A deep learning approach for vehicle velocity prediction considering the influence factors of multiple lanes
Predicting the future velocity of vehicles is essential for the safety of autonomous driving and the Intelligent Transport System. This study investigates how the surrounding vehicles influence a driving vehicle. Based on the HighD dataset, a scenario that considers the current lane and the neighbor...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-01-01
|
| Series: | Electronic Research Archive |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/era.2023020?viewType=HTML |
| _version_ | 1811169612220334080 |
|---|---|
| author | Mingxing Xu Hongyi Lin Yang Liu |
| author_facet | Mingxing Xu Hongyi Lin Yang Liu |
| author_sort | Mingxing Xu |
| collection | DOAJ |
| description | Predicting the future velocity of vehicles is essential for the safety of autonomous driving and the Intelligent Transport System. This study investigates how the surrounding vehicles influence a driving vehicle. Based on the HighD dataset, a scenario that considers the current lane and the neighboring lanes is selected while the drivers' visual angles and visual gap angles along with other parameters in the dataset are characterized as features. To predict the velocity of a driving vehicle and calibrate the influence of surrounding vehicles, a Transformer-based model integrating the features of multiple vehicles is proposed, and different features are added to the layers while constructing the model. Moreover, the information from previous timestamps of the vehicle state is integrated to estimate the duration of the influences, since the influence of an incident is not instantaneous. In our experiments, we find that the duration of the influence on the driving state perfectly fits the driver's reaction time when maneuvers occur in the surrounding vehicles. In addition, we further quantify the importance of the influence on the vehicle velocity prediction based on the Random Forest and obtain some practical conclusions, for instance, the velocity of a vehicle is more influenced by the front vehicle in the left lane than that in the right lane, but is still mainly influenced by the front vehicle in the current lane. |
| first_indexed | 2024-04-10T16:45:19Z |
| format | Article |
| id | doaj.art-50640b438afa4d94bbf15f6eabe2d280 |
| institution | Directory Open Access Journal |
| issn | 2688-1594 |
| language | English |
| last_indexed | 2024-04-10T16:45:19Z |
| publishDate | 2023-01-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Electronic Research Archive |
| spelling | doaj.art-50640b438afa4d94bbf15f6eabe2d2802023-02-08T01:00:59ZengAIMS PressElectronic Research Archive2688-15942023-01-0131140142010.3934/era.2023020A deep learning approach for vehicle velocity prediction considering the influence factors of multiple lanesMingxing Xu0Hongyi Lin 1Yang Liu21. Ministry of Housing and Urban-Rural Development of the People's Republic of China2. State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, China2. State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing, ChinaPredicting the future velocity of vehicles is essential for the safety of autonomous driving and the Intelligent Transport System. This study investigates how the surrounding vehicles influence a driving vehicle. Based on the HighD dataset, a scenario that considers the current lane and the neighboring lanes is selected while the drivers' visual angles and visual gap angles along with other parameters in the dataset are characterized as features. To predict the velocity of a driving vehicle and calibrate the influence of surrounding vehicles, a Transformer-based model integrating the features of multiple vehicles is proposed, and different features are added to the layers while constructing the model. Moreover, the information from previous timestamps of the vehicle state is integrated to estimate the duration of the influences, since the influence of an incident is not instantaneous. In our experiments, we find that the duration of the influence on the driving state perfectly fits the driver's reaction time when maneuvers occur in the surrounding vehicles. In addition, we further quantify the importance of the influence on the vehicle velocity prediction based on the Random Forest and obtain some practical conclusions, for instance, the velocity of a vehicle is more influenced by the front vehicle in the left lane than that in the right lane, but is still mainly influenced by the front vehicle in the current lane.https://www.aimspress.com/article/doi/10.3934/era.2023020?viewType=HTMLvehicle velocity predictiondeep learningfeature engineeringtime series analysis |
| spellingShingle | Mingxing Xu Hongyi Lin Yang Liu A deep learning approach for vehicle velocity prediction considering the influence factors of multiple lanes Electronic Research Archive vehicle velocity prediction deep learning feature engineering time series analysis |
| title | A deep learning approach for vehicle velocity prediction considering the influence factors of multiple lanes |
| title_full | A deep learning approach for vehicle velocity prediction considering the influence factors of multiple lanes |
| title_fullStr | A deep learning approach for vehicle velocity prediction considering the influence factors of multiple lanes |
| title_full_unstemmed | A deep learning approach for vehicle velocity prediction considering the influence factors of multiple lanes |
| title_short | A deep learning approach for vehicle velocity prediction considering the influence factors of multiple lanes |
| title_sort | deep learning approach for vehicle velocity prediction considering the influence factors of multiple lanes |
| topic | vehicle velocity prediction deep learning feature engineering time series analysis |
| url | https://www.aimspress.com/article/doi/10.3934/era.2023020?viewType=HTML |
| work_keys_str_mv | AT mingxingxu adeeplearningapproachforvehiclevelocitypredictionconsideringtheinfluencefactorsofmultiplelanes AT hongyilin adeeplearningapproachforvehiclevelocitypredictionconsideringtheinfluencefactorsofmultiplelanes AT yangliu adeeplearningapproachforvehiclevelocitypredictionconsideringtheinfluencefactorsofmultiplelanes AT mingxingxu deeplearningapproachforvehiclevelocitypredictionconsideringtheinfluencefactorsofmultiplelanes AT hongyilin deeplearningapproachforvehiclevelocitypredictionconsideringtheinfluencefactorsofmultiplelanes AT yangliu deeplearningapproachforvehiclevelocitypredictionconsideringtheinfluencefactorsofmultiplelanes |