PRISA: Proactive Infrastructure LiDAR Framework for Intersection Safety Assessment

2026-07-17

AI Summary

This study addresses the challenge of real-time conflict prediction at urban intersections, where complex multi-agent interactions and inadequate protection for vulnerable road users—particularly pedestrians—hinder existing systems from issuing timely warnings before conflicts escalate. To overcome this, the authors propose a modular edge computing framework leveraging roadside LiDAR, which employs unsupervised generation of scene-specific trajectory data to train prediction models. The system integrates Time-to-Collision (TTC) and Post-Encroachment Time (PPET) metrics into a unified risk assessment for both longitudinal and crossing conflicts. Implemented on an NVIDIA Jetson AGX Thor platform, the framework achieves privacy-preserving, low-latency operation with an end-to-end delay of only 194 milliseconds while supporting a 2.4-second prediction horizon. Validation on the R-LiViT dataset and real-world deployment at an intersection in Chattanooga, Tennessee, demonstrates its practical viability.

Abstract

Urban intersections are among the most hazardous locations in road networks, posing significant risks to vehicles and vulnerable road users (VRUs) such as pedestrians and cyclists. The complexity of multi-agent interactions demands continuous, real-time monitoring systems capable of anticipating conflicts before they escalate into crashes. We present PRISA, a modular infrastructure LiDAR framework leveraging privacy-preserving, low-light-robust roadside sensors for long-term traffic observation and real-time risk detection at the edge. The framework comprises two core components: a sensing and perception layer and a plug-and-play risk assessment module. The latter automatically curates site-specific training data from accumulated perception outputs to train a trajectory prediction model without manual annotation. It then deploys the trained model for continuous motion forecasting and dual surrogate safety evaluation, using Time-to-Collision (TTC) for longitudinal conflicts and Predicted Post-Encroachment Time (PPET) for crossing and VRU-involved interactions. PRISA is evaluated on the public R-LiViT dataset and deployed on an NVIDIA Jetson AGX Thor at a live signalized intersection in Chattanooga, Tennessee. PPET-based assessment operates at 194~ms end-to-end latency over a 2.4-second predictive horizon, with TTC-based detection and perception remaining within real-time constraints, demonstrating practical feasibility for proactive multi-agent intersection safety monitoring.

Problem

• intersection safety
• vulnerable road users
• real-time risk detection
• multi-agent interactions
• conflict anticipation

Innovation

• LiDAR-based perception
• trajectory prediction
• surrogate safety measures
• edge computing
• autonomous data curation