Using Connected Intelligent Transportation To Enhance Vulnerable Road User Safety
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This research addresses the critical safety challenges facing Vulnerable Road Users (VRUs), such as pedestrians and cyclists, in mixed traffic environments containing Autonomous Vehicles (AVs). The study is motivated by the loss of traditional human-to-human communication cues (e.g., eye contact) when interacting with highly automated vehicles, which increases collision risks. The authors identify three fundamental barriers to VRU safety: the lack of high-fidelity experimental platforms for testing interactions, localization failures in Global Navigation Satellite System (GNSS)-denied urban areas, and insufficient trajectory prediction capabilities for heterogeneous agents. To address these barriers, the researchers developed an integrated cooperative system comprising three specific technological components. First, they created "Sky-Drive," a distributed multi-agent simulation platform that utilizes Virtual Reality (VR) and digital twin frameworks to enable human-in-the-loop testing. This system allows for synchronized, cross-terminal interactions between AVs, human-driven vehicles, and VRUs, capturing multi-modal behavioral data including gaze and physiological signals. Second, the team implemented a Cellular Vehicle-to-Everything (C-V2X)-based cooperative localization framework called CV2X-LOCA. This method achieves lane-level positioning accuracy (approximately ±1.5 m) in GNSS-denied environments by leveraging Roadside Units (RSUs) and wireless signal measurements, eliminating the need for expensive onboard sensors on VRUs. Third, they developed a Kinematics-Aware Multigraph Attention Network (KA-MGAT) for trajectory prediction. This model integrates physics-informed learning with deep learning to accurately forecast the motions of diverse traffic agents by accounting for kinematic constraints and complex interaction dynamics. The findings demonstrate that the proposed integrated system effectively overcomes the identified limitations. The Sky-Drive platform provided a safe, immersive environment for reproducing safety-critical scenarios that are difficult to test in the real world. The CV2X-LOCA framework successfully maintained lane-level accuracy in challenging urban environments where traditional GNSS fails, utilizing only C-V2X channel state information. The KA-MGAT model outperformed baseline methods in predicting trajectories for heterogeneous agents, offering physically plausible predictions that capture the distinct motion characteristics of vehicles versus pedestrians. The significance of this work lies in establishing a comprehensive technological foundation for the safe and equitable coexistence of AVs and VRUs. By providing robust tools for simulation, localization, and prediction, the research supports the development of safer autonomous systems and informs transportation agency applications and policy considerations. The outputs, including open-source software and educational materials, aim to facilitate further research and practical deployment of connected intelligent transportation technologies to reduce VRU-related fatalities and injuries.
Key finding
The integrated system combining a VR-based simulation platform, C-V2X cooperative localization, and physics-informed trajectory prediction effectively addresses critical barriers to vulnerable road user safety in automated transportation environments.
Methodology
mixed_methods
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 19 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Methodological Resource: tool software
- Theoretical Contribution: computational model