Network Level Evaluation of Hangup Susceptibility of HRGCs using Deep Learning and Sensing Techniques: A Goal Towards Safer Future

2025-12-14

AI Summary

Steep-grade highway–rail grade crossings (HRGCs) pose a significant risk of vehicle undercarriage suspension and entrapment, potentially leading to train collisions. To address this, we propose the first network-scale suspension-risk assessment framework: (1) a hybrid LSTM–Transformer model that fuses high-resolution 3D point-cloud data from Pave3D8K LiDAR scanning and ground-truth cross-sectional profiles acquired via handheld profilers to reconstruct accurate 3D crossing geometry; (2) statistical modeling to quantify suspension sensitivity across three representative vehicle classes based on dimensional variability; and (3) an AI-integrated, multi-sensor-enabled decision support system embedded within an ArcGIS spatial database. Applied to Oklahoma’s HRGC network, the framework identified 36–67 highest-risk locations. A deployable interactive software platform and curated spatial database have been delivered to state transportation authorities, enabling data-driven, targeted mitigation interventions.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Steep profiled Highway Railway Grade Crossings (HRGCs) pose safety hazards to vehicles with low ground clearance, which may become stranded on the tracks, creating risks of train vehicle collisions. This research develops a framework for network level evaluation of hangup susceptibility of HRGCs. Profile data from different crossings in Oklahoma were collected using both a walking profiler and the Pave3D8K Laser Imaging System. A hybrid deep learning model, combining Long Short Term Memory (LSTM) and Transformer architectures, was developed to reconstruct accurate HRGC profiles from Pave3D8K Laser Imaging System data. Vehicle dimension data from around 350 specialty vehicles were collected at various locations across Oklahoma to enable up to date statistical design dimensions. Hangup susceptibility was analyzed using three vehicle dimension scenarios (a) median dimension (median wheelbase and ground clearance), (b) 75 25 percentile dimension (75 percentile wheelbase, 25 percentile ground clearance), and (c) worst case dimension (maximum wheelbase and minimum ground clearance). Results indicate 36, 62, and 67 crossings at the highest hangup risk levels under these scenarios, respectively. An ArcGIS database and a software interface were developed to support transportation agencies in mitigating crossing hazards. This framework advances safety evaluation by integrating next generation sensing, deep learning, and infrastructure datasets into practical decision support tools.

Problem

• Evaluates hangup susceptibility at highway-rail crossings using deep learning.
• Analyzes vehicle dimensions to identify high-risk crossing scenarios.
• Develops tools for transportation agencies to mitigate crossing hazards.

Innovation

• Hybrid deep learning model combining LSTM and Transformer
• Network-level evaluation using sensing and vehicle dimension scenarios
• ArcGIS database and software interface for decision support