<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>Algorithms to Convert Basic Safety Messages into Traffic Measures</title>
      <link>https://rip.trb.org/View/2701259</link>
      <description><![CDATA[Connected vehicles rely on short-range messaging using Basic Safety Message (BSM) data that includes information about vehicle size, speed, position, and heading (direction). In the future, all vehicles will be expected to send and receive this information to enhance safety and mobility. Exchange of BSM data among vehicles and traffic management systems will have the potential to generate traffic information that could be used to support current or develop new traffic measures such as travel time, end of queue information for work zones, road weather delay impact, and enhanced traffic signal control. This will be particularly valuable for arterial roadways and work zones in areas without instrumentation or where transportation systems management instrumentation is disrupted by construction. The aim of this research was to develop and validate algorithms that will use BSM data to estimate selected traffic measures that could be used for performance monitoring, traffic control, and traveler information.

]]></description>
      <pubDate>Tue, 12 May 2026 15:54:15 GMT</pubDate>
      <guid>https://rip.trb.org/View/2701259</guid>
    </item>
    <item>
      <title>Game-Theoretical Approach for Cyberattack Modeling and Deep Learning-Based Resilience of Connected Automated Vehicles</title>
      <link>https://rip.trb.org/View/2696944</link>
      <description><![CDATA[The current state of practice in security research on connected automated vehicles (CAVs) does not consider how adversaries may evolve over time and adapt to defense strategies. This proposed research takes the state of practice well beyond the current focus on anomaly detection towards strategic response in defense strategies by developing attack defender models with game-theoretical models. Game theory provides a framework to study the strategic interactions between defenders and adversaries with conflicting objectives. Given the above background, this study will design strategic games to study attacker and defender strategies for cyber deception, as well as algorithms to compute equilibrium or optimal defense strategies in a CAV environment. Real-world data from CAV experiments conducted by PIs will be used to design game theory models in a CAV environment. The study will design two strategic games, namely a zero-sum game and a Stackelberg security game, to formalize the interactions between attackers and defenders by devising a strategic comparison between a zero-sum game and a Stackelberg security game. The proposed game models define payoff functions that capture the trade-offs between model accuracy and the success rates of attacker and defender. The dynamic attacker-defender strategies mimic real-world applications and provide the ability to provide alerts to traffic management center operators for performing cyber incident response in a timely manner, which has attracted the Virginia Department of Transportation’s (VDOT’s) interest. VDOT will serve as a partner to help with real-world implementation. ]]></description>
      <pubDate>Wed, 29 Apr 2026 11:17:14 GMT</pubDate>
      <guid>https://rip.trb.org/View/2696944</guid>
    </item>
    <item>
      <title>Cyberattack Resilience in Cooperative Driving Automation Using Experimental Data and Federated Agents: Phase II</title>
      <link>https://rip.trb.org/View/2696905</link>
      <description><![CDATA[Cooperative driving automation or Connected and Automated Vehicles (CAVs) are rapidly taking over modern intelligent transportation systems. The proliferation of CAVs has also intensified concerns around cybersecurity and data privacy. The added communication involved in these driving maneuvers serves as a vulnerable attack surface. The data communicated in Basic Safety Messages (BSMs) of CAVs is highly safety-critical, thus requires secure processing and sharing. Traditional security strategies are mostly machine learning-based that rely on centralized data processing and storage. The centralized servers act as single-point-of-trust, which is vulnerable to failure, compromising data privacy, and adding overhead to communication. To address these challenges, Federated Learning (FL) has emerged as a distributed learning paradigm that enables CAV agents to locally train models and only share model parameters with a global server for updates. This eliminates the need for raw data sharing, which preserves the privacy of sensitive data transfer during CAV communication and reduces the risk of single-point failure.
Despite the benefits of FL, it is still susceptible to threats like poisoning attacks, inference-based adversaries and model manipulation. The model parameters are not secured while shared iteratively between local and global agents. It is possible for adversaries to deliberately inject anomalies into the local model updates, thereby degrading the accuracy of the global model or compromise the individual local agents. To mitigate this inherent problem of FL, Blockchain serves as the apt solution. Blockchain technology is lightweight, fully decentralized data storage framework that replaces conventional centralized databases by providing immutability and tamper-proofing to the stored data. The Secure Hashing Algorithm (SHA) and smart contracts employed by Blockchains facilitate trust and accountability in this storage solution. This research will integrate blockchain with FL to secure the training data shared between FL’s distributed agents. Due to the distributed nature of both frameworks, they complement each other well and are completely compatible for integration. 
]]></description>
      <pubDate>Tue, 28 Apr 2026 16:15:44 GMT</pubDate>
      <guid>https://rip.trb.org/View/2696905</guid>
    </item>
    <item>
      <title>Context Aware Optimal Information Selection for Reliable, Resilient, Secure, and Efficient
Cooperative Perception</title>
      <link>https://rip.trb.org/View/2676000</link>
      <description><![CDATA[Cooperative perception significantly enhances a vehicle's local field of view by leveraging shared information from nearby vehicles, thus improving overall situational awareness. However, in densely populated environments, cooperative perception can place substantial strain on both communication band-width and computational resources. Such scenarios often result in excessive redundant information, where multiple vehicles repeatedly report the same objects, provide data at unnecessarily high frequencies, or share information irrelevant to the ego vehicle's current context. These issues cumulatively increase computational overhead prior to data fusion and lead to prolonged decision-making times.
Therefore, an effective filtering mechanism is necessary to selectively retain only the most informative objects. Higuchi et al. proposed a value anticipation-based Vehicle-to-Vehicle (V2V) communication approach. In their method, the sender evaluates the potential informational value to receivers and, based on real-time network conditions, either defers or cancels transmissions. This ensures that primarily essential information is disseminated to neighboring vehicles. In another related study, Zhou et al. introduced the Augmented Informative Cooperative Perception (AICP) algorithm, which incorporates both a routing mechanism and message filtering at the receiver side. Their algorithm utilizes an informative-ness measure to assess and select messages, optimizing resource use while ensuring relevant data is received.

While redundant messaging is typically seen as a problem due to its computational demands, it can also provide significant benefits in enhancing security within V2X communications. Specifically, redundancy can enhance detection of malicious behavior through corroborative data from trustworthy vehicles, thereby improving the security of V2X communications. Lie et al. proposed Misbehavior Detection for Collective Perception Services in Vehicular Communications (MISO-V), which leverages redundancy from received V2X messages to validate incoming perception information. Upon verifying a new message against redundant data, the receiver updates the sender’s trust score based on whether the information is classified as benign or potentially malicious. This updated trust score subsequently guides down-stream tasks in determining whether to integrate or discard information provided by that sender.

Balancing redundancy is thus crucial - maintaining an optimal level of redundancy can simultaneously enhance security and sustain computational efficiency. A suitable approach involves dynamically adjusting redundancy based on multiple factors, including source reliability (assessed via trust mechanisms), the planned route of the ego vehicle, prevailing network conditions, and the Age of Information (AoI). This strategy ensures that cooperative perception remains robust, secure, and scalable, supporting accurate and timely decision-making within cooperative vehicle networks.

The aim is to establish a balance between purposeful and efficient redundancy and safety against potential attack scenarios, optimizing the use of communicated data and the reliability of data fusion necessary for downstream tasks such as planning and control. The research team will explore information redundancy, perception inconsistencies, context aware fusion, spoofing and other attack scenarios, and the detection of attack patterns and will employ optimization strategies and reinforcement learning techniques. The focus will include intersection scenarios with varying traffic densities and connectivity levels. In addition to using the VeReMi dataset, the team will explore extensions to more realistic collaborative perception message attach scenarios for evaluation and validation.
]]></description>
      <pubDate>Mon, 02 Mar 2026 19:08:48 GMT</pubDate>
      <guid>https://rip.trb.org/View/2676000</guid>
    </item>
    <item>
      <title>Enabling Mobility of Emergency Medical Service through Connected and Automated Vehicle Preemption</title>
      <link>https://rip.trb.org/View/2669655</link>
      <description><![CDATA[Emergency Medical Service (EMS) vehicles, typically ambulances, have time-critical transportation roles when responding to traffic incidents by bringing first medical responders and equipment from their bases to the incident scenes, and transferring injured persons from the scenes to medical facilities. Addressing the mobility of EMS vehicles supports but public health and safety goals, as well as those related to efficient mobility.     

The traditional way for EMS vehicles to reach their destinations faster is to use audible sirens to alert drivers of their presence. Upon hearing an EMS vehicle’s siren, drivers must yield the right of way to facilitate its passage. Previous research on traffic signal preemption for EMS vehicles has demonstrated its effectiveness in reducing delays at signalized intersections. With the advent of Connected and Automated Vehicle (CAV) technology, vehicles can now communicate directly with each other. EMS vehicles equipped as CAVs could leverage vehicle-to-vehicle (V2V) communication technology to transmit warning messages to the CAVs downstream along their routes, beyond the range of audible sirens. The CAVs that have received these messages can proactively move aside to create a clear lane for the EMS vehicle to pass. This “CAV preemption” concept has the potential to significantly improve EMS mobility, resulting in faster response times, earlier on-scene medical aid, and quicker patient transfer to hospitals. Furthermore, the proposed CAV preemption will accelerate incident clearance and the restoration of highway capacity.  

This research is based on an envisioned CAV preemption system in which an EMS vehicle broadcasts its impending arrival to downstream CAVs, while simultaneously sounding its siren and emitting high-intensity strobe light to request signal preemptions. All CAVs receiving this V2V message will automatically move to the right lane, while only a portion of the non-CAV drivers will comply and respond to the siren. The efficiency of this system depends the following factors: (1) The broadcast range of the warning messages to CAVs, (2) The market penetration rate of CAVs, (3) The move-aside compliance rate of non-CAV drivers, (4) The level of traffic congestion.  

This research will simulate and quantify the efficiency of the proposed CAV preemption system under varying operating conditions. An agent-based simulation model of the El Paso highway network will be used to assess the EMS vehicle’s travel time. Mobility efficiency is defined as the percentage reduction in the average travel time. The travel times of EMS vehicles from their bases (selected fire stations that house ambulances) to multiple incident sites (selected highway locations) will be simulated, extracted, and analyzed. The analyses will assess the impacts of broadcast range, CAV market penetration, non-CAV compliance rate, and traffic volume.   ]]></description>
      <pubDate>Sun, 15 Feb 2026 16:34:35 GMT</pubDate>
      <guid>https://rip.trb.org/View/2669655</guid>
    </item>
    <item>
      <title>Cyberattack Resilience in Cooperative Driving Automation Using Experimental Data and Federated Agents </title>
      <link>https://rip.trb.org/View/2531078</link>
      <description><![CDATA[Cooperative Driving Automation (CDA) or vehicles that are connected and automated can potentially transform the transportation system. CDA continuously communicates with their surrounding vehicles (V2V). These technologies can potentially help relieve congestion and improve roadway efficiency and safety in the near future. However, the wider use of communications and wireless networks in CDA and transportation operations and management systems has made these systems vulnerable to the risk of cyberattacks. These systems rely on the Internet of Things (IoT), and connectivity and provide wider accessibility. The XML messages used by the National Transportation Communication for Intelligent Transportation Systems (ITS) Protocol (NTCIP) are considered to have relatively small intrusions that are initiated by hackers and, thus, have no built-in security. The USDOT has also initiated a credential management system for security (SCMS) of vehicle and infrastructure-based communication. However, the increased dependency on communication provides hackers with multiple access points, making them vulnerable to cyberattacks and are the least understood in terms of cybersecurity.

Thus, it is imperative to assess the cyber risks of these systems and design efficient and effective anomaly detection methods so that anomalous behavior in CDA can be detected in real time and these systems can perform resiliently under cyberattacks. Past research has used CAN bus data from normal human-driven vehicles to develop anomaly detection algorithms using machine learning without accounting for the temporal dependencies between anomalous trajectories, and the influence of compromise on leaders or followers within a platoon has also not been considered.
]]></description>
      <pubDate>Mon, 31 Mar 2025 16:58:16 GMT</pubDate>
      <guid>https://rip.trb.org/View/2531078</guid>
    </item>
    <item>
      <title>Development of a Generalized Integrity Monitoring Framework For CAV Application</title>
      <link>https://rip.trb.org/View/2444697</link>
      <description><![CDATA[CAV applications can be broadly classified into three major categories: safety, mobility, and environmental. Mobility and environmental applications require a coarse positioning accuracy (5-10 m) and lane-level positioning accuracy (< 1 m), while safety-critical applications require a where-in-lane level accuracy (< 0.2 m). Uncertainty in positioning information can sabotage driving functionalities and cause a safety concern. Position uncertainty of a vehicle can be attributed to the sensor suite available on the vehicle, along with any additional external sensor information that may aid the in-vehicle sensors. Furthermore, a fully connected and Automated vehicle (CAV) may turn itself into a degraded CAV, AV-only, CV-only, or Human-driven vehicle (HDV) while experiencing communication or control loss. The type, quantity, placement, and measurement uncertainty of sensors play a great role in determining the navigation performance of a vehicle. Additionally, in a mixed traffic scenario, there exist various types of positioning solutions, vehicles, sensor modalities, communications capabilities, and applications. It is unlikely that two vehicles having the same set of sensors and computation hardware will output similar navigation performance. Therefore, it is important to study and analyze the integrity of positioning systems under various conditions. 

Integrity monitoring (IM) methods have been extensively studied and developed for in-vehicle sensor systems primarily consisting of GNSS receivers (e.g. RAIM) often integrated with IMUs, vehicle odometry, and perception sensors such as radar, camera, and LiDAR. The localization performance and safety of a vehicle have mainly been studied from an ego vehicle's perspective focusing on enabling automated driving functions through onboard sensors and compute platform. Further, there is a surge in V2V/V2I/V2P/V2X research focusing on information sharing between road agents for improved positioning, navigation, and control. Given the number of sensor sources and the amount of data shared between road agents, it is imperative to develop integrity monitoring frameworks for cooperative scenarios. Based on the research team's initial literature survey, despite the growing interest in this area, there is a noticeable gap in the current literature that addresses the "cooperative-IM (integrity monitoring)" framework, indicating the need for further research to propose new Required Navigation Performance (RNP) parameters that may support CAV applications.  

As a part of the research team's smart intersection projects (City of Riverside & City of Rialto), it has conducted various Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) based cooperative positioning experiments, where perception data from both onboard and roadside sensors i.e. camera, LiDAR, is shared among the vehicles and infrastructure through C-V2X communication. The research team has successfully demonstrated improved vehicle detection and positioning accuracy (0.3 meters with Roadside LiDAR). Furthermore, the research team is currently experimenting with Cohda wireless MK6 modules to transmit basic safety messages (BSMs) and other information among vehicles in a V2V setting. However, the question remains whether the empirically determined Required Navigation Performance (RNP) values hold consistent across different driving conditions, positioning hardware, and communication topologies. Inconsistencies in RNP parameters would lead to the failure of CAV applications. ]]></description>
      <pubDate>Tue, 22 Oct 2024 16:21:00 GMT</pubDate>
      <guid>https://rip.trb.org/View/2444697</guid>
    </item>
    <item>
      <title>Examining and Enhancing Vehicle Spoofing Detection Capabilities in CAV Applications: Real-World Testing </title>
      <link>https://rip.trb.org/View/2444698</link>
      <description><![CDATA[This project addresses the rising incidence of GNSS spoofing attacks by enhancing detection capabilities in Connected and Autonomous Vehicles (CAVs). The focus is on leveraging information shared by surrounding vehicles and signals of opportunity to identify jamming and spoofing threats during vehicle-to-vehicle maneuvers. Conducted in collaboration with the CARNATIONS team at Illinois Tech and StarNav, the project explores detection strategies using real-world spoofing data and onboard sensors such as LiDAR and cameras.

The research is divided into two tasks: (1) detecting GNSS meaconing, which involves analyzing the impact of signal retransmission delays on non-target vehicles and identifying key detection information, such as timing and signal direction, and (2) detecting targeted GNSS spoofing attacks, particularly in scenarios where the lead vehicle of a platoon is compromised, focusing on the detection and mitigation of manipulated satellite data.

The team will develop a layered defense strategy, implementing detection systems through hardware-in-the-loop simulations and real-world testing to explore vehicle re-localization during attacks. This research aligns with the U.S. Department of Transportation’s priority of enhancing transportation system safety and resilience by countering GNSS spoofing threats in CAV applications, particularly in highway platooning.]]></description>
      <pubDate>Tue, 22 Oct 2024 16:11:46 GMT</pubDate>
      <guid>https://rip.trb.org/View/2444698</guid>
    </item>
    <item>
      <title>Resilient V2X Communication for Cooperative and Remote Driving </title>
      <link>https://rip.trb.org/View/2444700</link>
      <description><![CDATA[This project focuses on developing a Global Navigation Satellite System (GNSS) spoofing detection and mitigation system for Connected and Autonomous Vehicles (CAVs) by leveraging information shared between vehicles and other signals of opportunity. The main goal is to detect jamming and spoofing attacks, particularly in vehicle-to-vehicle scenarios where cooperative operations are targeted. In collaboration with Illinois Tech's CARNATIONS team and StarNav, the project will utilize real-world data and onboard sensors such as LiDAR and cameras to enhance detection capabilities.

The research is structured into two tasks: (1) detecting GNSS meaconing, where attackers retransmit GNSS signals with a delay, misleading vehicles about their position and timing, and (2) identifying and mitigating targeted GNSS spoofing attacks, where attackers aim to control the navigation system of a lead vehicle in a platoon. These tasks will involve analyzing the spoofing effects on non-target vehicles and determining key detection information, such as signal arrival time and direction.

The detection system will be incrementally developed through hardware-in-the-loop simulations and real-world data analysis, exploring the potential for re-localization of affected vehicles during spoofing attacks. The project aligns with U.S. Department of Transportation priorities by enhancing transportation safety and resilience, particularly in highway platooning scenarios. The outcome will be a robust CAV application that remains resilient against GNSS spoofing threats.






]]></description>
      <pubDate>Tue, 22 Oct 2024 16:08:44 GMT</pubDate>
      <guid>https://rip.trb.org/View/2444700</guid>
    </item>
    <item>
      <title>Cooperative Sensing of Vulnerable Road Users and Real-time Response to Potential Collisions via Connected Vehicle and Infrastructure Communication</title>
      <link>https://rip.trb.org/View/2440028</link>
      <description><![CDATA[Intersection safety is critical for all traffic participants, but especially for vulnerable road users (VRU) such as pedestrians and cyclists. Recent autonomous driving advances allow mitigation of several human driver risk factors, such as fatigue and recklessness. However, state-of-the-art autonomous driving technology also has limitations. An individual vehicle’s perceptual field-of-view can be compromised by nearby occluding objects, greatly reducing detection accuracy, and distant objects can be difficult to detect. Limitations in detection accuracy introduce further challenges in the downstream tasks of object tracking, trajectory prediction, and motion planning. In this project, the research team develops techniques for cooperative sensing at intersections to address these challenges and enable more effective identification of potential collisions involving VRUs and then combine them with novel CAV collision-mitigating actions to improve VRU safety.

Cooperative sensing: Building on recent research in cooperative object recognition by multiple connected autonomous vehicles (CAVs) near an intersection, the team will develop extended techniques for tracking and predicting the trajectories of travelers. The team will first evaluate different approaches to reconciling shared feature maps (specifically the use of distributed Kalman filtering methods versus newer transformer-based approaches) to determine a baseline object tracking procedure. Second, the team will consider the tracking performance benefit of either additionally incorporating information from fixed-position camera/lidar sensors at the intersection (e.g., as would be possible at signalized intersections that use such sensors to support adaptive traffic signal control systems) or substituting them for CAV sensing altogether. Finally, the team will adapt and apply these results, which traditionally assume vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication and focus on accurate sensing of vehicles, to the sensing of VRUs. The team will use available traffic data to evaluate their initial technology results and use their East Liberty Surtrac/PedPal testbed site to test live VRU detection.

Collision mitigation: To enable safe response to projected collisions with sensed VRU, the project will also investigate CAV strategies for taking evasive action. Recently deep reinforcement learning (DRL) has successfully dealt with autonomous driving tasks. The team aims to use DRL to train an agent across various intersection scenarios with human-like reactive agents to learn to decode social maneuvers from the past observed trajectories of the surrounding road users and execute a safe strategy for crossing the intersection. The developed algorithms will be tested on CommonRoad scenarios with reactive agents trained on a wide range of human behaviors. 

The proposed work will use state-dropout-based curriculum RL with Control Barrier Functions (CBF) to react in cases wherein the ego vehicle comes close to collision with other road users. This allows the ego agent to receive the CBF’s initial help to learn how to react safely, and then as the agent learns, lift the CBF constraints in order to cross intersections faster without compromising on safety. The proposed approach is coupled with existing state-dropout-based curriculum RL where future states of the ego agent are initially available as privileged information to ease learning for the RL agent but are subsequently removed so the RL agent can efficiently cross the intersection.
]]></description>
      <pubDate>Sun, 13 Oct 2024 10:46:32 GMT</pubDate>
      <guid>https://rip.trb.org/View/2440028</guid>
    </item>
    <item>
      <title>Intersection Control of Connected Vehicles for Mobility and Safety
</title>
      <link>https://rip.trb.org/View/2422815</link>
      <description><![CDATA[Intersection control is currently done using traffic lights which are timed based on limited
sensor data generated by inductor loops located under the lane surface near the intersection. The traffic lights have limited information regarding the size of the queue and demand in either direction. This limited information makes it difficult to come up with accurate measurements of demand and design the traffic light cycles to optimize mobility. Currently available sensors such as vision and radar which can provide additional and more accurate information are costly to install and maintain and the infrastructure simply does not have the additional funds to carry out such significant changes on a big scale. On the other hand, car manufacturers have been producing vehicles with the latest in sensor technology and have capabilities that if used properly in a cyber based system can replace traffic lights by creating a connected and highly coordinated environment based on software and intelligence. The purpose of this project is to develop an intersection control system where vehicles approaching the intersection will be assigned paths and speed trajectories so that no two vehicles will be put in a colliding path. It is assumed that vehicles can communicate their location, speed, dynamical characteristics, and direction of travel to a virtual central coordinator which will issue them instructions to cross (green to proceed) following a reserved path at a certain desired speed based on certain protocols. The vehicles are expected to follow the instructions of the coordinator and use their on-board sensors to cross the intersection safely in case unexpected obstacles are in their way providing another layer of safety. The proposed system takes advantage of the current technologies that are already in most vehicles to create a connecting environment where vehicles can communicate with a central coordinator and possibly with other vehicles to improve mobility and enhance safety. The importance of the approach if successful is that hardware and physical elements such as traffic lights and inductor loops will be replaced with software and intelligence in a cyber space Intersection Control of Connected Vehicles for Mobility and Safety which is much easier to maintain and at a much lower cost. In addition, there is a strong potential for significant improvements in mobility as proper dynamic routing based on demand from each vehicle or group of vehicles will eliminate some of the deficiencies and dead periods where vehicles are waiting for green when no vehicles are crossing from the other direction. Safety is also expected to improve by having two layers of safety, one on the infrastructure coordination level and one on the vehicle level using its own on-board sensors and collision avoidance systems to confirm that the path assigned by the coordinator is safe to follow. In this project the study team plans to design a traffic light-free intersection controller and quantify its benefits with respect to mobility and safety by comparing it with current traffic lights. In addition, the study team will examine the evolution of such a highly coordinated system as it transitions from current situation where some vehicles will participate in the coordination, and some will not as they may not have the adequate technologies. In such an environment the integration of the current traffic lights with the proposed central coordinator will be investigated. The expected outcomes of the project are the design and evaluation of a virtual environment for controlling traffic at intersections by replacing current traffic lights and expensive hardware which is costly to buy and maintain with less costly software and intelligence by taking advantage of current and upcoming technologies on vehicles.]]></description>
      <pubDate>Tue, 27 Aug 2024 17:34:29 GMT</pubDate>
      <guid>https://rip.trb.org/View/2422815</guid>
    </item>
    <item>
      <title>Comprehensive Testing and Evaluation of Resilient PNT Systems</title>
      <link>https://rip.trb.org/View/2329760</link>
      <description><![CDATA[This project aims at testing the anti-jamming and anti-spoofing concepts, systems, and methods developed by CARNATIONS. The challenge with such experimentation is that open-sky broadcasting of radio-frequency (RF) signals at Global Navigation Satellite System (GNSS) frequencies is illegal, even for research purposes. In this project, the research team will (1) leverage existing test facilities at their academic institutions, (2) perform testing during opportunistic jamming events and during government-organized experimentations, and (3) develop new anti-interference testing capabilities.

(1) To the extent possible, the research team will conduct field testing at the Virginia Tech Transportation Institute (VTTI), the University of California Riverside (UCR)’s Innovation Corridor, and the Illinois Tech (IIT) State Street Transect. The Virginia Smart Roads includes a 2.7-mile long highway section, a roadway connector for transitions to live traffic, the “Rural Roadway”, and a modular “Surface Street” area. VTTI has a fleet of highly automated vehicles, equipped with multiple sensors and V2X communication systems. UCR’s Innovation Corridor is available for testing in live traffic. Illinois Tech has created a full GNSS and LiDAR map of a 6-mile-long transect of State Street in Chicago, IL. The density of transportation systems provides a complex framework in which to investigate navigation performance for various transportation scenarios.

The research team will use the VTTI vehicle platforms to test the resilient positioning navigation and timing (R-PNT) solutions developed by CARNATIONS. The research team will use the Smart Roads to test and evaluate the connected PNT defenses. At UCR’s Innovation Corridor, the research team will investigate ways to limit attacks to a connected vehicle fleet by generating surrogate, simulated PNT jamming and spoofing without broadcasting at protected frequencies. The research team performs similar research at IIT’s State Street transect in an urban area after having carefully monitored State Street’s RF environment.

(2) The research team have developed and tested a method to predict live jamming alongside highways. They analyzed months of RF data over hundreds of sites near highways where they routinely observe jammers from personal privacy devices (PPDs). PPDs are employed by road users to disable GPS trackers. Jamming tends to coincide with truck delivery schedules. The research team will use these predictable events to test RFI detectors and localizers.

Field tests with RFI are desirable, and the research team will continue to utilize opportunities with partners in the Department of Defense (DOD), such as Edwards Air Force Base (AFB), and the Department of Homeland Security (DHS), such as the GPS Testing for Critical Infrastructure (GET-CI), when available. The research team attended DHS’ 2017 and 2021 GET-CI.

(3) The VTTI Rural Roadway is located in an isolated valley surrounded by hundreds of acres of forest and overlooked by a bridge – an ideal location for contained radio-frequency (RF) emissions with limited collateral interference using directional, downward-pointing antennas. The research team will explore partnerships with the Federal Communications Commission (FCC) and other competent authorities to research whether creation of such a unique RF interference (RFI) testbed at VTTI is possible.]]></description>
      <pubDate>Wed, 31 Jan 2024 16:04:01 GMT</pubDate>
      <guid>https://rip.trb.org/View/2329760</guid>
    </item>
    <item>
      <title>Towards Resilient V2X Communications over 5G/6G Networks: Sensing and Cooperative Perception</title>
      <link>https://rip.trb.org/View/2329756</link>
      <description><![CDATA[Enabling mission critical communication for vehicular networks can be achieved by exploiting 5G and 6G wireless systems. However, given that such systems are primarily designed with high rate services in mind (e.g., multimedia), ensuring continuous availability of the communication link for V2X communication is a major challenge.

The goal of the first year of this project is to explore the use of resilience as a metric for guaranteeing the operation of V2X links under different dynamics of the environment. This will create a seed for the next year of this project that can exploit the developed fundamentals to investigate other avenues like integrated sensing and communications.

(1) Resilient Communications Fundamentals: 5G and 6G networks may rely on high-frequency bands to provide high-speed wireless access for V2X. High-frequency bands can potentially be intermittent due to factors such as blockage and fading. This susceptibility to signal blockage and low signal-to-interference ratio is also a challenge at low frequency bands. While 3GPP has advocated for providing ultra-reliable wireless communications for 5G mission-critical systems, this design, centered on reliability – which requires continuous availability of a communication link – has proven to be difficult to achieve in the real world due to the challenges of the wireless channel. In contrast, it may be more apropos to design resilient communication links that can quickly recover from failures (unintentional or intentional). This includes failures due to cybersecurity breaches. Despite significant research in this space in fields such as cyber-physical systems, to date, the very definition of resilience in cellular networks, in general, and V2X networks, in particular remains ambiguous.

In this research task, the research team will explore for the first time the fundamentals of resilience for wireless networks, in general, and connected autonomy systems (V2X or drones), in particular. The research team will develop new metrics for resilience and analyze the performance achievable by a wireless systems in terms of those new metrics, while contrasting them to classical standardization metrics like reliability.

(2) Optimization of resilience in V2X systems: Once metrics are defined, the next step is to optimize the overall operation of the system to enhance resilience under various intentional and non-intentional failures, including cybersecurity threats like jamming. In particular, the goal here will be to study how to design the cross-layer communication mechanisms, from beamforming to network resource management in a way to meet the resilience needs of V2X systems, as quantified in the first task. This task will potentially explore machine learning (ML) techniques to deal with complex optimization problems, and to ensure adaptation of the system to large-scale dynamics.]]></description>
      <pubDate>Wed, 31 Jan 2024 15:11:16 GMT</pubDate>
      <guid>https://rip.trb.org/View/2329756</guid>
    </item>
    <item>
      <title>Generating High-Accuracy Transportation Datasets with Unmanned Aerial Vehicles</title>
      <link>https://rip.trb.org/View/2326637</link>
      <description><![CDATA[A new trend in the area of connected and automated vehicles (CAVs) is infrastructure-based sensing and tracking. By installing roadside cameras at the infrastructure, one can monitor the overall traffic situation and, after processing the collected data via edge computing, the information can be shared with CAVs via V2X connectivity. This has a huge potential to improve traffic safety and efficiency. The study team identifies two main challenges to deploy such systems: (i) to obtain high precision data and (ii) to label the obtained data. It is necessary to have sufficient high-precision labelled datasets for training the underlying machine learning (ML) algorithms to detect, identify, localize and track the road participants. In other words, one needs to know the “ground truth” (with high precision) for large variety of different scenarios. As of now, this may be done by hand-labeling images, which is immensely labor intensive, or by using probe vehicles equipped with high precision GPS, which can only provide data about a few specific vehicles.]]></description>
      <pubDate>Fri, 26 Jan 2024 16:45:04 GMT</pubDate>
      <guid>https://rip.trb.org/View/2326637</guid>
    </item>
    <item>
      <title>5G-enabled Safe and Robust Deep Multi-agent Reinforcement Learning Framework for CAV Coordination</title>
      <link>https://rip.trb.org/View/2321726</link>
      <description><![CDATA[We address the problem of coordination and control of Connected and Automated Vehicles (CAVs) in the presence of imperfect observations in mixed traffic environment. A commonly used approach is learning-based decision-making, such as reinforcement learning (RL). However, most existing safe RL methods suffer from two limitations: (i) they assume accurate state information, and (ii) safety is generally defined over the expectation of the trajectories. It remains challenging to design optimal coordination between multi-agents while ensuring hard safety constraints under system state uncertainties (e.g., those that arise from noisy sensor measurements, communication, or state estimation methods) at every time step. We propose a safety guaranteed hierarchical coordination and control scheme called Safe-RMM to address the challenge. Specifically, the high-level coordination policy of CAVs in mixed traffic environment is trained by the Robust Multi-Agent Proximal Policy Optimization (RMAPPO) method. Though trained without uncertainty, our method leverages a worst-case Q network to ensure the model's robust performances when state uncertainties are present during testing. The low-level controller is implemented using model predictive control (MPC) with robust Control Barrier Functions (CBFs) to guarantee safety through their forward invariance property. We compare our method with baselines in different road networks in the CARLA simulator. Results show that our method provides the best evaluated safety and efficiency in challenging mixed traffic environments with uncertainties.]]></description>
      <pubDate>Tue, 16 Jan 2024 12:08:44 GMT</pubDate>
      <guid>https://rip.trb.org/View/2321726</guid>
    </item>
  </channel>
</rss>