A Study on Machine Learning-Enhanced Roadside Unit-Based Detection of Abnormal Driving in Autonomous Vehicles
Ensuring the safety of autonomous vehicles is becoming increasingly important with ongoing technological advancements. In this paper, we suggest a machine learning-based approach for detecting and responding to various abnormal behaviors within the V2X system, a system that mirrors real-world road c...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/13/2/288 |
| _version_ | 1797344218505543680 |
|---|---|
| author | Keon Yun Heesun Yun Sangmin Lee Jinhyeok Oh Minchul Kim Myongcheol Lim Juntaek Lee Chanmin Kim Jiwon Seo Jinyoung Choi |
| author_facet | Keon Yun Heesun Yun Sangmin Lee Jinhyeok Oh Minchul Kim Myongcheol Lim Juntaek Lee Chanmin Kim Jiwon Seo Jinyoung Choi |
| author_sort | Keon Yun |
| collection | DOAJ |
| description | Ensuring the safety of autonomous vehicles is becoming increasingly important with ongoing technological advancements. In this paper, we suggest a machine learning-based approach for detecting and responding to various abnormal behaviors within the V2X system, a system that mirrors real-world road conditions. Our system, including the RSU, is designed to identify vehicles exhibiting abnormal driving. Abnormal driving can arise from various causes, such as communication delays, sensor errors, navigation system malfunctions, environmental challenges, and cybersecurity threats. We simulated exploring three primary scenarios of abnormal driving: sensor errors, overlapping vehicles, and counterflow driving. The applicability of machine learning algorithms for detecting these anomalies was evaluated. The Minisom algorithm, in particular, demonstrated high accuracy, recall, and precision in identifying sensor errors, vehicle overlaps, and counterflow situations. Notably, changes in the vehicle’s direction and its characteristics proved to be significant indicators in the Basic Safety Messages (BSM). We propose adding a new element called <i>linePosition</i> to BSM Part 2, enhancing our ability to promptly detect and address vehicle abnormalities. This addition underpins the technical capabilities of RSU systems equipped with edge computing, enabling real-time analysis of vehicle data and appropriate responsive measures. In this paper, we emphasize the effectiveness of machine learning in identifying and responding to the abnormal behavior of autonomous vehicles, offering new ways to enhance vehicle safety and facilitate smoother road traffic flow. |
| first_indexed | 2024-03-08T10:59:10Z |
| format | Article |
| id | doaj.art-637e9368faaa426e93b7ff87353a76a5 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-08T10:59:10Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-637e9368faaa426e93b7ff87353a76a52024-01-26T16:13:04ZengMDPI AGElectronics2079-92922024-01-0113228810.3390/electronics13020288A Study on Machine Learning-Enhanced Roadside Unit-Based Detection of Abnormal Driving in Autonomous VehiclesKeon Yun0Heesun Yun1Sangmin Lee2Jinhyeok Oh3Minchul Kim4Myongcheol Lim5Juntaek Lee6Chanmin Kim7Jiwon Seo8Jinyoung Choi9Pentasecurity, Incorporated, 9F, 115, Yeouigongwon-ro, Yeongdeungpo-gu, Seoul 07241, Republic of KoreaPentasecurity, Incorporated, 9F, 115, Yeouigongwon-ro, Yeongdeungpo-gu, Seoul 07241, Republic of KoreaPentasecurity, Incorporated, 9F, 115, Yeouigongwon-ro, Yeongdeungpo-gu, Seoul 07241, Republic of KoreaPentasecurity, Incorporated, 9F, 115, Yeouigongwon-ro, Yeongdeungpo-gu, Seoul 07241, Republic of KoreaPentasecurity, Incorporated, 9F, 115, Yeouigongwon-ro, Yeongdeungpo-gu, Seoul 07241, Republic of KoreaPentasecurity, Incorporated, 9F, 115, Yeouigongwon-ro, Yeongdeungpo-gu, Seoul 07241, Republic of KoreaKorea Automotive Technology Institute, 4F, 94, Cheongna emerald-ro, Seo-gu, Incheon 22739, Republic of KoreaKorea Automotive Technology Institute, 4F, 94, Cheongna emerald-ro, Seo-gu, Incheon 22739, Republic of KoreaKorea Automotive Technology Institute, 4F, 94, Cheongna emerald-ro, Seo-gu, Incheon 22739, Republic of KoreaXbrain, Incorporated, 5F, 168, Yeoksam-ro, Gangnam-gu, Seoul 06248, Republic of KoreaEnsuring the safety of autonomous vehicles is becoming increasingly important with ongoing technological advancements. In this paper, we suggest a machine learning-based approach for detecting and responding to various abnormal behaviors within the V2X system, a system that mirrors real-world road conditions. Our system, including the RSU, is designed to identify vehicles exhibiting abnormal driving. Abnormal driving can arise from various causes, such as communication delays, sensor errors, navigation system malfunctions, environmental challenges, and cybersecurity threats. We simulated exploring three primary scenarios of abnormal driving: sensor errors, overlapping vehicles, and counterflow driving. The applicability of machine learning algorithms for detecting these anomalies was evaluated. The Minisom algorithm, in particular, demonstrated high accuracy, recall, and precision in identifying sensor errors, vehicle overlaps, and counterflow situations. Notably, changes in the vehicle’s direction and its characteristics proved to be significant indicators in the Basic Safety Messages (BSM). We propose adding a new element called <i>linePosition</i> to BSM Part 2, enhancing our ability to promptly detect and address vehicle abnormalities. This addition underpins the technical capabilities of RSU systems equipped with edge computing, enabling real-time analysis of vehicle data and appropriate responsive measures. In this paper, we emphasize the effectiveness of machine learning in identifying and responding to the abnormal behavior of autonomous vehicles, offering new ways to enhance vehicle safety and facilitate smoother road traffic flow.https://www.mdpi.com/2079-9292/13/2/288autonomous vehicleroadside unitabnormal drivingmachine learning |
| spellingShingle | Keon Yun Heesun Yun Sangmin Lee Jinhyeok Oh Minchul Kim Myongcheol Lim Juntaek Lee Chanmin Kim Jiwon Seo Jinyoung Choi A Study on Machine Learning-Enhanced Roadside Unit-Based Detection of Abnormal Driving in Autonomous Vehicles Electronics autonomous vehicle roadside unit abnormal driving machine learning |
| title | A Study on Machine Learning-Enhanced Roadside Unit-Based Detection of Abnormal Driving in Autonomous Vehicles |
| title_full | A Study on Machine Learning-Enhanced Roadside Unit-Based Detection of Abnormal Driving in Autonomous Vehicles |
| title_fullStr | A Study on Machine Learning-Enhanced Roadside Unit-Based Detection of Abnormal Driving in Autonomous Vehicles |
| title_full_unstemmed | A Study on Machine Learning-Enhanced Roadside Unit-Based Detection of Abnormal Driving in Autonomous Vehicles |
| title_short | A Study on Machine Learning-Enhanced Roadside Unit-Based Detection of Abnormal Driving in Autonomous Vehicles |
| title_sort | study on machine learning enhanced roadside unit based detection of abnormal driving in autonomous vehicles |
| topic | autonomous vehicle roadside unit abnormal driving machine learning |
| url | https://www.mdpi.com/2079-9292/13/2/288 |
| work_keys_str_mv | AT keonyun astudyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT heesunyun astudyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT sangminlee astudyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT jinhyeokoh astudyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT minchulkim astudyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT myongcheollim astudyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT juntaeklee astudyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT chanminkim astudyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT jiwonseo astudyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT jinyoungchoi astudyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT keonyun studyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT heesunyun studyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT sangminlee studyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT jinhyeokoh studyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT minchulkim studyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT myongcheollim studyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT juntaeklee studyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT chanminkim studyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT jiwonseo studyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles AT jinyoungchoi studyonmachinelearningenhancedroadsideunitbaseddetectionofabnormaldrivinginautonomousvehicles |