<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>The Effects of Tactile Display on Automated Vehicle Takeover: A Literature Review</title>
      <link>https://trid.trb.org/View/2689178</link>
      <description><![CDATA[Current autonomous vehicles are still semi-autonomous and require drivers to take over control of the vehicle under various conditions (e.g., encountering erased lane markings). This presents an issue in human-machine interaction, as there is a need for reliable methods to guide drivers through the sudden and complex takeover process. A tactile display that can present multi-dimensional information (e.g., status, direction, and position) may be a good option, especially when the information presented in their visual and auditory channels is overloading. However, limited work has attempted to summarize this topic. Therefore, the goal of this study is to synthesize literature that examined the effects of tactile display on takeover performance in automated vehicles. Findings indicated that tactile displays can be placed in multiple in-vehicle locations to present various vibrotactile patterns helping to improve drivers’ performance during the automated vehicle takeover, which could inform the design of human-machine interfaces for autonomous vehicles.]]></description>
      <pubDate>Sun, 03 May 2026 18:19:54 GMT</pubDate>
      <guid>https://trid.trb.org/View/2689178</guid>
    </item>
    <item>
      <title>Level of detail in visualization for human autonomy teaming: Speed, accuracy, and workload effects</title>
      <link>https://trid.trb.org/View/2680925</link>
      <description><![CDATA[For human autonomy teaming, information for promoting transparency could lead to information overload, negatively impacting performance and workload. This paper presents an empirical study investigating how different levels of detail (LODs) about the autonomy represented on the user interface would influence speed, accuracy, and workload. Specifically, we compared visualizations of a lost person model at four different LODs to aid in directing human and unmanned aerial vehicles searchers in search and rescue missions. The lowest LOD was found to support higher accuracy but at the expense of speed. The highest LOD induced the highest workload, while the other three LODs induced lower and similar levels of workload. The results indicate that the LOD in transparent displays could induce a speed and accuracy tradeoff.]]></description>
      <pubDate>Sat, 02 May 2026 15:47:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2680925</guid>
    </item>
    <item>
      <title>Towards an approach to define transparency requirements for maritime collision avoidance</title>
      <link>https://trid.trb.org/View/2680969</link>
      <description><![CDATA[This study discusses an approach to support human supervision of autonomous maritime collision avoidance systems by disclosing the system’s perceived information, internal reasoning, decisions, and planned actions as layers of transparency. Information requirements, identified through a cognitive task analysis, were structured using the information processing model by Parasuraman, Sheridan, and Wickens (2000). This model was contextualized to the maritime collision avoidance setting such that the information from the analysis could be structured into unique and distinct layers. A set of minimum information requirements was identified depicting the system’s decisions and planned action, supported by additional layers to reveal its internal reasoning. This approach aims at supporting humans in effectively supervising autonomous collision avoidance systems in their operational context by providing understandability and predictability about what the system is doing, why it is doing it, and what it will do next, i.e., transparency.]]></description>
      <pubDate>Sat, 02 May 2026 15:47:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2680969</guid>
    </item>
    <item>
      <title>Dynamic Driving Style Recognition for Human Machine Shared Control</title>
      <link>https://trid.trb.org/View/2659112</link>
      <description><![CDATA[An intelligent human machine shared control system should be able to identify the driving style of real human drivers, so that the recommended driving strategy is in line with their driving style, and thus reduce the human intervention during the human-machine co-driving. The upgrade of vehicle sensors provides us an opportunity for a better judgement of the driver's driving style. This paper proposes a new driving style classification method based on the active learning. This method first uses the concept of driving volatility measurement to measure the performance of vehicles in terms of speed and acceleration, and then generates data to reduce the influence of data distribution on learning effect. The proposed method divides drivers' behaviors into aggressive, ordinary and calm styles. It can effectively learn the features related to driving style in driving volatility measurement, and the active learning method itself can reduce the requirement of human expert experience. The effectiveness of the proposed method is proved by the experiments on the UAH-Driveset, and then this paper uses the proposed method to analyze some data from the security pilot model deployment (SPMD).]]></description>
      <pubDate>Wed, 29 Apr 2026 09:10:07 GMT</pubDate>
      <guid>https://trid.trb.org/View/2659112</guid>
    </item>
    <item>
      <title>Identifying Research Gaps Through Self-Driving Car Data Analysis</title>
      <link>https://trid.trb.org/View/2659129</link>
      <description><![CDATA[There are currently around thirty companies testing self-driving cars in San Francisco, CA, effectively creating a living laboratory. Of these companies, only Waymo is engaged in commercial operations, while Zoox conducts routine driverless testing operations in San Francisco. Despite these successes, federal investigations have been opened into both companies for safety concerns, and Cruise is attempting to reinstate its permit after a near-fatal pedestrian crash. An analysis of these three companies’ crash data from required reporting illustrates that many areas of self-driving need improvement. The most significant crash type for Waymo and Zoox are struck-from-behind events, while Cruise struggled most with unexpected actions by others. Computer vision systems are very brittle and likely play an outsized role in crashes. Self-driving cars also struggle to reason under uncertainty, and simulations are not effectively bridging the physical-to-real-world testing gap. This analysis underscores that research is lacking, especially for artificial intelligence involving computer vision and reasoning under uncertainty.]]></description>
      <pubDate>Wed, 29 Apr 2026 09:10:07 GMT</pubDate>
      <guid>https://trid.trb.org/View/2659129</guid>
    </item>
    <item>
      <title>LLM-as-UI: A preliminary exploration of fine-tuned language models as intelligent interfaces in modular ship design</title>
      <link>https://trid.trb.org/View/2690430</link>
      <description><![CDATA[Complex modular ship design platforms often create usability barriers for non-expert stakeholders due to rigid graphical user interfaces (GUIs). This paper introduces an ‘LLM-as-UI’ methodology, a novel interaction paradigm where a fine-tuned large language model (LLM) serves as the primary user interface, replacing traditional GUI elements to bridge the gap between human intent and system execution. The core challenge of this approach lies in the fundamental mismatch between the inherent ambiguity of natural language and the strict, schema-bound parameter structures required by modular ship design systems, which creates a gap that prevents general-purpose LLMs from reliably converting user inputs into precise, system-compliant formats. To address this, we fine-tuned a lightweight, small-scale LLM using low-rank adaptation (LoRA) combined with structured prompting strategies designed to enforce output constraints and domain-specific formatting. We demonstrate that while the off-the-shelf lightweight model is insufficient for this task, its fine-tuned counterpart provides a robust and viable solution within the constraints of consumer-grade hardware. Experimental results demonstrate that a fine-tuned LLM can effectively function as an intelligent interface layer, significantly enhancing the reliability and fidelity of translating user intent into precise, system-compliant parameters.]]></description>
      <pubDate>Tue, 28 Apr 2026 11:19:11 GMT</pubDate>
      <guid>https://trid.trb.org/View/2690430</guid>
    </item>
    <item>
      <title>AI-based System for Road Surface Condition Forecasting Using Multi-Source Meteorological Data</title>
      <link>https://trid.trb.org/View/2683917</link>
      <description><![CDATA[Accurate and timely forecasts of road surface conditions are crucial for efficient winter maintenance, enhanced traffic safety, and the optimized use of de-icing agents. Road surface phenomena, in complex fields present challenges to traditional forecasting methods due to their nonlinear and localized nature. This study presents a machine learning framework predicting real-time road states (dry, wet, icy, snowy) across Bavaria, Germany. It integrates data from over 516 Road Weather Stations (RWS), thermal measurements from winter maintenance vehicles, and elevation data from the Open Elevation API. Data undergoes temporal alignment, spatial interpolation, and missing-value imputation. Decision Trees form the core model for interpretability and nonlinear pattern handling. Each RWS employs a localized model, while a generalized version covers unmonitored roads via spatial adjustments. With over 85% accuracy, the system facilitates dynamic winter maintenance and minimizes resource waste. Cyber-physical in smart mobility and transportation networks support improved real-time hazard responses. This approach shows how scalable infrastructure can be made resilient using machine learning.]]></description>
      <pubDate>Mon, 27 Apr 2026 15:01:18 GMT</pubDate>
      <guid>https://trid.trb.org/View/2683917</guid>
    </item>
    <item>
      <title>Investigating flight crew strategies to cope with unexpected events: A multi-layered extended control model of joint crew-automation activity</title>
      <link>https://trid.trb.org/View/2684752</link>
      <description><![CDATA[Although commercial aviation is a highly standardized and ultra-safe industry, there are still times when the flight crew are faced with an unexpected situation, and must respond appropriately. This article studies how to characterize variability in flight crew strategies handling unexpected events, problematic as well as successful. Hollnagel’s Extended Control Model (ECOM) is operationalized as an analysis tool for crew-automation Joint Cognitive System (JCS) performance, for simulated B747 and A330 scenarios, as well as more generally for joint activity of crew and automation in airliner cockpits. This development and application of ECOM to two studies in a research flight simulator is described, highlighting crew-automation JCS performance at multiple layers of control. The ECOM analyses are found to be in unison with industry expert ratings, while providing a more nuanced qualitative perspective supporting pattern identification. Various process-tracing visualizations of flight crew strategies in terms of performance at the various ECOM layers illustrate patterns. ECOM and related Contextual Control Model (COCOM) classifications and assessments contribute to the explanation of performance and as a rich qualitative description of desirable performance. Frequent and regular interaction between ECOM layers and tactical/strategic control modes correspond to desirable performance. Recommendations to the aviation industry for preparing pilots better for unexpected events are outlined.]]></description>
      <pubDate>Mon, 27 Apr 2026 14:57:56 GMT</pubDate>
      <guid>https://trid.trb.org/View/2684752</guid>
    </item>
    <item>
      <title>Mutual trust based human-machine shared steering control of intelligent vehicles</title>
      <link>https://trid.trb.org/View/2691733</link>
      <description><![CDATA[The allocation of driving authority is critical to the intelligent human-machine shared steering system of vehicles. Currently, the mutual trust levels between the driver and automatic controller are rarely considered when allocating driving authority. However, a thoughtless mutual trust may reduce cooperation efficiency and even cause decision conflicts, leading to a threat to driving safety. To this end, this paper proposes a human-machine shared steering control (SSC) method for intelligent vehicles that considers mutual trust between humans and machines. Firstly, a human-machine mutual trust (HMMT) model was constructed with consideration of the driver’s and vehicle’s capability. Then, a Takagi-Sugeno fuzzy method considering the HMMT level, the driver’s steering angle, the lateral deviation, and the yaw rate is designed. Finally, driver-in-the-loop experiments under three conditions (high-trust, moderate-trust, and low-trust levels) are carried out. The results indicate that the proposed SSC method can minimize driver workload while ensuring driving safety and stability of intelligent human-machine shared vehicles.]]></description>
      <pubDate>Thu, 23 Apr 2026 13:54:43 GMT</pubDate>
      <guid>https://trid.trb.org/View/2691733</guid>
    </item>
    <item>
      <title>Experimental performance analysis of inland vessel remote operation: A case study on the Yangtze River</title>
      <link>https://trid.trb.org/View/2693280</link>
      <description><![CDATA[The Remote Driving and Control (RDC) system constitutes a key component within the technical advancement of intelligent shipping. Its closed-loop operational framework integrates a shore-based monitoring and control platform, many shipboard perception devices, autonomous control units, and high-reliability communication systems. Comprehensive validation of the RDC system in the inland waterway serves as a critical transitional phase from theoretical development to engineering implementation in intelligent shipping. Hence, this study establishes a multi-dimensional performance encompassing key points such as course keeping accuracy, path tracking robustness, collision avoidance efficacy, communication link stability, and human-machine cooperation efficiency. Experimental results demonstrate that systematic testing can be effectively realized within the constructed hardware and software platform, contributing to enhanced operational safety and control performance of RDC systems. These findings offer empirical evidence for the iterative advancement of intelligent shipping technologies. Through the design and execution of multi-scenario experiments and system-level performance assessments, this study identifies critical technical challenges in RDC, including communication latency, bottlenecks in perceptual information fusion, consistency in decision-making, and operator cognitive load under human-in-the-loop conditions.]]></description>
      <pubDate>Thu, 23 Apr 2026 09:39:35 GMT</pubDate>
      <guid>https://trid.trb.org/View/2693280</guid>
    </item>
    <item>
      <title>Comparative analysis of touchscreen inceptors and traditional sidesticks on flight decks: flight performance, visual behaviours and situation awareness</title>
      <link>https://trid.trb.org/View/2657039</link>
      <description><![CDATA[The concept of touchscreen primary control device is a novel approach of touchcreen implentation. The objective of this study is to investigate differences in flight performance and attention allocation between a touchscreen inceptor and a traditional sidestick. Twenty-one participants flew four simulated instrument landing system (ILS) approaches – with the touchscreen inceptor or traditional sidestick – during flight scenarios where an aircraft attitude disturbance was either present or absent. Results demonstrated that participant performance scores were worse with the touchscreen inceptor compared to the sidestick during attitude disturbance scenarios. Interestingly, participants exhibited reduced attention to external visual cues with the touchscreen inceptor compared to the sidestick. In addition, use of the touchscreen inceptor resulted in lower performance and lower self-reported situation awareness. Overall, the touchscreen inceptor demonstrated poorer performance compared to the traditional sidestick, highlighting limitations in its current design that warrant cautious consideration and further investigation.]]></description>
      <pubDate>Wed, 22 Apr 2026 16:15:30 GMT</pubDate>
      <guid>https://trid.trb.org/View/2657039</guid>
    </item>
    <item>
      <title>Safety assessment of MASS navigational performance in coastal voyage using cognitive reliability and Bayesian best worst approach</title>
      <link>https://trid.trb.org/View/2693312</link>
      <description><![CDATA[Maritime autonomous surface ships (MASS) represent new operational perspective which transfer navigational responsibilities from ship crew/operator to complex automated systems, specifically in coastal sea voyage where marine traffic congestion and environmental conditions pose significant risks. This paper performs a conceptual safety performance assessment of MASS navigation in coastal voyage systematically under cognitive human error prediction and Bayesian best–worst method (BWM). In the paper, while cognitive human error is predicted to quantify human–machine interaction (HMI) vulnerabilities, including perception, decision-making, and supervisory control tasks; the BWM can predict probabilistic priority weights for critical safety key tasks under uncertainty and expert judgment inconsistency. The outcome of the paper is showing that operational key task MFD2 and CC2 has the highest failure probability values affecting safety performance of MASS navigation in coastal voyage. Besides improving safety performance of autonomous ship navigation, the paper will contribute by providing a conceptual framework for determining critical navigational vulnerabilities, prioritizing safety factors, and supervisory strategies for designers, safety inspectors, ship owners, remote control centre operators and safety researchers.]]></description>
      <pubDate>Wed, 22 Apr 2026 14:59:35 GMT</pubDate>
      <guid>https://trid.trb.org/View/2693312</guid>
    </item>
    <item>
      <title>Towards a human-centred approach in navigational risk assessment of restricted waters</title>
      <link>https://trid.trb.org/View/2693306</link>
      <description><![CDATA[With the development of human-machine cooperative Maritime Autonomous Surface Ships (MASS), ensuring navigational safety has become increasingly complex. Existing risk assessment methods remain primarily geometry-driven, lacking explicit representation of seafarer factors during human–machine cooperative navigation. Hence, this study presents a human-centred approach in ship navigational risk assessment using field theory to enhance maritime safety. By intergating human, ship, and environmental factors affecting navigational safety, an integrated navigational risk field is constructed to evaluate their impact on ships. The Bayesian optimisation (BO) technique is applied to calibrate the model's parameters. Finally, a navigational risk indicator is proposed to assess a ship's overall navigational risk. A case study using real navigation data validates the model's feasibility, offering a fresh perspective on ship navigational risk assessment. Findings reveal high-risk periods primarily during turning manoeuvres into traffic-dense inbound channels and berthing phases, influenced by local traffic and environmental conditions. The case study also highlights differences between the traditional Collision Risk Indicator (CRI) and the proposed Driving Risk Indicator (DRI). The DRI effectively captures navigational risks, especially those associated with human factors, providing new insights for collision prevention. This study helps seafarers proactively identify and respond to collision risks, supporting future human-machine cooperative MASS development.]]></description>
      <pubDate>Wed, 22 Apr 2026 14:59:35 GMT</pubDate>
      <guid>https://trid.trb.org/View/2693306</guid>
    </item>
    <item>
      <title>Investigating the Necessary Components of eHMI for Effective Communication in Mixed Traffic: Insights from a Pedestrian Perspective</title>
      <link>https://trid.trb.org/View/2655730</link>
      <description><![CDATA[The increasing prevalence of automated vehicles (AVs) in urban environments requires effective communication between AVs and other road users—including both pedestrians and manually driven vehicles (MVs)—to ensure safety and a smooth traffic flow. While prior research has primarily focused on one-to-one interactions such as AV-pedestrian scenarios, real-world traffic situations often involve mixed road user types, leading to communication ambiguities. This study investigates how an external human–machine interface (eHMI) can facilitate communication in complex traffic scenes involving AVs, MVs, and pedestrians. A virtual reality-based experiment was conducted, in which participants acted as pedestrians in a scenario involving an AV yielding to both an MV and a pedestrian. Five types of eHMI designs and two MV driver gaze conditions (eye contact vs. no eye contact) were tested. The results indicated that the clarity of eHMI messages and their perceived addressees significantly influenced participants’ comprehension of the AV’s yielding intent and their decision to begin walking. Notably, pictograms explicitly depicting pedestrians were most effective, as they conveyed both the AV’s intention and the communication target. These findings suggest that, in mixed traffic conditions, eHMI designs must clearly indicate both the intention and the intended recipient to avoid miscommunication and enhance traffic cooperation.]]></description>
      <pubDate>Tue, 21 Apr 2026 14:30:17 GMT</pubDate>
      <guid>https://trid.trb.org/View/2655730</guid>
    </item>
    <item>
      <title>Human-oriented adaptive shared steering control for intelligent vehicles</title>
      <link>https://trid.trb.org/View/2691750</link>
      <description><![CDATA[Before autonomous driving is fully realized, human-machine shared control plays a key role in advancing vehicle intelligence. In order to adapt to drivers’ driving abilities as well as to mitigate human-machine conflicts, a novel human-oriented online driving authority optimization method of shared steering is proposed, where a fuzzy control method is used to optimize the driving authority. This method can reduce the driver’s workload and mental load when the drivers and automated driving agent have similar driving intentions. On the other hand, when the automation intention is inconsistent with the human drivers, the human drivers have absolute control over the intelligent vehicle within the vehicle safety zone. To demonstrate the effectiveness of the proposed method, the driving simulator experiments are conducted under four working conditions, namely, manual driving (Manual), low-weighted shared control (SSC-Low), high-weighted shared control (SSC-High), and adaptive fuzzy shared control (SSC-Adaptive), respectively. The experimental results show that compared to SSC-High, SSC-Low, and Manual methods, the proposed SSC-Adaptive method can ensure the vehicle in the safe area while reducing the driver’s workload and mental load.]]></description>
      <pubDate>Mon, 20 Apr 2026 17:01:12 GMT</pubDate>
      <guid>https://trid.trb.org/View/2691750</guid>
    </item>
  </channel>
</rss>