<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=PHNlYXJjaD48cGFyYW1zPjxwYXJhbSBuYW1lPSJzdWJqZWN0aWQiIHZhbHVlPSIxODA0IiAvPjxwYXJhbSBuYW1lPSJzdWJqZWN0bG9naWMiIHZhbHVlPSJvciIgLz48cGFyYW0gbmFtZT0idGVybXNsb2dpYyIgdmFsdWU9Im9yIiAvPjxwYXJhbSBuYW1lPSJsb2NhdGlvbiIgdmFsdWU9IjE2IiAvPjwvcGFyYW1zPjxmaWx0ZXJzIC8+PHJhbmdlcyAvPjxzb3J0cz48c29ydCBmaWVsZD0icHVibGlzaGVkIiBvcmRlcj0iZGVzYyIgLz48L3NvcnRzPjxwZXJzaXN0cz48cGVyc2lzdCBuYW1lPSJyYW5nZXR5cGUiIHZhbHVlPSJwdWJsaXNoZWRkYXRlIiAvPjwvcGVyc2lzdHM+PC9zZWFyY2g+" 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>Fleet Turnover and Secondary Market Dynamics in U.S. Commercial Truck Markets</title>
      <link>https://rip.trb.org/View/2775678</link>
      <description><![CDATA[Commercial heavy-duty trucks operate over long service lives and frequently change ownership through active secondary markets. While most transportation research focuses on new vehicle sales, limited attention has been given to how secondary markets influence fleet turnover and long-term technology adoption. This gap reduces the accuracy of models used to forecast fleet evolution, especially as new vehicle technologies enter the market. This project empirically characterizes primary and secondary truck markets and develops a simulation framework to examine how turnover dynamics shape technology diffusion. Using publicly available used truck listing data, the study will estimate how vehicle prices decline with age and mileage, how usage changes over time, and when trucks typically appear in the secondary market. These empirical patterns will be used to construct a fleet turnover model that represents vehicle aging, resale, and retirement. The model will simulate how a new vehicle technology introduced through new sales spreads through the fleet as trucks transition across ownership stages. The analysis will generate estimates of fleet composition over time under different assumptions about resale behavior, utilization, and adoption rates. By incorporating observed secondary market behavior, this research improves understanding of how commercial vehicle fleets change over time and supports more accurate forecasting for transportation planning and policy design.]]></description>
      <pubDate>Wed, 09 Sep 2026 15:35:46 GMT</pubDate>
      <guid>https://rip.trb.org/View/2775678</guid>
    </item>
    <item>
      <title>Designing Flexible Vehicle Efficiency Regulations for Light-Duty Vehicles</title>
      <link>https://rip.trb.org/View/2775563</link>
      <description><![CDATA[Improving the efficiency of the vehicle fleet and diversifying available vehicle technologies are critical strategies for strengthening transportation system resilience and reducing dependence on imported fuels. One type of public policy to achieve these goals is performance-based regulations, which act upstream in the supply chain by requiring vehicle manufacturers to meet a specified standard across a fleet. A key feature of modern vehicle regulations is the inclusion of flexible design mechanisms that allow manufacturers to choose among multiple compliance pathways. These mechanisms—such as credit trading and banking—are intended to reduce compliance costs and improve policy acceptability. However, despite their widespread use, there is limited systematic understanding of how these design features are defined, their rationale for implementation, and how they influence regulatory outcomes. This project will develop a comprehensive framework for understanding and designing flexible vehicle efficiency regulations. The work will identify flexible design mechanisms embedded in global vehicle efficiency regulations, analyze how different policy design features influence compliance costs and cost distribution across manufacturers, and provide policy-relevant guidance for designing efficient, durable, and adaptable vehicle regulations. ]]></description>
      <pubDate>Wed, 09 Sep 2026 15:23:32 GMT</pubDate>
      <guid>https://rip.trb.org/View/2775563</guid>
    </item>
    <item>
      <title>Drone-in-a-Box: Enhancing Public Safety and Environmental Monitoring on Cape Cod</title>
      <link>https://rip.trb.org/View/2775052</link>
      <description><![CDATA[Cape Cod, a popular tourist destination, faces unique challenges due to its geographic isolation, seasonal population fluctuations, and increasing environmental concerns. This research proposes leveraging drone-in-a-box (DiB) technology, an autonomous drone system with automated launch, landing, and charging capabilities, to address these challenges. DiB systems offer persistent aerial surveillance and rapid response capabilities, making them ideal for various applications in remote and dynamic environments.

The research team for this project includes representatives from 
Massachusetts Department of Transportation (MassDOT) Aeronautics, MassAutonomy, and Endicott College.  Endicott College will identify appropriate team members based on the expertise needed for each aspect of the project.

This project is significantly strengthened by the collaboration and support of the Wellfleet Police and Fire Departments, who will provide valuable expertise, operational insights, and access to critical resources.

The objectives of this project are to: (1) Evaluate the technical feasibility of deploying DiB systems in the Cape Cod environment, considering factors such as weather conditions, Federal Aviation Administration (FAA) regulations, and communication infrastructure.
(2) Assess the operational effectiveness of DiB systems in each use case, measuring improvements in traffic flow, emergency response times, and shark detection accuracy.
(3) Analyze the cost-benefit of DiB implementation compared to traditional methods. 
(4) Investigate public perception and acceptance of drone technology for public safety and environmental monitoring.
The project will yield data and associated reports detailing the effectiveness of the use of drone-in-a-box (DiB) technology, an autonomous drone system with automated launch, landing, and charging capabilities, to address these challenges.
]]></description>
      <pubDate>Fri, 04 Sep 2026 14:40:10 GMT</pubDate>
      <guid>https://rip.trb.org/View/2775052</guid>
    </item>
    <item>
      <title>Cost Recovery for New Entrant Aircraft Technologies</title>
      <link>https://rip.trb.org/View/2772541</link>
      <description><![CDATA[As new entrant aircraft technologies begin to emerge, airports face new questions regarding how to recover the costs associated with supporting these operations. Many airports currently recover a portion of their operating costs through fuel flowage fees, but alternative propulsion technologies, including electric, hydrogen, and hybrid aircraft, may require different cost recovery approaches. Airports also need to consider costs associated with infrastructure, charging or fueling systems, lease agreements, and other facilities and services needed to support these aircraft. Research is needed to identify practical and equitable approaches that airports can use to recover costs associated with supporting new entrant aircraft technologies as aircraft propulsion systems and related infrastructure needs evolve.

The objective of this research is to develop guidance on cost recovery approaches for new entrant aircraft technologies. The research should examine cost recovery mechanisms for alternative propulsion technologies, including electric, hydrogen, and hybrid aircraft, and address airport approaches to recovering costs associated with infrastructure, charging or fueling systems, lease agreements, facilities, and other services needed to support these aircraft. The resulting guidance should provide airports with practical approaches that can be adapted to different airport operating environments and emerging aircraft technologies.]]></description>
      <pubDate>Thu, 03 Sep 2026 08:27:06 GMT</pubDate>
      <guid>https://rip.trb.org/View/2772541</guid>
    </item>
    <item>
      <title>Synthesis of Information Related to Transit Practices. Topic SG-23. Data-Driven Approaches for Optimizing Transit Parts Procurement, Lead Time Risk, and Critical Spare Parts Planning</title>
      <link>https://rip.trb.org/View/2772554</link>
      <description><![CDATA[Transit agencies depend on the timely availability of spare parts to maintain fleet reliability, minimize vehicle downtime, and sustain safe and efficient service. Agencies employ a variety of approaches to procure, stock, and manage spare parts inventories; however, practices vary considerably based on fleet composition, agency size, operating environment, warehouse capacity, staffing resources, and supplier relationships.

In recent years, transit agencies have experienced increasing challenges associated with extended supplier lead times, supply chain disruptions, parts obsolescence, and limited availability of critical vehicle components. At the same time, agencies are making greater use of maintenance management systems, enterprise resource planning (ERP) systems, inventory management software, vehicle diagnostic data, asset management programs, and other operational data to improve procurement and inventory decision-making.

Although many agencies have developed innovative practices to address these challenges, there has been limited documentation of current industry approaches for managing spare parts inventories, mitigating supply chain risks, identifying critical spare parts, and using data to support procurement decisions. A synthesis would provide transit agencies with a comprehensive understanding of current practices, emerging approaches, and lessons learned across the industry.

OBJECTIVE: The objective of this synthesis is to document current practices used by transit agencies to optimize spare parts procurement, inventory management, supplier lead time risk, and critical spare parts planning. The synthesis should identify how agencies use data, technology, and operational practices to improve parts availability, reduce vehicle downtime, and support reliable transit service.

]]></description>
      <pubDate>Tue, 01 Sep 2026 17:16:59 GMT</pubDate>
      <guid>https://rip.trb.org/View/2772554</guid>
    </item>
    <item>
      <title>Department of Vehicle Regulation Fraud Identification and Mitigation Study</title>
      <link>https://rip.trb.org/View/2768420</link>
      <description><![CDATA[Administrators in the Divisions of Driver Licensing (DDL), Motor Vehicle Licensing (DMVL), and Motor Carriers (DMC) lack sufficient time to research possible forms of fraud. Nevertheless, administrators are aware of various forms of fraud impacting the operations of each division. DDL has contended with the production of illegal driver’s licenses, while DMVL has confronted issues with rebuilt title fraud, use of fraudulent personal IDs to apply for certificates of title, and non-payment of motor vehicle registration fees, along with misused temporary tags and stolen vehicles. DMC has to negotiate challenges associated with International Registration Plan (IRP) credentialing fraud, use of counterfeit International Fuel Tax Agreement (IFTA) decals, and underpayment/non-payment of Kentucky Weight Distance (KYU) taxes. Because these issues present a significant challenge to the Department of Vehicle Regulation (DVR), administrators need timely data-driven insights into the types of fraud occurring in areas over which DVR has statutory or regulatory responsibility.]]></description>
      <pubDate>Wed, 26 Aug 2026 17:04:26 GMT</pubDate>
      <guid>https://rip.trb.org/View/2768420</guid>
    </item>
    <item>
      <title>Micromobility Adoption, Ownership, and Use Patterns in the United States</title>
      <link>https://rip.trb.org/View/2767440</link>
      <description><![CDATA[Micromobility modes—including conventional bicycles, electric bicycles, electric scooters, shared micromobility services, and other emerging personal mobility devices—are becoming increasingly important components of the United States transportation system. These modes offer opportunities to support short-distance travel, improve first- and last-mile access to transit, reduce automobile dependence, and promote healthier and more sustainable travel behavior. Despite growing adoption, there remains limited national evidence regarding who owns and uses micromobility devices, how frequently they are used, the purposes they serve, and the extent to which they substitute for automobile, transit, ridehailing, walking, or other travel modes.

This project aims to provide a comprehensive assessment of micromobility adoption, ownership, and use patterns in the U.S using data from Wave 2 of the Transportation Heartbeat of America (THA) Survey, a nationally representative travel behavior survey of more than 8,000 U.S. adults. The study will examine household ownership and familiarity with a broad range of micromobility devices; characterize utilitarian and recreational use across demographic, household, geographic, and work-arrangement segments; analyze trip characteristics such as distance, duration, timing, and purpose; and investigate mode substitution patterns, safety perceptions, and motivations for use.

The project will employ weighted descriptive analyses, cross-tabulations, and visualization techniques to identify meaningful differences in micromobility ownership and travel behavior across population groups. Findings will provide a comprehensive national characterization of how micromobility modes are integrated into everyday travel and the roles they play in expanding mobility options, supporting first- and last-mile connectivity, and reducing reliance on motorized transportation.
]]></description>
      <pubDate>Wed, 26 Aug 2026 15:49:26 GMT</pubDate>
      <guid>https://rip.trb.org/View/2767440</guid>
    </item>
    <item>
      <title>Fusion Sensor Warning Light/Siren System For Follow Vehicles</title>
      <link>https://rip.trb.org/View/2767346</link>
      <description><![CDATA[Work zones continue to pose a significant safety challenge on the nation's roadways. In 2022 alone, roughly 96,000 work zone crashes nationwide resulted in approximately 37,000 injuries and 891 fatalities. Rear-end collisions accounted for about 21 percent of fatal work zone crashes, and speeding was a contributing factor in roughly 34 percent of them, with commercial motor vehicles involved in a substantial share of these incidents. While work zone fatalities have shown a modest recent decline, overall crash and injury totals remain elevated following a decade of steady increases, underscoring the continued need for effective safety measures for both motorists and roadway workers.

Truck-mounted attenuators are widely used to reduce injury severity when a vehicle strikes a work zone safety truck, absorbing impact energy to protect motorists, workers, and equipment. However, these devices function primarily as passive protection: they mitigate the consequences of a crash but do not prevent one from occurring. Because traditional signage and attenuators still rely heavily on driver awareness and behavior, distracted, speeding, or inattentive drivers can still strike shadow vehicles and active work zones despite these safeguards.

To help close this gap between impact mitigation and crash prevention, Omnisight, Inc. has developed the Fusion Sensor, a system that combines HD radar and video analytics with predictive algorithms to detect approaching road users and assess the likelihood of a collision with a mobile work zone. The system is designed to deliver timely visual and acoustic alerts to both drivers and roadway workers before a potential incursion, shifting work zone safety from passive protection to proactive, real-time intervention. Beyond immediate crash risk reduction, this type of advance warning can also support smoother traffic flow by reducing sudden braking and secondary collisions.

This research is needed to rigorously evaluate and validate the performance of the Fusion Sensor system in reducing work zone incidents, enhancing roadway safety, and minimizing the human and economic impacts associated with work zone crashes, providing the Utah Department of Transportation (UDOT) with an evidence-based understanding of the technology's value before broader deployment decisions are made.]]></description>
      <pubDate>Tue, 25 Aug 2026 12:24:30 GMT</pubDate>
      <guid>https://rip.trb.org/View/2767346</guid>
    </item>
    <item>
      <title> 
Research Experience for Undergraduates (REU): Smart Cities Supplement Summer 2027
</title>
      <link>https://rip.trb.org/View/2762047</link>
      <description><![CDATA[Since 2020, the University of Nevada, Las Vegas (UNLV) has hosted an NSF Research Experiences for Undergraduates (REU) Site on Smart Cities focused on advanced mobility technologies, including Intelligent Transportation Systems (ITS), Connected and Automated Vehicles (CAVs), and vehicle-to-everything (V2X) communication. The program attracts more than 100 applicants annually and has trained over 45 students, producing more than one peer-reviewed publication per summer. This project supplements the existing site to support two additional undergraduate researchers working on Research and Education for Promoting Safety University Transportation Center (REPS UTC) safety-related projects.
The project will recruit two undergraduate students from relevant disciplines (electrical and computer engineering, civil engineering, computer science), with emphasis on outreach to institutions with varied student populations. Selected students will complete a ten-week summer research experience under faculty mentorship across the ITS, CAV, and V2X focus areas, complemented by co-curricular training including weekly cohort meetings, enrichment activities, and cohort-building. Key tasks include developing compelling safety research projects with UNLV mentors, national advertising and recruitment, candidate evaluation and selection, mentored summer research, and final reporting through the UNLV Undergraduate Research Symposium and academic publication venues.
Expected outcomes include expanded undergraduate participation in transportation safety research, student projects aligned with REPS UTC initiatives, student reports, presentations, and potential peer-reviewed publications. The project strengthens the pipeline of future transportation professionals and UNLV's research infrastructure in traffic safety, helping develop the next generation of researchers and practitioners equipped to address emerging safety challenges in transportation systems.
]]></description>
      <pubDate>Wed, 19 Aug 2026 15:59:14 GMT</pubDate>
      <guid>https://rip.trb.org/View/2762047</guid>
    </item>
    <item>
      <title>Tools for Improving Visibility for Snow Plowing</title>
      <link>https://rip.trb.org/View/2762132</link>
      <description><![CDATA[The ability for snowplow operators to see ahead and around their equipment is crucial to the safe and efficient clearing and treatment of roadways during storm events. Under poor visibility, a plow operator may lose situational awareness of their surroundings, which includes other vehicles, the edge or center of the roadway, ditches, curbs, and so forth. Aside from the direct safety impacts on the travelling public in the form of a potential crash, the loss of visibility by plow operators means a need to pay even closer attention to their environment, leading to increased fatigue, stress, etc. Low visibility also increases the likelihood of striking minor objects, such as concrete curbing, leading to the potential for operator injuries to occur, not to mention infrastructure damage.
There is a need for research to investigate the available technologies that can be employed in-vehicle to improve the visibility of the roadway environment for plow operators. As autonomous vehicles become more sophisticated, the technologies they employ to view the roadway are likely transferable to activities like snow plowing. The application of these technologies (i.e., a Global Positioning System [GPS], different types of cameras, other sensors) to snowplows would provide operators with improved visibility of the road ahead. However, until an investigation is made into what technologies are available, their capabilities and costs, what agencies within Minnesota and nationally may be already using them, among other questions, the potential for widespread application of such devices remains largely untapped. The primary benefit of this research will be an understanding of the technologies and products that are available to assist plow operators in seeing the road ahead and the associated costs of those technologies. ]]></description>
      <pubDate>Wed, 19 Aug 2026 15:18:12 GMT</pubDate>
      <guid>https://rip.trb.org/View/2762132</guid>
    </item>
    <item>
      <title>Exploring Role-Based Human-Centered AI Alerts with Novel Wearable Sensors and Multi-Sensory Cues</title>
      <link>https://rip.trb.org/View/2762040</link>
      <description><![CDATA[As vehicles transition between manual control and varying levels of automation in response to roadway, weather, traffic, and system conditions, drivers frequently lack a clear understanding of the vehicle's current capability boundaries, the actions expected of them, and the urgency of required responses. These gaps elevate risk during safety-critical control transitions. This project designs and empirically evaluates role-based, human-centered artificial intelligence (AI) safety alerts delivered through novel wearable sensors (a smart ring and a haptic glove) and in-cabin interfaces (seat vibration, windshield visuals, and odor cues where feasible) to improve alert meaning, driver comprehension, and driving performance.
The research proceeds in two phases using a driving simulator with conditional automation. Phase I employs repeated-measures, counterbalanced design to compare smart ring, glove-based, and seat-vibration cues during standardized, time-limited takeover events, including periods of driver distraction, with urgency manipulated through available lead time. Dependent measures include takeover and response timing, minimum time-to-collision, lane-keeping and speed stability, braking and steering profiles, control smoothness, and subjective ratings of workload, trust, clarity, and comfort. Phase II examines how AI role communication, information framing and tone (neutral, supportive, stern) affect driver understanding, workload, and trust calibration when delivered through multi-sensory interfaces. Mixed-effects models will account for repeated events within drivers.
The project will deliver implemented alert prototypes, empirical evidence on whether wearable sensors provide measurable safety benefits over traditional seat vibration, a validated approach for communicating AI support roles and tone, and design guidance for transparent, higher-meaning driver alerts. Results will support agencies, vehicle manufacturers, and suppliers in refining alert strategies that reduce confusion, improve response quality, and promote appropriate trust calibration during automated driving.
]]></description>
      <pubDate>Wed, 19 Aug 2026 11:47:24 GMT</pubDate>
      <guid>https://rip.trb.org/View/2762040</guid>
    </item>
    <item>
      <title>LIFT: Localization-Informed Flight Trajectories for UAV Resilience against GPS Loss  </title>
      <link>https://rip.trb.org/View/2762044</link>
      <description><![CDATA[Autonomous vehicles—such as autonomous cars and drones—require highly accurate localization to operate safely, yet global positioning system (GPS) alone often cannot provide the needed precision. Furthermore, many real-world applications—such as disaster response—often require localization in GPS-denied environments. Cooperative localization offers a promising alternative to GPS: connected vehicles share information to localize more accurately than any one vehicle can. The accuracy of this localization depends on how they move and the sensing geometry they create. These challenges motivate new approaches that integrate localization, sensing, and planning, which aligns closely with priorities from national agencies—such as the U.S. Department of Transportation—that are exploring sensing-based PNT solutions (link).  The research team proposes Localization-Informed Flight Trajectory (LIFT) planning to enable drone and other autonomous vehicle the ability to achieve precise and reliable localization across diverse environments, from dense urban areas to remote rural regions. This capability will improve resilience against GPS loss, which is particularly a concern in high-latitude locations (such as northern Minnesota) during geomagnetic storms. LIFT leverages sensing-enabled localization, where cooperative autonomous vehicles estimate their position relative to mobile or stationary anchors using sensor measurements (e.g., range and line-of-sight) instead of relying on GPS. Such sensing-based localization is lightweight and power-efficient, but its performance is highly sensitive to the geometric configuration of the autonomous vehicles and the anchors. This vehicle–anchor geometry directly affects localization accuracy, which in turn affects trajectory planning. Conversely, the planned trajectories influence future sensing geometry, creating a closed feedback loop among motion, sensing, and localization. This project develops LIFT, a unified framework that jointly reasoning over localization, sensing, and planning to generate UAV trajectories that maintain high localization accuracy. The team will introduce localization-informed constraints, develop real-time trajectory optimization algorithms, and validate the proposed LIFT framework experimentally in realistic GPS-denied environments. ]]></description>
      <pubDate>Wed, 19 Aug 2026 11:26:11 GMT</pubDate>
      <guid>https://rip.trb.org/View/2762044</guid>
    </item>
    <item>
      <title>Leveraging AI to Improve the Safety of Connected and Automated Vehicles	in Winter Weather	</title>
      <link>https://rip.trb.org/View/2762041</link>
      <description><![CDATA[Connected and automated vehicles (CAVs) are socially important because they have the potential to reduce accidents, expand access to transportation, and improve efficiency. However, broader adoption of CAVs in the Minnesota region is hampered by many challenges. First, winter weather snowfall corrupts sensor data as LiDAR returns become noisier, camera imagery loses contrast, and both modalities suffer from occlusions and missing data. These corruptions lower the reliability of perception modules and introduce uncertainty into all subsequent decision-making stages. Second, cold weather affects battery chemistry, reducing range and increasing charging time, which increases uncertainty for drivers and automated vehicles alike. For instance, during a cold snap in January 2024 in Chicago, charging stations saw long lines of electric CAVs [15], many with dead batteries, exacerbating the range anxiety hampering adoption in cold-weather states. This project investigates the potential of recent artificial intelligence (AI) breakthroughs, such as diffusion models and generative AI, to enhance winter safety and increase the adoption rate of CAVs. To improve safety, the project evaluates the ability of diffusion models, a recent AI advance, to reduce noise in winter-degraded LiDAR, camera, and other sensor data during snowfall. To spur adoption and support the sustainability of CAVs, the project examines the value of AI in improving models for estimating CAV energy use and emissions, extending the range of CAVs, and facilitating eco-routing to help choose routes that reduce energy use and emissions.  ]]></description>
      <pubDate>Wed, 19 Aug 2026 11:03:50 GMT</pubDate>
      <guid>https://rip.trb.org/View/2762041</guid>
    </item>
    <item>
      <title>Active-Inference Control and Sensor-Fusion Simulation for Bicycle Stabilization in Aging Rider Mobility Systems </title>
      <link>https://rip.trb.org/View/2762039</link>
      <description><![CDATA[Low-speed fall events are the leading cause of cycling injuries among older adults, generating 25,000–40,000 annual emergency-department visits and more than $50B in national medical costs. (CDC, 2022; Weiss & Elixhauser, 2012; NCBI, 2012) These incidents primarily occur during mounting, slow riding, deceleration, and stopping—contexts where traditional steering-based stability controls, passive safety devices, and prior gyroscopic concepts fail to prevent loss of balance. 
StaeblTECH has developed a dual–Control-Moment-Gyroscope (CMG) stabilization prototype designed to proactively prevent these falls. Its success depends on a predictive, adaptive control architecture that can learn individual rider characteristics and manage uncertainty. Active Inference (AIF), a unified probabilistic framework for perception, prediction, and action, offers capabilities not available in conventional PID or Model Predictive Control (MPC) systems. (Bagaev & de Vries, 2023) 
This project develops the simulation-based control and sensor-fusion foundation required to integrate AIF into StaeblTECH’s stabilization platform. Leveraging MnRI’s robotics simulation environment, the research team will: (1) build a high-fidelity digital twin of bicycle, rider, and dual-CMG dynamics; (2) implement and tune AIF controllers using message-passing variational inference; (3) integrate IMU, optical-flow, and load-sensor data to evaluate latency, noise sensitivity, and perceptual accuracy; and (4) benchmark AIF performance against PID and MPC baselines using a 7-degree-of-freedom bicycle model. 
All outputs including AIF controllers, sensor-fusion models, stability metrics, and digital-twin datasets directly support StaeblTECH’s NIH Direct-to-Phase II proposal by providing validated simulation results and de-risking subsequent hardware development. This project strengthens Minnesota’s leadership in artificial intelligence (AI)-assisted mobility, addresses a critical aging-transportation challenge, and positions the UMN–StaeblTECH partnership for future federal funding. ]]></description>
      <pubDate>Wed, 19 Aug 2026 10:45:20 GMT</pubDate>
      <guid>https://rip.trb.org/View/2762039</guid>
    </item>
    <item>
      <title>Embedding Human-Understandable Symbolic Rules into Vision-Language Decision Systems for Safe, Transparent, and Ethical Autonomous Driving </title>
      <link>https://rip.trb.org/View/2762038</link>
      <description><![CDATA[In this project, the research team aims to embed human-understandable physical and symbolic rules into the decision-making process of Vision-Language Models (VLMs) for autonomous driving, enabling the model to justify and articulate its decision-making process and consequent driving behavior in real-time. Conventional end-to-end autonomous driving models, i.e., models that learn a direct mapping from raw sensor input (camera, radar, LiDAR) to low-level control commands (steering, throttle, and braking), typically operate as highly complex black-box models. While such models have achieved strong empirical autonomous driving performance, their internal reasoning and decision-making processes are opaque, which makes it difficult for human users to interpret or build trust in the models. Moreover, safety constraints and traffic regulations are often incorporated into these models only as soft constraint penalties during training. As a result, there is no formal guarantee that the probability of generating an unsafe or illegal action is strictly zero at inference. As a result, without an additional safety verification layer, the model may still produce rare but high-risk behaviors, which also may be amplified under distributional shifts or adversarial conditions. ]]></description>
      <pubDate>Wed, 19 Aug 2026 10:42:42 GMT</pubDate>
      <guid>https://rip.trb.org/View/2762038</guid>
    </item>
  </channel>
</rss>