<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Transport Research International Documentation (TRID)</title>
    <link>https://trid.trb.org/</link>
    <atom:link href="https://trid.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>Transport Research International Documentation (TRID)</title>
      <url>https://trid.trb.org/Images/PageHeader-wTitle.jpg</url>
      <link>https://trid.trb.org/</link>
    </image>
    <item>
      <title>Driver visual attention and in-vehicle touchscreen: the role of short training session</title>
      <link>https://trid.trb.org/View/2706362</link>
      <description><![CDATA[The growing integration of in-vehicle centre stack touchscreens has enhanced driver access to information and control systems but raised significant safety concerns due to increased visual distraction. This study investigates whether a short pre-drive training session can mitigate distraction and improve driver interaction with in-vehicle touchscreen. Using a driving simulator and eye-tracking technology, 60 licensed Norwegian drivers were assigned to trained and untrained groups to compare visual attention patterns during secondary tasks involving touchscreen use. Results showed that while all participants exhibited high visual demand on the touchscreen, trained drivers demonstrated slightly lower fixation counts, shorter durations, and reduced self-transition probabilities within the touchscreen area, suggesting more efficient and potentially safer interactions. However, these differences were not statistically significant, indicating a limited effect of the short training provided. The findings highlight the complexity of the touchscreen interface and potential of pre-drive touchscreen familiarization in improving visual attention.]]></description>
      <pubDate>Wed, 10 Jun 2026 09:05:21 GMT</pubDate>
      <guid>https://trid.trb.org/View/2706362</guid>
    </item>
    <item>
      <title>Explaining acceptance and acceptability of connected automated vehicles: the impact of evaluations of attributes and traffic complexity</title>
      <link>https://trid.trb.org/View/2611025</link>
      <description><![CDATA[Connected Automated Vehicles (CAVs) may, when available, be able to reduce greenhouse gasses emissions caused by the transport sector, and may increase traffic safety. In order for CAVs to be adopted by the public, they first need to be accepted (i.e., evaluated positively). Therefore, it is critical to identify the predictors of CAVs’ acceptability (general evaluation before experience) and acceptance (willingness to use after experience). We examined to what extent evaluations of different attributes of CAVs are related to acceptability and acceptance, and to what extent acceptability and acceptance are related. Specifically, we hypothesised that more positive evaluations of safety, trustworthiness, instrumental, and hedonic attributes would be related to higher acceptability before experiencing a CAV, and to acceptance after experiencing a CAV. To be able to assess acceptance, we conducted a driving simulator experiment (N = 46). This enabled participants to experience a CAV in both a low and high traffic complexity scenario, and we could examine to what extent experiencing a CAV influences the evaluation of CAVs. Our results show that experiencing a CAV can enhance perceived safety and trustworthiness of CAVs. Further, both acceptability and acceptance were higher when the CAV was evaluated more positively on the attributes before and after experiencing a CAV, respectively. Safety attributes were more strongly related to acceptability than acceptance, while hedonic and instrumental attributes were more strongly related to acceptance than acceptability. In contrast to our expectations, traffic complexity did not affect acceptance, perceived safety, or trustworthiness of CAVs after the simulated drive. These results suggest that policies aimed at enhancing safety, driving pleasure, trustworthiness of CAVs, and by ensuring that CAVs are able to meet people’s mobility needs could increase both acceptability and acceptance of CAVs.]]></description>
      <pubDate>Thu, 16 Oct 2025 11:56:47 GMT</pubDate>
      <guid>https://trid.trb.org/View/2611025</guid>
    </item>
    <item>
      <title>Enabling virtual validation &amp; verification for ADAS and AD features, EVIDENT : final report</title>
      <link>https://trid.trb.org/View/2598585</link>
      <description><![CDATA[The EVIDENT project aims to address challenges in the automotive industry's validation and verification (V&V) processes for advanced driver assistance systems (ADAS) and autonomous driving (AD) features. Traditional V&V methods struggle to keep up with the increasing frequency of software updates. The project explores virtual validation strategies to complement or replace physical testing, thereby enhancing efficiency and safety assurance. Automotive innovations are increasingly software-driven, necessitating frequent updates. Current validation processes heavily rely on physical testing, which is time-consuming and costly. The project focuses on how vehicle functionalities could be tested and validated in simulation models and what fidelity level that could be reached. By utilizing virtual environments, the project aims to proactively test software functions before deployment, ensuring accurate assessments of system performance in diverse scenarios. The primary goal is to develop strategies that balance the realism of virtual test environments with practical implementation. Key research questions include: - What level of realism is required for simulations to be credible for testing edge cases? - How can virtual testing be integrated with real-world data to discover new edge cases? - How can virtual testing ensure functional safety to satisfy regulatory bodies? Five key case studies were tested: 1. Automated Lane Keeping System (ALKS). 2. Car-to-Car Front Turn-Across-Path (CCFTap). 3. Car in Curve. 4. S-Curve. 5. Occluded Child.]]></description>
      <pubDate>Fri, 12 Sep 2025 10:18:38 GMT</pubDate>
      <guid>https://trid.trb.org/View/2598585</guid>
    </item>
    <item>
      <title>Guidelines for using high-level driving simulators in user studies : an interview study regarding user performance, experience, and ride comfort</title>
      <link>https://trid.trb.org/View/2534330</link>
      <description><![CDATA[Driving simulators have been extensively applied across various study areas, including user performance, user experience and ride comfort. While existing literature provides insights into the applications of driving simulators across diverse research realms, primarily focusing on the physical capabilities of driving simulators, however, comprehensive assessments of the overall benefits and challenges associated with employing driving simulators in studies regarding user studies have been infrequent. Moreover, previous research has often overlooked the distinctions in methodological approaches between studies utilising driving simulators and those employing real vehicles. Consequently, the purpose here was to undertake an interview study to propose guidelines for using high-level driving simulators in studies regarding user performance, experience, and ride comfort. A total of 14 participants were included, comprising six driving simulator technicians and eight researchers with experience in driving simulator studies. The guidelines outline several advantages that simulators provide, such as improved safety, repeatability, fewer practical constraints, controllability and efficiency. Nevertheless, challenges like space limitations, restricted motion realism, hardware dependence, communication difficulties between researchers and technicians, and time-consuming new scenario development could potentially undermine the feasibility of simulations. Moreover, the guidelines suggest simulation study designs with caution against scenarios involving acceleration, deceleration, extensive lateral manoeuvres, and low-light conditions. Crucial aspects include ethical considerations, task duration, data collection, resource allocation, simulation fidelity and environmental factors. Specific guidelines for user performance, experience and ride comfort underscore the importance of prioritising factors and using relative comparison methods for valid and reliable results.]]></description>
      <pubDate>Fri, 04 Apr 2025 15:16:49 GMT</pubDate>
      <guid>https://trid.trb.org/View/2534330</guid>
    </item>
    <item>
      <title>Pedestrian behavior prediction using machine learning methods</title>
      <link>https://trid.trb.org/View/2534302</link>
      <description><![CDATA[Accurate pedestrian behavior prediction is essential for reducing fatalities from pedestrian-vehicle collisions. Machine learning can support automated vehicles to better understand pedestrian behavior in complex scenarios. This thesis aims to predict pedestrian behavior using machine learning, focusing on trajectory prediction, crossing intention prediction, and model transferability. We identified research gaps by reviewing the literature on pedestrian behavior prediction. To address these gaps, we proposed deep learning models for pedestrian trajectory prediction using real-world data, considering social and pedestrian-vehicle interactions. We integrated spectral features to improve model transferability. Additionally, we developed machine learning models to predict pedestrian crossing intentions using simulator data, analyzing interactions in both single and multi-vehicle scenarios. We also investigated cross-country behavioral differences and model transferability through a comparative study between Japan and Germany. For trajectory prediction, incorporating social and pedestrian-vehicle interactions into deep learning models improved accuracy and inference speed. Integrating spectral features using discrete Fourier transform improved motion pattern capture and model transferability. For crossing intention prediction, neural networks outperformed other machine learning methods. Key factors that influence pedestrian crossing behavior included the presence of zebra crossings, time to arrival, pedestrian waiting time, walking speed, and missed gaps. The cross-country study revealed both similarities and differences in pedestrian behavior between Japan and Germany, providing insights into model transferability.]]></description>
      <pubDate>Fri, 04 Apr 2025 15:16:26 GMT</pubDate>
      <guid>https://trid.trb.org/View/2534302</guid>
    </item>
    <item>
      <title>Emergency vehicle approaching : final report : activity 5</title>
      <link>https://trid.trb.org/View/2534240</link>
      <description><![CDATA[The purpose of the EVA pilot is to provide drivers with quick and accurate information and warnings about some of the possible hazardous events on the roads. This, in turn, can help prevent incidents and accidents, as well as reduce congestion. The EVA service is planned to cover Swedish highways and national roads and the pilot is aiming for deployment after the NordicWay 3 project. Furthermore, driving simulators will be used to gain a greater understanding of driver behavior when receiving EVA or Accident Zone Warnings. The pilot focuses on scenarios where the positive effects on traffic safety and emergency response times of reaching out with those warning messages are likely to be high. The established data flow infrastructure and software components from NordicWay 2 will be used.]]></description>
      <pubDate>Fri, 04 Apr 2025 15:15:35 GMT</pubDate>
      <guid>https://trid.trb.org/View/2534240</guid>
    </item>
    <item>
      <title>Critical scenario identification for testing of realistic autonomous driving systems</title>
      <link>https://trid.trb.org/View/2534228</link>
      <description><![CDATA[Testing is imperative to validate the functionalities and safety of autonomous driving systems. Simulated scenario-based testing is commonly adopted for autonomous driving systems, which aims to construct various driving scenarios and validate the autonomous driving systems in simulation. Nevertheless, identifying relevant test scenarios, especially critical ones that expose hazards or risks of harm to autonomous vehicles remains an open challenge. We focus on critical scenario identification for testing of realistic autonomous driving systems in this thesis. Specifically, our objective is to establish an effective approach for identifying critical scenarios for testing of industrial autonomous driving systems. Also, we aim to explore and improve current practices of testing autonomous driving systems with critical scenarios in industry. We follow the design science research paradigm and perform two iterations of the design research cycle in this thesis. The first iteration focuses on the first objective of the thesis to design an approach for critical scenario identification. In the second iteration, we explore industry practices of using critical scenarios for testing of autonomous driving systems, and propose a preliminary solution to evaluate the realism of such scenarios and improve their validity.]]></description>
      <pubDate>Fri, 04 Apr 2025 15:15:24 GMT</pubDate>
      <guid>https://trid.trb.org/View/2534228</guid>
    </item>
    <item>
      <title>Mastering skills in an unpredictable world : simulator training for train drivers</title>
      <link>https://trid.trb.org/View/2534224</link>
      <description><![CDATA[Train drivers play a crucial role in the railway system, with their performance significantly impacting accident rates and punctuality. This is particularly true during abnormal situations, such as signal failures or the presence of people on or near the tracks. In these circumstances, good driver performance enhances overall railway performance, leading to better punctuality, fewer accidents, and a reduction in collisions between trains and other vehicles, animals, or people. One of the most critical skills for a train driver to minimize errors is situational awareness, a person's ability to comprehend what is happening in a given situation, which is essential for responding effectively. This skill becomes especially important in abnormal situations. A situationally unaware driver results from either a lack of expertise or failure of expertise. Lack of expertise means that the driver does not possess the necessary knowledge to build an accurate situational model, increasing the risk of misinterpreting a situation. Naturally, novice drivers, lacking experience in many situations, are more prone to making mistakes due to this knowledge gap. Basic train driver education in Sweden includes around 20 weeks of on-the-job training. However, it is debatable whether this provides enough exposure to various situations for drivers to gain adequate experience. In response to this criticism, a low-fidelity train driving simulator has been introduced in the last decade to complement traditional training. This thesis explores how the simulator can enhance the internship experience and help produce more well-prepared train drivers. This thesis also examines how in-cab information systems influence driver attention and the possibility of developing accurate situational awareness.]]></description>
      <pubDate>Fri, 04 Apr 2025 15:15:20 GMT</pubDate>
      <guid>https://trid.trb.org/View/2534224</guid>
    </item>
    <item>
      <title>Emergency vehicle approaching : warning drivers using cooperative intelligent transport systems</title>
      <link>https://trid.trb.org/View/2534221</link>
      <description><![CDATA[Driving an emergency vehicle can be difficult. The driver of the emergency vehicle must navigate, communicate with emergency services, often drive at high speeds, and take surrounding traffic into account. Civilian drivers are required by law to give way to emergency vehicles with lights and sirens activated. Despite this, they sometimes fail to move over. One reason is not noticing the emergency vehicle in time. This dissertation aims to understand how technology can support civilian drivers in their interactions with emergency vehicles. One form of technology used to make drivers move over is emergency vehicle lighting. The results of this dissertation show that alternative designs of emergency vehicle lighting can affect driver behavior and that the current designs are not always suited to promote the most desirable driver behavior. Another technological approach to supporting drivers in their interactions with emergency vehicles is the use of Cooperative Intelligent Transport Systems (C-ITS). One C-ITS service is the Emergency Vehicle Approaching (EVA) warning. An EVA warning is an early in-car warning sent out to the driver before being overtaken by an emergency vehicle, providing more time to move over. Three driving simulator studies with EVA warnings were conducted in this dissertation.]]></description>
      <pubDate>Fri, 04 Apr 2025 15:15:17 GMT</pubDate>
      <guid>https://trid.trb.org/View/2534221</guid>
    </item>
    <item>
      <title>Examining the effects of texting, web surfing, and navigating apps on urban driving behavior and crash risk</title>
      <link>https://trid.trb.org/View/2533899</link>
      <description><![CDATA[This research aims to assess the impact of using texting, web surfing and navigating applications on driving behavior and road safety in urban environments. The study involved collecting driving data from 36 young adult drivers through a driving simulator experiment, supplemented by a survey to gather participant characteristics and driving profiles. The driving experiment included periods of distraction-free driving and intervals when drivers used Facebook (scrolling through the feed), Google Maps (searching for specific locations), and Facebook Messenger (texting). Data analysis utilized linear and binary logistic mixed models to explore the effects of texting and web surfing on speed and its deviation, headway distance and its deviation, and crash risk. Results indicate that using texting, web surfing and navigating applications while driving elevate crash risk by 10% and decrease speed, speed deviation, headway, and headway deviation by 9%, 23%, 6%, and 18%, respectively. These findings underscore the crucial role of specific smartphone applications in shaping driving behavior and emphasize the need for targeted interventions to mitigate the associated risks in urban driving scenarios.]]></description>
      <pubDate>Wed, 02 Apr 2025 09:34:21 GMT</pubDate>
      <guid>https://trid.trb.org/View/2533899</guid>
    </item>
    <item>
      <title>Evaluation of the human interaction with automated vehicles on highways</title>
      <link>https://trid.trb.org/View/2509302</link>
      <description><![CDATA[Human-driven vehicles (HVs) will be interacting with automated vehicles (AVs) at AV market penetrations between 0% and 100%. However, little is known about how HVs interact with AVs. This study addresses knowledge gaps related to how HVs will interact with AVs on highways. The research was conducted in Oregon State University's Passenger Car Driving Simulator. Additionally, a Shimmer3 GSR+ sensor was used to measure participants' galvanic skin response (GSR). Two independent variables (i.e. leading vehicle speed and autonomy) were selected and resulted in a 2x2 factorial design. Participants were also exposed to two hard-braking scenarios: one with a leading HV and one with a leading AV. A post-drive survey included questions about the participant's level of comfort following HVs and AVs. The driving simulator experiment was successfully completed by 36 participants. Results from the linear mixed model show that driver level of stress was 70% higher in hard-brake scenarios involving HVs versus AVs. Of the 78 hard-braking scenarios tested in this study, 10 crashes were observed (4 with an HV, 6 with an AV). Half of the participants involved in a crash with an HV perceived the leading vehicle to be at fault, while all the participants who crashed with an AV blamed themselves for the error. Additionally, drivers over the age of 34.5 were found to give AVs 2% larger headways than HVs, while younger drivers gave AVs 18% smaller headways than HVs. Zero participants above the age of 34.5 years self-reported being ‘unconcerned’ when following an AV in the post-drive survey, while 38% of participants under the age of 34.5 did. This study supports the need for a better understanding of how human drivers will interact with AVs to calibrate human driver models when AV market penetrations are between 0% and 100%.]]></description>
      <pubDate>Mon, 24 Feb 2025 13:21:17 GMT</pubDate>
      <guid>https://trid.trb.org/View/2509302</guid>
    </item>
    <item>
      <title>Älgskadefondsföreningens viltsimulator : effektutvärdering</title>
      <link>https://trid.trb.org/View/2491298</link>
      <description><![CDATA[Älgskadefondsföreningen has since 2015 been demonstrating its wildlife simulator, a small portable driving simulator with scenarios where wildlife (game) comes up on the road so that it is very difficult to avoid hitting it. The effects of this demonstration activity were investigated in an online survey, with n = 751 respondents with experience of the wildlife simulator, and n = 4 585 respondents without experience of the wildlife simulator. The results showed that those who have had wildlife contact after driving or watching someone else drive a wildlife simulator believe they have benefited from their wildlife-simulator experience. More experienced drivers and those who had been involved in a wildlife accident or incident before 2015 felt that they had benefited less from their wildlife-simulator experience. Those who had experienced wildlife accidents and incidents before their wildlife-simulator experience also had relatively few wildlife accidents in relation to wildlife incidents after their wildlife-simulator experience. There was also a positive correlation between the number of scattered training sessions in a wildlife simulator (years 2015-2023. and the number of wildlife incidents, while there was no corresponding correlation with wildlife accidents. Otherwise, there were non-significant effects of wildlife-simulator experience. The conclusions are that the wildlife simulator demonstrations are appreciated and considered valuable in subsequent wildlife contacts in traffic, and that repeated training in avoiding wildlife collisions should be favourable for reducing wildlife accidents.]]></description>
      <pubDate>Fri, 17 Jan 2025 15:18:09 GMT</pubDate>
      <guid>https://trid.trb.org/View/2491298</guid>
    </item>
    <item>
      <title>Objective motion cueing tuning for vehicle dynamics evaluation in winter conditions</title>
      <link>https://trid.trb.org/View/2491285</link>
      <description><![CDATA[Vehicle manufacturers strive for an increasingly efficient and faster development process. Although computer-aided engineering has made significant progress toward a fully virtual development process, a challenge remains in integrating human subjective feedback to fully close the virtual development loop. Subjective assessment of ride and driving characteristics are still very important traits of a passenger car. Moving-base driving simulators have the ability to introduce the human into the virtual development loop, thus enabling subjective assessment of virtual vehicle models. Such an introduction has the potential to significantly speed up the development process and at the same time save resources by avoiding physical testing and providing informed decisions in the early phase of vehicle development cycles. The challenge to do so lies in the possibility to evaluate a vehicle in a driving simulator, which is highly dependent on the motion cueing. Motion cueing algorithms are used to map the vehicle motion into the confined workspace of a driving simulator. As of today, these algorithms are still often tuned and evaluated subjectively. The challenge with this approach is that it does not guarantee the fidelity of the cueing and it needs physical vehicles to be compared with. This work thus focuses on the objective development and evaluation of motion cueing, which potentially could enable high fidelity motion cueing in the early stages of the vehicle development process, when prototypes are not available. This is very important for winter testing since the testing is challenging with regards to ambient conditions, the limited testing season and the increasing need to speed up the development process. The goal of this work is to move towards an objective approach to cueing evaluation based on physical models combining vehicle model, simulator, and human. Therefore, this thesis presents an objective methodology to motion cueing evaluation and development.]]></description>
      <pubDate>Fri, 17 Jan 2025 15:17:54 GMT</pubDate>
      <guid>https://trid.trb.org/View/2491285</guid>
    </item>
    <item>
      <title>Improving speed compliance amongst young novice drivers</title>
      <link>https://trid.trb.org/View/2431458</link>
      <description><![CDATA[Speeding is a serious issue, that is the leading cause of road-related deaths and hospitalisations each year. Previous studies have indicated that training can be used as a speeding deterrent; even a single session of training can reduce the number of speeding violations, and the magnitude of speeding. The aim of this study was to examine the effect of training on young novice drivers’ speed management behaviour. Approximately forty provisional licensed drivers between eighteen to twenty-five years of age were selected to participate in this study. The participants were divided into a control group, and a training group, and all participants were required to conduct three drives in a computer-based driving simulator; a familiarization drive, a baseline drive, and a test drive. For the training group, self-explanatory and graphical based feedback was provided after the baseline drive, before conducting the test drive. Upon completing the drives, participants completed a postdrive survey, which provided self-reported data relating to speeding occurrences, and their reasons for speeding. Based on this information, each driver was classed under one of the four key driver typologies derived by Blincoe et al. (2006). Namely, these typologies include: conformers, who report they never exceed speed limits; deterred drivers, who are put off speeding by the presence of cameras; manipulators, who slow only at camera locations; and defiers, who exceed limits regardless of cameras. The results of this study are important in addressing the issue of providing effective and tailored driver training to various types of young drivers, in order to improve their speed compliance. Ultimately, reducing the number of speed violations, and the magnitude of these speed violations should contribute to reduce road fatalities and hospitalisations on Australian roads.]]></description>
      <pubDate>Tue, 17 Sep 2024 14:48:14 GMT</pubDate>
      <guid>https://trid.trb.org/View/2431458</guid>
    </item>
    <item>
      <title>Fit2Drive</title>
      <link>https://trid.trb.org/View/2388979</link>
      <description><![CDATA[The goal of the project was to assess fitness to drive, and specifically how alcohol intoxication interacts with driver attention and drowsiness. A test track and simulator study involved 35 participants driving in a simulator and on a test track while sober and under the influence of alcohol with increasing levels of breath alcohol content. The participants were recruited through word of mouth and a list of interested participants and underwent screening. The simulator consisted of a car seat and three screens, and the route involved driving through urban and suburban areas with other road users present. During the driving, participants were asked to perform a non-driving-related activity task. The test track was approximately 3.1 km long, and the vehicle used was equipped with three Smart Eye Driver Monitoring Systems and a Smart Eye Cabin Monitoring System. The participants in the study were equipped with heart rate measuring electrodes and filled out a background questionnaire before practicing driving the simulator or instrumented vehicle on the track while sober. Participants then drove a sober baseline trial in both settings before receiving the first dose of alcohol based on the Hume-Weyers formula, targeting 0.2 ‰. The participants underwent the procedure for three additional target levels of intoxication (0.5 ‰, 0.8 ‰, 1.0 ‰). In addition to the test track and simulator study, a field study with naturalistic driving in the city and outside of it was conducted. During the session, participants were allowed to use cruise control and were observed by a test leader who monitored the measuring equipment and made notes on the driver's behaviour, sleepiness level, and any unexpected events or deviations from expected driving behaviour. The data collected included video recordings of the driver's head and eye movements, recordings of the inside of the cabin and the driver's upper body, heart activity measurements and driving behaviour.]]></description>
      <pubDate>Mon, 10 Jun 2024 14:04:56 GMT</pubDate>
      <guid>https://trid.trb.org/View/2388979</guid>
    </item>
  </channel>
</rss>