement performance and develop procedures that can be used for the different IoH configurations, pavement types, and applications. Also, there is a need to develop a tool to facilitate the implementation of these procedures. These procedures and accompanying tool should help highway agencies in making decisions regarding the movement of IoH on highway pavements. 
 
OBJECTIVES: The objectives of this research are to (1) propose procedures for quantifying the effects of implements of husbandry (IoH) on pavement performance and (2) develop a tool to facilitate implementation of these procedures. 
 

 

]]></description>
      <pubDate>Sun, 11 Dec 2016 08:38:53 GMT</pubDate>
      <guid>https://rip.trb.org/View/1439867</guid>
    </item>
    <item>
      <title>Alabama Traffic Data Collection Analysis</title>
      <link>https://rip.trb.org/View/1298736</link>
      <description><![CDATA[The objective of this project is to administer a component of the Highway Performance Monitoring System (HPMS) on behalf of the Alabama Department of Transportation (ALDOT).  Timely and accurate implementation of the HPMS is essential to the functioning of ALDOT.  Traffic data (volumes and vehicle classification counts) collected under the HPMS are used to determine the level of federal highway funding ALDOT receives each year.  ALDOT is required to provide annual reports of traffic volumes and sampled vehicle classification counts on its roadway system.  The reports are typically generated on a county-by-county basis.  The University of Alabama (UA) will engage traffic data specialists, Southern Traffic Services (STS), to implement the 2012-2013 HPMS counts in Houston County, Alabama.]]></description>
      <pubDate>Fri, 14 Feb 2014 01:01:01 GMT</pubDate>
      <guid>https://rip.trb.org/View/1298736</guid>
    </item>
    <item>
      <title>Approach to Real-Time Commercial Vehicle Monitoring</title>
      <link>https://rip.trb.org/View/1228343</link>
      <description><![CDATA[Vehicle classification algorithms allocate vehicles to predefined classes based on selected vehicle characteristics. Such algorithms have many important applications in transportation systems analysis and policy development, including travel forecasting, goods movement studies, road design and maintenance, setting user fees, safety studies, traffic flow modeling, environmental impact analysis, traffic management and automated toll collection. This research will collect a large and unique dataset of commercial vehicle (CV) signatures using conventional inductive loops and a new wireless sensor with potential for cost-effective and widespread use. The data will be used to develop detailed and accurate vehicle classification algorithms for CVs, and will provide important insights into the strengths and limitations of a new wireless traffic sensor.]]></description>
      <pubDate>Thu, 03 Jan 2013 13:19:14 GMT</pubDate>
      <guid>https://rip.trb.org/View/1228343</guid>
    </item>
    <item>
      <title>Estimating Vehicle-Miles-Traveled by Vehicle Class for the State of Delaware</title>
      <link>https://rip.trb.org/View/1228191</link>
      <description><![CDATA[The initial stage of the project will involve a thorough literature search and review of documentation related to the existing body of knowledge and practices. A statistically accurate method for functional conversion of the raw vehicle registration and travel data will be developed to identify the contribution of each vehicle type to VMT. This project will convert Division of Motor Vehicle (DMV) reported registration data from percent registration by vehicle type to actual mileage accumulation rates as they contribute to VMT through- out the state. Project output will be a statistically reliable automated process for converting available DMV registration information to an accurate on-road mileage based contribution by vehicle type, acceptable to both USEPA and FHWA as part of the transportation conformity air quality analysis process.]]></description>
      <pubDate>Thu, 03 Jan 2013 13:16:19 GMT</pubDate>
      <guid>https://rip.trb.org/View/1228191</guid>
    </item>
  </channel>
</rss>