Automated Record Keeping for Maintenance Operations via Tracking of Maintenance Vehicles Using Telematics Tracks

Naman, Anugunj; Zhang, Yaguang; Ault, Aaron; Krogmeier, James V. · 2025 · ROSA P / Indiana Department of Transportation

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 study addresses the inefficiencies and inaccuracies inherent in manual record-keeping for transportation maintenance operations, specifically focusing on winter highway maintenance for the Indiana Department of Transportation (INDOT). Current practices rely on manual logs that lack spatial precision and temporal accuracy, creating significant administrative burdens for managers and limiting data-driven decision-making. The research aims to develop an automated system that leverages telematics-based GPS tracking to verify work orders, track vehicle movements, and enhance data accuracy, thereby optimizing resource allocation and improving accountability. The researchers utilized a large-scale dataset from the INDOT Data Warehouse, comprising over 5.1 million GPS data points from 1,051 vehicles during the winter season of December 2020 to April 2021. The study developed two complementary tools: a MATLAB-based algorithm for statewide comprehensive analysis and a web-based application for district-level interactive supervision. The methodology involved preprocessing GPS data, converting coordinates to INDOT’s linear reference system (road names and mileposts), and matching vehicle tracks against recorded work orders. The system was designed to automate work order verification and partially automate generation, incorporating visualization tools to display spatial and temporal operational details. Key findings indicate that the current minute-level GPS sampling rate is insufficient for accurate work order automation, leading to recommendations for second-level tracking to capture precise vehicle activity. The study successfully automated the verification of work orders for patrolling and snow removal, reducing manual effort and improving accuracy. A standardized methodology for converting GPS coordinates to road locations was established to ensure data consistency. However, the research identified operational challenges, including data transmission gaps in rural areas due to limited connectivity and the necessity of integrating precise start and end times into work orders for effective automation. The developed web application provided a scalable, privacy-focused interface for managers to visualize and validate maintenance activities locally. The significance of this work lies in providing a scalable framework for automating maintenance record-keeping, which can be expanded to other operations such as asphalt patching and roadside mowing. The study emphasizes the critical need for higher-resolution GPS data, standardized data processing frameworks, and enhanced work order recording methods to improve operational efficiency. By bridging advanced research with practical application, the findings offer a pathway for transportation agencies to transition from manual, error-prone logging to automated, data-driven fleet management, ultimately supporting better planning, cost analysis, and performance evaluation.

Key finding

The automated system successfully verified winter maintenance work orders using GPS telematics, but minute-level GPS sampling proved insufficient for accurate automation, necessitating higher-resolution second-level tracking.

Methodology

dataset

Sample size: 1051

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).

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.

• exposure measurement