Periodic Reporting for period 1 - TRACE-V2X (Smart and Proactive Multi-RAT Traffic Steering for V2X)
Okres sprawozdawczy: 2024-01-01 do 2025-12-31
Connected and autonomous vehicles (CAVs) have the potential to provide efficient and sustainable transportation. However, road safety of autonomous driving remains a critical challenge, the lack of which hinders their widespread adoption and integration into the transportation system. It is thus pressing to evolve vehicle-to-everything (V2X) communications to provide reliable and secure communications for CAVs to exchange critical information for cooperative decision-making, ensuring the road safety. This project sets an ambitious goal of designing smart and proactive traffic steering across multiple radio access technologies (multi-RAT) in the environment of CAVs. The technical approach is threefold. First, to ensure the reliability of communications, this project unleashes the full potential of massive sensing that involves the collection of vast amounts of data from sensors deployed on vehicles and roadside infrastructure, and then leverage the cooperation perception of environment for situational awareness and ahead-of-time decision-making in V2X. Second, it develops a security and privacy preservation mechanism to protect the integrity and privacy of the highly dynamic vehicular network as well as defending the widely used machine learning process. Finally, relying on the 5G testbed, Open RAN (O-RAN) solution, and other V2X facilities provided by some partners, the final step is to implement and evaluate the performance of developed solutions, which closes the gap between theory and practice. The planned secondments provide partners the opportunity to test their solutions on the infrastructure possessed by other partners.
The TRACE-V2X project has made significant technical progress in advancing intelligent traffic steering for Vehicle-to-Everything (V2X) ecosystems by integrating wireless communications, machine learning, and advanced algorithm design. Key scientific achievements include the development of an integrated-navigation-and-communication (INAC) network to reduce localization errors, the implementation of radar-assisted compressed sensing for robust channel estimation in dense urban environments, and the creation of proactive multi-RAT traffic steering solutions that reduce communication handovers by up to 63%. Furthermore, the consortium introduced advanced security frameworks, such as path-backtracking trust management and differential privacy schemes to protect user data, while also achieving 100% accuracy in line-of-sight signal identification. These theoretical advancements are supported by the development of an O-RAN compliant testbed platform integrated with mobility simulators and the exploration of Large Language Model (LLM)-enabled edge-AI to enhance autonomous decision-making in complex vehicular traffic loops.
The TRACE-V2X project, an MSCA Staff Exchange initiative coordinated by ENSEA, has successfully established a multi-disciplinary consortium of 11 organizations across Europe and Asia, fostering international collaboration and career development through targeted knowledge transfer and staff secondments. During its first reporting period, the project expanded its network by adding three new partners through proactive grant amendments and mitigation planning to ensure future secondment targets are met. The consortium demonstrates a strong commitment to the MSCA Green Charter by prioritizing digital communication to reduce its environmental footprint and maintains a focus on gender balance and ethical AI standards in its management. Communication efforts have remained robust, utilizing a dedicated web portal and social media to ensure high visibility, while joint supervision and training programs have significantly enhanced the employability and international exposure of the participating research staff.