<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Research in Progress (RIP)</title>
    <link>https://rip.trb.org/</link>
    <atom:link href="https://rip.trb.org/Record/RSS?s=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" rel="self" type="application/rss+xml" />
    <description></description>
    <language>en-us</language>
    <copyright>Copyright © 2026. National Academy of Sciences. All rights reserved.</copyright>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <managingEditor>tris-trb@nas.edu (Bill McLeod)</managingEditor>
    <webMaster>tris-trb@nas.edu (Bill McLeod)</webMaster>
    <image>
      <title>Research in Progress (RIP)</title>
      <url>https://rip.trb.org/Images/PageHeader-wTitle-RIP.jpg</url>
      <link>https://rip.trb.org/</link>
    </image>
    <item>
      <title>Research Project Name: Development of a CAV Testbed-enhanced Smart Campus at Morgan State University - Phase III</title>
      <link>https://rip.trb.org/View/2606401</link>
      <description><![CDATA[This research advances Connected and Automated Vehicle (CAV) infrastructure through Phase III expansion of an established testbed, integrating LiDAR-powered safety applications with signal control systems and conducting comprehensive CAV market penetration analysis in partnership with Maryland Department of Transportation. Building on previous phases, the study coordinates signal phasing and timing across three campus intersections equipped with LiDAR and roadside unit infrastructure, implementing dynamic all-red extensions based on vehicle speed and red-light violation risk detection. The methodology develops pedestrian signal extensions activated by real-time crosswalk occupancy detection and creates Safety Data Sharing Messages compliant with SAE J2735 standards for broadcasting object-level data to vehicles. Portable LiDAR deployments collect trajectory data at additional intersections and work zones for solution validation. The market penetration analysis component catalogues CAV data sources, develops quality assurance frameworks, and compares traditional probe data with connected vehicle information. Collaboration with Maryland Motor Vehicle Administration provides vehicle registration cross-referencing with automation levels, while commercial vendor partnerships supply dynamic usage patterns. The research creates geographic information system (GIS)-based visualizations representing regional CAV penetration and develops interactive dashboards for transportation planning support.]]></description>
      <pubDate>Thu, 02 Oct 2025 14:53:58 GMT</pubDate>
      <guid>https://rip.trb.org/View/2606401</guid>
    </item>
    <item>
      <title>Enhancing Road Safety Through Video Analytics and Connected and Automated Vehicles (CAV)</title>
      <link>https://rip.trb.org/View/2562267</link>
      <description><![CDATA[This project develops and demonstrates an end-to-end prototype that integrates roadside video analytics with connected vehicle (CV) technology to enable real-time safety warnings for drivers. Building upon the MSight roadside perception platform, the system detects, tracks, and predicts vehicle and vulnerable road users (VRU) trajectories using infrastructure-mounted cameras, then transmits safety-critical information to vehicles via C-V2X communication. A vehicle-side onboard application processes received messages and delivered timely, intuitive warnings to drivers. Rather than focusing on productization alone, the work uses a prototype-and-field-test approach at Mcity to quantify current technical performance, identify key technology gaps and integration barriers (e.g., detection reliability for VRUs, end-to-end latency, communication constraints, and driver warning usability), and translate findings into prioritized, actionable recommendations. The outcome is a practical assessment of what today’s video analytics + V2X stack can and cannot deliver, and a roadmap of high-impact next steps for DOTs to advance toward deployable, scalable crash-prevention applications.]]></description>
      <pubDate>Fri, 06 Jun 2025 14:55:37 GMT</pubDate>
      <guid>https://rip.trb.org/View/2562267</guid>
    </item>
    <item>
      <title>Investigation of Emerging Sensing and AI/ML Technologies to Enhance the Safety of Vulnerable Roadway Users at Signalized Intersection</title>
      <link>https://rip.trb.org/View/2553153</link>
      <description><![CDATA[Accurately identifying and analyzing vulnerable roadway users (VRUs) such as pedestrians, bicyclists, and other non-vehicle occupants, are a crucial yet difficult undertaking. VRUs’ behavior is influenced by localized factors such as land use, and their movements are not confined to predefined paths. This study will investigate the use of emerging technologies such as LiDAR, network cameras, and artificial intelligence/machine learning (AI/ML) algorithms to capture the movements and behaviors of vulnerable road users (VRUs). By evaluating pedestrian demand, including the volume and characteristics of pedestrian traffic, this research aims to assess and improve the safety of intersections.
This project will start with a comprehensive study of the state-of-the-art methods of VRU data collection, image- and LiDAR-based VRU object detection and classification, and dynamic VRU trajectory estimation methods. Next, a candidate study intersection will be reviewed and selected for the sensor installation and data collection. The LiDARs and Cameras will be synchronized with the field processing unit and the retrieved data will be transferred and saved to be further analyzed. 
In the model development process, three traffic data collection framework will be designed: a roadside LiDAR-based VRU data collection, video-based VRU data collection, and an integrated framework.
]]></description>
      <pubDate>Tue, 13 May 2025 19:09:57 GMT</pubDate>
      <guid>https://rip.trb.org/View/2553153</guid>
    </item>
    <item>
      <title>Secure and Robust Machine Learning for Autonomous Driving Systems</title>
      <link>https://rip.trb.org/View/2529891</link>
      <description><![CDATA[As autonomous driving systems (ADS) become increasingly prevalent in modern transportation, critical concerns have emerged regarding their security vulnerabilities and performance inconsistency, particularly in pedestrian detection and natural language processing components. Current machine learning technologies, while effective, can introduce variability where the model performance remains uniform across different scenarios and is susceptible to security attacks that may compromise both safety and robustness. This research aims to enhance the security and robustness of autonomous driving systems through a comprehensive investigation of vulnerabilities and the development of novel protective strategies. The project will focus on identifying and analyzing security and robustness vulnerabilities in ADS, developing novel strategies to promote robustness and enhance security in pedestrian detection systems, improving robustness in automotive large language models, and implementing prototype systems for real-world evaluation. The research methodology encompasses four integrated tasks. First, the research team will develop a novel consistency poisoning attack framework to assess system vulnerabilities. Second, the research team will analyze and mitigate consistency vulnerabilities in pedestrian detection systems through advanced machine-learning techniques. Third, the research team will enhance consistency in Large Language Models through innovative prompt engineering and model fine-tuning. Finally, the research team will implement prototype systems and conduct comprehensive evaluations using real-world datasets to validate its th  approaches.
This project directly aligns with the key priorities of the U.S. Department of Transportation (USDOT). First, it supports the Safety strategic goal by developing robust defenses against security and consistency attacks in autonomous vehicles, particularly focusing on protecting vulnerable road users through enhanced pedestrian detection systems. Secondly, the research advances the Department's Cybersecurity priority by addressing AI vulnerability in autonomous systems that could impact various communities. The outcomes of robust and consistent machine learning directly support the USDOT commitment to promoting transportation safety and ensuring that emerging technologies benefit all Americans. In summary, the project's comprehensive approach to addressing both technical and societal challenges in autonomous driving systems demonstrates strong alignment with the USDOT vision for safe and sustainable transportation innovation.]]></description>
      <pubDate>Thu, 27 Mar 2025 15:28:42 GMT</pubDate>
      <guid>https://rip.trb.org/View/2529891</guid>
    </item>
  </channel>
</rss>