Roadside LiDAR for Cooperative Safety Auditing at Urban Intersections: Toward Auditable V2X Infrastructure Intelligence

2026-04-11

AI Summary

This work addresses the limitations of单车智能 in urban intersections, where occlusions and perceptual blind spots hinder comprehensive safety risk assessment and lack infrastructure-level auditability. The study proposes the first roadside LiDAR–based safety auditing framework, integrating trajectory reconstruction, human-in-the-loop iterative quality control, and direction-agnostic time-to-collision (TTC) analysis. This approach effectively mitigates failure modes such as trajectory fragmentation and uncovers conflict mechanisms predominantly driven by lateral intrusions. Validated at a real-world intersection in New York City, the framework successfully identifies high-risk events—such as those between heavy vehicles and bicycles—with TTC under one second, significantly reducing false triggers and trajectory breaks. It thereby delivers a scalable and interpretable post-hoc safety auditing capability for V2X cooperative perception systems.

Technology Category

• Natural Language Processing: Safety and Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health

Abstract

Urban intersections expose the limitations of single-vehicle perception under occlusion and partial observability. In this study, we present an auditable roadside LiDAR framework for infrastructure-assisted safety analysis at a signalized urban intersection in New York City, developed and evaluated using real-world data. The proposed framework integrates trajectory construction, iterative human-in-the-loop quality assurance (QA), and interpretable near-miss analytics to produce defensible safety evidence from infrastructure sensing. Using a human-labeled heavy vehicle--bicycle interaction as an anchor case, we show that direction-agnostic time-to-collision (TTC) drops below 1s, while longitudinal TTC remains above conservative braking thresholds, revealing a lateral-intrusion-dominated conflict mechanism. Beyond individual cases, continuous-window evaluation and multi-round QA analysis demonstrate that the framework systematically reduces failure modes such as track fragmentation, spurious TTC triggers, unstable geometry, and cross-lane false conflicts. These results position roadside LiDAR as a practical post-hoc auditing mechanism for cooperative perception systems, with broader statistical validation discussed. This work provides a pathway toward scalable, data-driven safety auditing of urban intersections, enabling transportation agencies to identify and mitigate high-risk interactions beyond crash-based analyses.

Problem

• roadside LiDAR
• urban intersections
• safety auditing
• V2X infrastructure
• near-miss analytics

Innovation

• roadside LiDAR
• cooperative safety auditing
• human-in-the-loop QA
• interpretable near-miss analytics
• V2X infrastructure intelligence