Historical Prediction Attention Mechanism based Trajectory Forecasting for Proactive Work Zone Safety in a Digital Twin Environment

2025-08-05

AI Summary

To address low trajectory prediction accuracy and delayed risk warnings in highway work zones, this paper proposes HPNet—a trajectory prediction method integrating historical prediction attention mechanisms with a digital twin environment. The system fuses multi-source real-time sensor data, Lanelet2-based high-definition maps, and probabilistic conflict modeling, enabling infrastructure-driven proactive safety alerts within a SUMO-CARLA co-simulation platform. Innovatively, HPNet incorporates historical prediction errors into attention weight computation and enhances alert reliability via vehicle bounding-box conflict detection. Evaluated on a custom work-zone dataset, HPNet achieves an average displacement error (ADE) of 0.1327 m and final displacement error (FDE) of 0.3228 m—significantly outperforming Argoverse and Interaction benchmarks. Results demonstrate HPNet’s superior prediction accuracy and capability for active, safety-critical early warning in dynamic construction environments.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Hardware-aware ML

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Proactive safety systems aim to mitigate risks by anticipating potential conflicts between vehicles and enabling early intervention to prevent work zone-related crashes. This study presents an infrastructure-enabled proactive work zone safety warning system that leverages a Digital Twin environment, integrating real-time multi-sensor data, detailed High-Definition (HD) maps, and a historical prediction attention mechanism-based trajectory prediction model. Using a co-simulation environment that combines Simulation of Urban MObility (SUMO) and CAR Learning to Act (CARLA) simulators, along with Lanelet2 HD maps and the Historical Prediction Network (HPNet) model, we demonstrate effective trajectory prediction and early warning generation for vehicle interactions in freeway work zones. To evaluate the accuracy of predicted trajectories, we use two standard metrics: Joint Average Displacement Error (ADE) and Joint Final Displacement Error (FDE). Specifically, the infrastructure-enabled HPNet model demonstrates superior performance on the work-zone datasets generated from the co-simulation environment, achieving a minimum Joint FDE of 0.3228 meters and a minimum Joint ADE of 0.1327 meters, lower than the benchmarks on the Argoverse (minJointFDE: 1.0986 m, minJointADE: 0.7612 m) and Interaction (minJointFDE: 0.8231 m, minJointADE: 0.2548 m) datasets. In addition, our proactive safety warning generation application, utilizing vehicle bounding boxes and probabilistic conflict modeling, demonstrates its capability to issue alerts for potential vehicle conflicts.

Problem

• Predict vehicle trajectories in work zones using historical attention mechanisms
• Enhance proactive safety via real-time multi-sensor data and HD maps
• Evaluate prediction accuracy with displacement error metrics

Innovation

• Digital Twin integrates real-time multi-sensor data
• HPNet model for accurate trajectory prediction
• Co-simulation with SUMO and CARLA for validation