<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>Cybersecurity Dynamometer Testbed: A Review to Advance Vehicle-in-the-Loop Testing of Traditional, Connected and Autonomous Vehicles</title>
      <link>https://trid.trb.org/View/2658696</link>
      <description><![CDATA[Modern vehicles are increasingly more cyber-physical as well as more connected with each passing year. Manufacturers are innovating new technologies (including performance, automation, comfort, and safety) that enhance the driver/passenger experience and continue to move towards increased automation. However, each of these cyber-physical systems poses a potential additional vulnerable attack surface for malicious actors to exploit. Due to high costs, safety risks, and logistical difficulties of testing full vehicles in motion, most research in assessing the cybersecurity of vehicles has focused on simulation, vehicle subsystem(s), or constricted case studies, and not real-world vehicle testing and realistic human interaction assessment. To address this shortcoming, hardware-in-the-loop (HIL) cyber vulnerability testing of fully operational vehicles is needed. This paper presents a review of vehicle cybersecurity research and testing including common technical, logistical, and human factors issues as well as current regulations and guidance. Informative research-focused case studies are presented followed by a proposed cybersecurity vehicle-in-the-loop testbed integrated with a dynamometer to provide a comprehensive, robust, and safe test environment where true effects of cyber testing can be evaluated on a complete vehicle.]]></description>
      <pubDate>Wed, 29 Apr 2026 16:50:11 GMT</pubDate>
      <guid>https://trid.trb.org/View/2658696</guid>
    </item>
    <item>
      <title>Real-Time End-to-End Stop Sign and Traffic Light Detection Development and Vehicle Testing</title>
      <link>https://trid.trb.org/View/2691811</link>
      <description><![CDATA[With the rise of end-to-end autonomous driving, visual perception for environmental understanding has become a key research topic in advanced driver assistance system (ADAS) development. Most existing end-to-end models generate only executable control commands or planned trajectories, making the prediction process difficult to interpret. In this study, we present an end-to-end approach for traffic-light recognition and stop-sign detection built on top of the open-source openpilot framework. Instead of deploying separate object detection networks, we extend the existing backbone with two lightweight multi-task heads: a traffic-light detection and classification head, and a stop-sign detection head with confidence estimation. The modified architecture preserves openpilot’s core driving functionality by reusing shared features and incorporating compact residual and feed-forward layers. The additional perception outputs are appended to the original outputs, ensuring that the model’s performance on other driving tasks remains unaffected. The proposed model is trained under diverse scenes and lighting conditions and demonstrates high accuracy in traffic-light classification and stop-sign detection, maintaining stable and consistent behavior during on-road evaluation. Furthermore, the enhanced model is fully compatible with Comma 3X hardware and has been successfully deployed and validated on a 2025 Nissan Leaf test vehicle. This work demonstrates the feasibility of developing a compact, lightweight, and deployable perception module that integrates traffic-signal understanding directly into an end-to-end driving model with minimal architectural modification.]]></description>
      <pubDate>Thu, 23 Apr 2026 09:11:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2691811</guid>
    </item>
    <item>
      <title>Urban high-risk scenarios for automated vehicle safety testing: A generation and generalization method based on accident data</title>
      <link>https://trid.trb.org/View/2679337</link>
      <description><![CDATA[To improve the effectiveness of automated vehicles (AVs) safety testing and address key issues including distribution bias in road data collection and insufficient coverage of high-risk events, this study adopts a generation and generalization method to establish high-risk scenarios based on the AV Testing – High-Risk City Accident Dataset (AVT-HRCAD). Firstly, Cramer’s V coefficient and eta squared coefficient are employed to identify risk variables that significantly affect accident severity. Secondly, the K-medoids clustering algorithm, iteratively optimized based on Gower distance, generates baseline risk scenarios. Ultimately, a Risk Index (RI) measures risk levels, while the NRPE criterion—assessing Number, Risk, P-value, and Effect—is intended to evaluate and generalize test situations. Principal findings indicate: Nine, seven, and seven key risk variables were identified for expressways, intersections, and road segments, respectively. Ego behavior, target type, collision angle, and lighting conditions consistently emerged as consistently significant risk factors across all three road types. Scenario generalization effectively addressed low-sample/high-severity variables (e.g., three-wheelers), broadening 18 baseline risk scenarios into general-risk, high-frequency-risk, and long-tail high-risk scenarios. A total of 93 urban high-risk test scenarios were established to assess AV capabilities in risk avoidance (across different vehicle types and collision angles), safety distance determination, and distance maintenance. This method provides a more authentic and valuable testing platform for comprehensive AV safety evaluation.]]></description>
      <pubDate>Wed, 08 Apr 2026 13:40:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/2679337</guid>
    </item>
    <item>
      <title>A Mathematical Model for Design and Production Verification Planning</title>
      <link>https://trid.trb.org/View/1784265</link>
      <description><![CDATA[The paper focuses on various important decisions of verification and testing plans of the product during its design and production stages. In most of the product and process development projects, decisions on verification and testing are ad-hoc or based on traditions. Such decisions never guarantee the performance of the product as planned, during its whole life cycle. We propose an analytical approach to provide the concrete base for such crucial decisions of verification planning. Accordingly, a mathematical model is presented. Also, a case study of an automotive Electro-mechanical product is included to illustrate the application of the model.]]></description>
      <pubDate>Tue, 24 Feb 2026 15:39:56 GMT</pubDate>
      <guid>https://trid.trb.org/View/1784265</guid>
    </item>
    <item>
      <title>An Evaluation of Light-Vehicle Automatic Emergency Brake System Responses to 2-Wheeled Road Users</title>
      <link>https://trid.trb.org/View/2658079</link>
      <description><![CDATA[The research in this report used lead vehicle stopped, lead vehicle moving, and lead vehicle decelerating test scenarios to evaluate the automatic emergency braking (AEB) performance of four light vehicles (subject vehicles, or SVs) when presented with a test surrogate designed to emulate a 2-wheeled road user as the principal other vehicle (POV). Up to two motorcycle and two bicycle test surrogates, and two lateral overlaps per POV type, were nominally used for each test scenario. Additionally, up to two POV decelerations were used during conduct of the lead vehicle decelerating tests. Time-to-collision values at the onset of the SV’s forward collision warning and automatic braking initiated by the AEB systems are presented. Crash avoidance summaries are provided where applicable. For test trials that concluded with the SV contacting the POV, relative impact speeds are indicated. Discussions of how the test surrogate radar cross sections compare to the requirements defined in ISO 19206-4:2020 and ISO 19206-5:2025, and of test surrogate use considerations, are also provided.]]></description>
      <pubDate>Mon, 02 Feb 2026 14:13:55 GMT</pubDate>
      <guid>https://trid.trb.org/View/2658079</guid>
    </item>
    <item>
      <title>Examining the Performance of Automatic Emergency Braking Systems</title>
      <link>https://trid.trb.org/View/2658635</link>
      <description><![CDATA[Automated vehicles are expected to significantly reduce traffic crashes and the resultant injuries and fatalities. Although there is ambiguity as to the timeline for market-ready fully automated vehicles, lower levels of automation have already demonstrated some of this significant safety potential. This includes technologies such as automatic emergency braking (AEB), which will be a mandatory feature in all new vehicles from September 2029. This study involved an evaluation of AEB test data from the Insurance Institute for Highway Safety. These tests covered various scenarios, including those in which the test vehicle encounters a balloon car, as well as tests involving “dummy” pedestrians that were walking either parallel or perpendicular to the road. These tests were conducted under various speeds and lighting conditions. The test vehicles ranged from model year 2013 to 2025 and included a diverse range of sensor configurations. A series of random-effects logistic regression models were estimated to evaluate the efficacy of these vehicles across the test scenarios. The results showed that AEB performance has improved considerably over time, reflecting improvements in the underlying sensor technology. However, performance was significantly worse at higher testing speeds, under nighttime conditions, and in other scenarios that represented greater challenges for the sensing technology. This study provides important insights as to the potential and limitations of these systems in their current form.]]></description>
      <pubDate>Tue, 27 Jan 2026 09:19:18 GMT</pubDate>
      <guid>https://trid.trb.org/View/2658635</guid>
    </item>
    <item>
      <title>Evaluation of Safety Perspectives, Approaches, and Needs for Testing, Deploying, and Operating Vehicles Equipped with Driving Automation Systems (Automated Vehicles) on Public Roadways</title>
      <link>https://trid.trb.org/View/2655699</link>
      <description><![CDATA[States and cities across the country would benefit from enhanced technical resources that evaluate different safety perspectives, approaches, and needs in the United States and around the world for testing, deploying, and operating vehicles equipped with driving automation systems (automated vehicles) on public roadways and to assist them in addressing issues in driver licensure, liability and traffic laws under their regulatory jurisdiction. These resources would help inform updates to jurisdiction-specific or agency-specific needs and approaches to automated vehicle safety in the United States. These resources could also help inform the development of a more coordinated multi-jurisdictional, multi-state, or national scale approach for testing, deploying, and operating automated vehicles more safely on public roadways in the United States. 
Below are questions that will be explored as part of this research project. (1) What does safety mean? (2) How does safety get measured? (3) How are safety hazards analyzed and risks assessed and mitigated? (4) What constitutes a positive safety culture for an organization? (5) How does safety get communicated to others? (6) What are effective ways for building public trust? (7) What roles do and should different stakeholders play to ensure acceptable safety? (8) How safe is safe enough for determining when, where, and how to conduct public road testing and/or deployments with or without a safety driver? (9)  Who takes responsibility for ensuring acceptable safety during public road testing and/or deployments? (10) How does liability (including tort and product liability) get addressed in public road testing, deployments and operations of automated vehicles?

The goals of this project are to: (1) Create a clear understanding of different safety perspectives, approaches, and needs for testing, deploying, and operating automated vehicles on public roadways from numerous examples in the United States and around the world. (2) Recognize best practices for the roadway automation industry and state and local transportation agencies in the United States to consider as a basis for a future government-industry coordinated multi-jurisdictional or national framework for safe testing, deployments, and operations of automated vehicles on public roadways.
               ]]></description>
      <pubDate>Fri, 16 Jan 2026 08:03:54 GMT</pubDate>
      <guid>https://trid.trb.org/View/2655699</guid>
    </item>
    <item>
      <title>Interpretation of EU Regulation 2022/1426 on the Type Approval of Automated Driving Systems: Addendum 2 on Testing for Type Approval and Operational Design Domain</title>
      <link>https://trid.trb.org/View/2598550</link>
      <description><![CDATA[The present document provides information to support the interpretation of the requirements established in the Commission Implementing Regulation (EU) 2022/1426 on laying down rules for the application of Regulation (EU) 2019/2144 of the European Parliament and of the Council as regards uniform procedures and technical specifications for the type-approval of the automated driving system (ADS) of fully automated vehicles (European Commission, 2022, referred to as comply with those requirements, and how to provide evidence of such compliance. The present report is therefore a second addendum to the first interpretation document which includes some guidance and interpretation material concerning the testing to be conducted by the Type-Approval Authority for type-approval and the Operational Design Domain of the Automated Driving System. It has been drafted with the active contribution by the experts who compose the Automated and Connected Vehicles sub-group of the Working Group on Motor Vehicles (MVWG-ACV).]]></description>
      <pubDate>Mon, 29 Dec 2025 09:37:23 GMT</pubDate>
      <guid>https://trid.trb.org/View/2598550</guid>
    </item>
    <item>
      <title>Efficient Precision-Driven Scenario Design: Tailoring Collision Type Probabilities for Richer Autonomous Testing</title>
      <link>https://trid.trb.org/View/2598861</link>
      <description><![CDATA[Multi-objective reinforcement learning strategy employs vehicle reachable set optimization are proposed to address two prevalent problems in autonomous vehicle testing: the lack of critical scenarios and the sameness in scenarios generated by traditional methods.The framework prioritizes vehicle dynamics to construct relevant and varied testing scenarios, with a focus on risk triggering states. To streamline the navigation of safety states, we implement a distance-based reward function. Simultaneously, other reward functions balance the frequency and distribution of critical events, drawing on historical trends and Kullback-Leibler divergence for fine-tuning. Our model's efficacy is underpinned by stringent evaluation, showcasing a synergy between training efficiency and scenario variety. Further validation is provided through advanced hardware-in-the-loop simulations, confirming the robustness of our scenario design components in real-world conditions. The proposed method exhibits strong adaptability compared to Reinforcement Learning and Diversity-Driven Exploration, ensuring that the actual probability distribution of accident occurrences closely aligns with the expected distribution (𝐾𝐿 < 0.5) Furthermore, it achieves a coverage rate of 98.77% for the environmental states that may lead to accident scenarios, effectively preventing the occurrence of a single dominant critical scenario type in testing.]]></description>
      <pubDate>Mon, 22 Dec 2025 16:07:16 GMT</pubDate>
      <guid>https://trid.trb.org/View/2598861</guid>
    </item>
    <item>
      <title>Impact Assessment Support Study on the Directives of the Roadworthiness Package</title>
      <link>https://trid.trb.org/View/2601284</link>
      <description><![CDATA[The study analysed the economic, social and environmental impacts of 4 alternative policy options to revise the Roadworthiness Package. They included measures to update the periodic technical inspections (PTI) and the roadside inspection test methods and procedures covering pollutant and noise emissions and safety aspects to ensure that they are suited to modern cars and new technologies. Some of the policy options also include measures to extend the scope of PTI and roadside requirements for specific vehicles categories (i.e. motorcycles and trailers) as well as a requirement for mandatory annual testing of vehicles over ten years. Furthermore, the options include measures to enhance digitisation and exchange of information and data among national authorities as well as a measure intended to tackle odometer tampering. Thanks to a common set of measures, all policy options analysed are expected to lead to improvements in terms of the key objectives of improving road safety (i.e. reduction of fatalities and accidents from road transport), reducing noise and pollutant emissions and reducing the level of odometer tampering. Monetised benefits from the policy options have been estimated between EUR 297.9 billion and EUR 396.1 billion, expressed as present value over the 2026-2050 period relative to the baseline. They are mainly driven by the external costs savings expected related to air pollutant emissions, noise emissions, road crashes, including fatalities, and from the avoided odometer fraud. The mandatory yearly testing for vehicles that are 10-year-old or older would lead to significant additional road safety benefits and benefits for the PTI centres. Other costs savings identified represent a relatively small share of the total benefits in all policy options. In addition to the monetised impacts, additional impacts are expected in terms of promoting innovation and technological development from the promotion of new test methods – especially in the most ambitious policy options– as well as contributions to the functioning on the internal market based on the enhancement of information exchange, better enforcement and mutual recognition of PTI certificates. There are also some limited impacts on employment expected. The associated costs are estimated to be between EUR 7.3 billion and EUR 68.6 billion expressed as present value for the period 2026-2050. The main costs drivers are the adjustment costs for PTI centres followed by the administrative costs for vehicle owners – businesses and citizens – and the administrative costs for national authorities. On balance, Policy Option 2 is identified as the preferred option as it addresses all identified issues in a comprehensive manner, even if it does not have the highest benefit to cost ratio. Additional benefits associated with another policy option – related to a more extended scope of PTI to cover all two and three wheelers and the full recognition of PTI certificates in other Member States – are accompanied with higher costs and make that option significantly more difficult to implement.]]></description>
      <pubDate>Thu, 18 Dec 2025 10:56:12 GMT</pubDate>
      <guid>https://trid.trb.org/View/2601284</guid>
    </item>
    <item>
      <title>Geographically Distributed Test Environment: Validation of Integrated Motion Control of Multi-Actuated Electric Vehicle</title>
      <link>https://trid.trb.org/View/2591559</link>
      <description><![CDATA[As an example of a geographically distributed test environment, an integrated motion control system for multi-actuated electric vehicles has been proposed and evaluated. This system unifies three active subsystems: drive-by-wire propulsion with independent in-wheel electric motors, electro-hydraulic brake actuators, and active suspension actuators. A distributed X-in-the-loop network architecture supports the approach, integrating a real-time validated vehicle model, dedicated test benches for each subsystem, and a driving simulator located in different geographical locations. This setup enables real-time testing and validation of the integrated control strategy. Validation results show improved ride comfort and safety.]]></description>
      <pubDate>Thu, 20 Nov 2025 17:07:21 GMT</pubDate>
      <guid>https://trid.trb.org/View/2591559</guid>
    </item>
    <item>
      <title>Using simulation to develop protocols for bicycle crash-avoidance testing</title>
      <link>https://trid.trb.org/View/2617069</link>
      <description><![CDATA[In the U.S., bicyclist fatalities have risen 47.5% over the last decade. On some of their latest vehicles, automakers have introduced bicycle-detecting automatic emergency braking (AEB) systems that automatically apply the brakes to avoid or mitigate collisions with bicyclists. These systems are not evaluated in the U.S. market, although similar tests are conducted elsewhere. The purpose of this study was to use simulation to understand the AEB system characteristics that might perform well in potential testing protocols. Using openPASS, a bicycle and passenger vehicle were simulated traversing through a four-way intersection of two- lane roadways. Both a straight crossing path and a parallel path scenario were simulated with the subject vehicle traveling between 20 and 80 km/h and the bicycle traveling between 5 and 20 km/h. The subject vehicle’s sensor field of view (30, 60, 90, 120, 150, 180 degrees) and range (10, 20, 30, 40, 50, 60 m) were varied, and the AEB response was designed to match the braking characteristics observed in pedestrian crash-avoidance testing. In total, 30 hypothetical AEB systems were tested in 20 unique straight crossing path scenarios and 18 hypothetical AEB systems were tested in 24 unique parallel path scenarios. In the straight crossing path scenario, when evaluating based on avoidance, the simulations where the subject vehicle and bicycle were moving at similar speeds differentiated systems by the sensor field of view. In both straight crossing path and parallel path scenarios, collision avoidance at higher relative speeds was differentiated by the sensor range. A straight crossing path protocol with the subject vehicle and bicycle moving at similar, low speeds could lead to bicycle-detecting AEB implementations with a wider field of view. The test speed in both scenarios primarily influenced the sensor range. This research provides testing agencies with information about how testing protocol decisions could influence AEB system design. In addition, this study demonstrates the feasibility of using simulation tools to develop relevant crash avoidance testing protocols. Future simulations could predict the performance in real-world bicycle crashes of systems that would also perform well in the potential testing protocols.]]></description>
      <pubDate>Wed, 19 Nov 2025 17:09:39 GMT</pubDate>
      <guid>https://trid.trb.org/View/2617069</guid>
    </item>
    <item>
      <title>Make full use of testing information: An integrated accelerated testing and evaluation method for autonomous driving systems</title>
      <link>https://trid.trb.org/View/2614616</link>
      <description><![CDATA[Testing and evaluation is an important step to address the safety of the intended functionality (SOTIF) before the large-scale application of the autonomous driving systems (ADSs). Based on the three level of scenario abstraction theory, a testing can be performed within a logical scenario, followed by an evaluation stage which is inputted with the testing results of each concrete scenario generated from the logical parameter space. During the above process, abundant testing information is produced which is beneficial for comprehensive and accurate evaluations. To make full use of testing information, this paper proposes an Integrated accelerated Testing and Evaluation Method (ITEM). Based on a Monte Carlo Tree Search (MCTS) paradigm and a dual surrogates testing framework proposed in the previous work, this paper applies the intermediate information (i.e., the tree structure, including the affiliation of each historical sampled point with the subspaces and the parent–child relationship between subspaces) generated during the testing stage into the evaluation stage to achieve accurate hazardous domain identification. Moreover, to better serve this purpose, the Upper Confidence Bound (UCB) calculation method is improved to allow the search algorithm to focus more on the hazardous domain boundaries. Further, a stopping condition is constructed based on the convergence of the search algorithm. Ablation and comparative experiments are then conducted to verify the effectiveness of the improvements and the superiority of the proposed method. The experimental results show that ITEM could well identify the hazardous domains in both low- and high-dimensional cases, regardless of the shape of the hazardous domains, indicating its generality and potential for the safety evaluation of ADSs.]]></description>
      <pubDate>Tue, 18 Nov 2025 09:30:32 GMT</pubDate>
      <guid>https://trid.trb.org/View/2614616</guid>
    </item>
    <item>
      <title>Interactive Critical Scenario Generation for Autonomous Vehicles Testing Based on In-Depth Crash Data Using Reinforcement Learning</title>
      <link>https://trid.trb.org/View/2591901</link>
      <description><![CDATA[Before implementing Autonomous Vehicles (AVs) in real-world settings, it is imperative to conduct thorough safety testing. Virtual simulation testing, known for its high fidelity, cost-effectiveness, and efficiency, emerges as a pivotal technology poised to replace traditional testing methods. This study proposes an interactive critical scenario generation method based on in-depth crash data for AV safety testing. The process begins by reconstructing intersection crashes from the China In-depth Mobility Safety Study-Traffic Accident (CIMSS-TA) database. Scene setup involves extracting static and dynamic variables from the original crashes. Subsequently, scene diversity is enhanced using Conditional Tabular Generative Adversarial Network (CTGAN). Next, the dynamic interaction between the objective vehicle, controlled by the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, and the ego vehicle, controlled by Baidu Apollo within the SVL simulator, generates challenging scenarios. Following this, various experiments are designed to ensure comprehensive coverage of intersection driving situations, with diversity stemming from the relative positions of the vehicles and their driving tasks. Lastly, the effectiveness of these generated critical scenarios is evaluated using metrics such as crash rate, Generalized-Time-To-Collision (GTTC), and Post Encroachment Time (PET). The study also compares the performance of different control algorithms. The experimental results indicate that the interactive critical scenarios present significant challenges to AVs, making them valuable for assessing the safety and resilience of AVs in dynamic, interactive, and hazardous situations.]]></description>
      <pubDate>Tue, 11 Nov 2025 11:58:11 GMT</pubDate>
      <guid>https://trid.trb.org/View/2591901</guid>
    </item>
    <item>
      <title>An Accelerated Filter for Critical Scenario Identification in Automated Driving Function Testing: A Model-Free Approach</title>
      <link>https://trid.trb.org/View/2553212</link>
      <description><![CDATA[Automated Vehicle (AV) safety is a critical issue and appeals to worldwide focus. To ensure AV safety, AV functions should be tested and evaluated in an enormous number of scenarios. Since such AV testing is time-consuming, scenario filters have been developed to identify safety-critical scenarios and omit ordinary ones. However, the scenarios identified by these filters do not uniquely match the AV function to be tested and are most likely not critical for the AV function. Therefore, an enhanced scenario filter is proposed in this paper. It bears the following features: 1) Automated-driving-function-specific scenario identification; 2) High coverage of critical scenarios; 3) Enhanced identification efficiency by avoiding adopting a surrogate model; 4) High reliability of critical scenario identification. To enable the above features, the proposed filter formulates the identification problem into an optimization problem and solves it with a model-free approach. Experiments have been conducted to evaluate and validate the proposed filter. The results confirm that the proposed filter is able to improve coverage of critical scenarios, efficiency of identification, and reliability of identification compared to the state-of-the-art filter. Specifically, the proposed filter improves coverage by up to 70 percent, efficiency by up to 97 percent, and reliability by up to 22 percent. The results also reveal that the proposed filter shows an increasing advantage for testing AV functions with higher complexity.]]></description>
      <pubDate>Fri, 07 Nov 2025 16:56:52 GMT</pubDate>
      <guid>https://trid.trb.org/View/2553212</guid>
    </item>
  </channel>
</rss>