An Ontology-based Method for Estimating Traffic Congestion Costs According to Autonomous Vehicle Operation

Seunghyun Kim; Jinyoung Kim; Mingyu Park; Sujin Kim

doi:10.7470/jkst.2026.44.3.363

All Issue

2026 Vol.44, Issue 3 Preview Page Next Page

Article

An Ontology-based Method for Estimating Traffic Congestion Costs According to Autonomous Vehicle Operation 자율주행차량 운영을 통한 온톨로지 기반의 교통혼잡비용 감소방안 연구

30 June 2026. pp. 363-375

PDF XML

Abstract

Recently, it has become possible to automatically create or expand ontologies using machine learning, natural language processing, and knowledge graphs. This helps AI utilize data more efficiently and enhances its reasoning capabilities to solve complex problems. Ontology is an explicit formal specification of a shared conceptualization in terms of a computer engineering. In this study, we applied the 3-layer structure of semantic-kinetic -dynamic, one of the latest ontology techniques, to build a system that quantitatively calculates traffic congestion costs based on various traffic-related big data generated in the autonomous vehicle driving environment and analyzes the congestion reduction effect. For ontology design, we used the free, open-source ontology editor ‘Protégé’. The Semantic layer defines each data entity and defines its properties to calculate traffic congestion costs using the diverse data collected in autonomous vehicle environments. The Kinetic layer connects the entities and concepts defined in the Semantic layer to real-world data and defines the methods and logic for system operation. The Dynamic layer is a layer that predicts and simulates the behavior and interaction of objects, and implements the necessary functions by developing a smart mobility control system on the web. This program was used to structure data on traffic volume, speed, signal operation, and optimal routes, and to systematically define data flow and decision rules between systems. This provided an analytical framework for quantitatively and visually assessing the dynamic interactions that could occur in autonomous vehicle-based traffic operations. This study analyzed the results of the ‘Autonomous driving technology development innovation project’ test-bed installed in Siheung City and found that it reduced traffic congestion costs by approximately 20% compared to existing commercialized navigation guidance routes.

Keywords

autonomous vehicle

ontology

semantic-kinetic-dynamic layer

smartmobility guidance system

traffic congestion costs

최근 머신러닝과 자연어 처리, 지식그래프 등을 활용해 자동으로 온톨로지를 생성하거나 확장하는 것이 가능해졌다. 이를 통해 AI가 데이터를 더욱 효율적으로 활용하고, 복잡한 문제를 해결하는 추론 능력을 강화하도록 돕고 있다. 온톨로지는 컴퓨터 공학적 관점에서 일반적으로 개념화된 것을 형식적으로 명백하게 기술하는 명세라고 정의할 수 있다. 본 연구에서는 최신 온톨로지 기법중의 하나인 시맨틱–키네틱–다이내믹의 3-레이어 구조를 적용해 자율주행차 운행환경에서 발생하는 다양한 교통관련 빅데이터를 기반으로 교통혼잡비용을 정량적으로 산출하여 혼잡감소 효과를 분석하는 시스템을 구축하였다. 온톨로지 설계를 위해 무료 오픈소스 온톨로지 편집기인 ‘Protégé’ 프로그램을 사용하였다. 시멘틱 레이어는 논리적 추상화 계층으로 개체 또는 데이터가 무엇이며 어떻게 연관되어 있는지를 분석한다. 키네틱 레이어는 실행 및 동작 계층으로 데이터가 모델에 매핑되는 방식을 결정한다. 다이나믹 레이어는 개체의 동작 및 상호작용 방식을 예측하고 시뮬레이션하고, 웹 기반 스마트모빌리티 관제시스템을 구현해 필요한 기능을 구현하는 계층이다. 이를 활용해 교통량, 속도, 신호운영 및 최적경로 데이터를 구조화하고 시스템 간 데이터 흐름 및 의사결정 규칙을 체계적으로 정의하였다. 이를 통해 자율주행차 기반 교통운영 환경에서 발생 가능한 동적 상호작용을 정량적, 시각적으로 평가할 수 있는 분석 프레임워크를 마련하였다. 본 연구를 통해 시흥시에 설치된 자율주행기술개발혁신사업 테스트베드 실증결과 기존의 상용화된 네비게이션 안내경로 대비 약 20%의 교통혼잡비용 절감 효과가 나타나는 것으로 분석되었다.

키워드

자율주행차량

온톨로지

시멘틱-키넥틱-다이나믹 레이어

스마트모빌리티 관제시스템

교통혼잡비용

References

Austroads (2022), Austroads Future Vehicles 2030 Report (AP-R623-20), 4.

Bayen A. M. (2021), Eliminating Traffic Jams With Self-Driving Cars, UC Berkeley CEE, Institute of Transportation Studies, https://ce.berkeley.edu/news/2537, 2025.11.03.

Cheon S., Lee C. (2024), National Transportation Policy Evaluation Indicator Survey Project, 3, General AR-22-20, KOTI (The Korea Transport Institute), 22-28.

Cho H. (2013), 2010 National Traffic Congestion Cost Estimation and Trend Analysis, KOTI (The Korea Transport Institute), 20-25.

Dictionary of Information & Communication Terminology (2025), http://terms.tta.or.kr/dictionary/dictionaryView.do?word_seq=050917-5, 2025.11.03.

European Commission (2017), Support Action for Vehicle and Road Automation Network, CORDIS-EU research results, https://cordis.europa.eu/project/id/610737?utm_source=chatgpt.com, 2025.12.11.

Fernandez S., Hadfi R., Ito T., Marsa-Maestre I., Velasco J. R. (2016), Ontology-Based Architecture for Intelligent Transportation Systems Using a Traffic Sensor Network, Sensors Journal, 16(8), MDPI, 1287-1296.

10.3390/s1608128727537878PMC5017452

Gruber A. T. (1992), A Translation Approach to Portable Ontology Specifications, Knowledge Acquisition, 5(2), Knowledge Systems Laboratory Technical Report KSL 92~71, 199-220.

10.1006/knac.1993.1008

Kim B. (2023), A Study on the Value of Travel Time in Gyeonggi-do, Basic Research-2023-01, GRI (Gyeonggi Research Institute), 31-34.

Kim S., Cheon S. (2019), A Study on the Estimation Methodology of Traffic Congestion Cost Based on Individual Vehicle Speed Data, KOTI (The Korea Transport Institute), 26(3), Journal of Transport Research, 45-57.

Lee C. (2023), Will Autonomous Driving Reduce Traffic Congestion?, KETI (Korea Electronic Technology Institute), https://www.linkedin.com/pulse/autonomous-driving-reduce-traffic-congestion-chaehoon-lee, 2025.11.05.

Lee J. (2025), Rising PALANTIR, Maximizing Business Value With AI, Joongang Sunday, 2025.03.08.

Obaid M., Torok A. (2021), Macroscopic Traffic Simulation of Autonomous Vehicle Effects, Vehicles, 3(2), MDPI, 187-196.

10.3390/vehicles3020012

Palantir homepage (2025), https://www.palantir.com/platforms/foundry/foundry-ontology, 2025.11.05.

Salter A. (2024), Will Autonomous Vehicles Put an End to Traffic Congestion?, Easy Mile, https://easymile.com, 2025.11.05.

Westhofen L., Neurohr C., Butz M., Scholtes M., Schuldes M. (2022), Using Ontologies for the Formalization and Recognition of Criticality for Automated Driving, OJ-Intelligent Transp. Sys., 3, 519-538.

10.1109/OJITS.2022.3187247

Information

Publisher :Korean Society of Transportation
Publisher(Ko) :대한교통학회
Journal Title :Journal of Korean Society of Transportation
Journal Title(Ko) :대한교통학회지
Volume : 44
No :3
Pages :363-375
Received Date : 2025-12-26
Revised Date : 2026-01-18
Accepted Date : 2026-02-24
DOI :https://doi.org/10.7470/jkst.2026.44.3.363

Journal of Korean Society of Transportation ISSN:1229-1366(Print) 2234-4217(Online) 대한교통학회지

All Issue