Trajectory and velocity prediction of cut-in vehicles with deep learning method
Numerous studies have been conducted to predict lane-change trajectories. The significant differences between cut-ins and other lane changes suggest the necessity of building specialized algorithms tailored to learning vehicle cut-ins. In this paper, we explore predicting the trajectory and velocity...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/181883 |
| _version_ | 1826125955962241024 |
|---|---|
| author | Wang, Hanfeng |
| author2 | Su Rong |
| author_facet | Su Rong Wang, Hanfeng |
| author_sort | Wang, Hanfeng |
| collection | NTU |
| description | Numerous studies have been conducted to predict lane-change trajectories. The significant differences between cut-ins and other lane changes suggest the necessity of building specialized algorithms tailored to learning vehicle cut-ins. In this paper, we explore predicting the trajectory and velocity of the cut-in vehicles with a deep learning method. Particularly, we propose a prediction algorithm by combining a Transformer-based encoder and an LSTM-based decoder. The Transformer-based encoder is applied to capture features related to the driv ing context of the cut-in vehicle. The LSTM decoder is employed to predict the
trajectory and velocity of the cut-in vehicles by considering their temporal and social relationships. We extracted the cut-in events from NGSIM dataset for algorithm evaluation. We compared the performance of the proposed algorithm and three other deep learning algorithms based on the extracted cut-in events. The results suggest that the proposed algorithm outperforms other algorithms in trajectory and velocity predictions of the cut-in vehicles. Moreover, we analyze the effect of the historical data window size on the prediction performance of the proposed algorithm. |
| first_indexed | 2025-03-09T14:10:22Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/181883 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-03-09T14:10:22Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1818832024-12-27T15:46:14Z Trajectory and velocity prediction of cut-in vehicles with deep learning method Wang, Hanfeng Su Rong School of Electrical and Electronic Engineering RSu@ntu.edu.sg Engineering Numerous studies have been conducted to predict lane-change trajectories. The significant differences between cut-ins and other lane changes suggest the necessity of building specialized algorithms tailored to learning vehicle cut-ins. In this paper, we explore predicting the trajectory and velocity of the cut-in vehicles with a deep learning method. Particularly, we propose a prediction algorithm by combining a Transformer-based encoder and an LSTM-based decoder. The Transformer-based encoder is applied to capture features related to the driv ing context of the cut-in vehicle. The LSTM decoder is employed to predict the trajectory and velocity of the cut-in vehicles by considering their temporal and social relationships. We extracted the cut-in events from NGSIM dataset for algorithm evaluation. We compared the performance of the proposed algorithm and three other deep learning algorithms based on the extracted cut-in events. The results suggest that the proposed algorithm outperforms other algorithms in trajectory and velocity predictions of the cut-in vehicles. Moreover, we analyze the effect of the historical data window size on the prediction performance of the proposed algorithm. Master's degree 2024-12-27T13:22:32Z 2024-12-27T13:22:32Z 2024 Thesis-Master by Coursework Wang, H. (2024). Trajectory and velocity prediction of cut-in vehicles with deep learning method. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/181883 https://hdl.handle.net/10356/181883 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering Wang, Hanfeng Trajectory and velocity prediction of cut-in vehicles with deep learning method |
| title | Trajectory and velocity prediction of cut-in vehicles with deep learning method |
| title_full | Trajectory and velocity prediction of cut-in vehicles with deep learning method |
| title_fullStr | Trajectory and velocity prediction of cut-in vehicles with deep learning method |
| title_full_unstemmed | Trajectory and velocity prediction of cut-in vehicles with deep learning method |
| title_short | Trajectory and velocity prediction of cut-in vehicles with deep learning method |
| title_sort | trajectory and velocity prediction of cut in vehicles with deep learning method |
| topic | Engineering |
| url | https://hdl.handle.net/10356/181883 |
| work_keys_str_mv | AT wanghanfeng trajectoryandvelocitypredictionofcutinvehicleswithdeeplearningmethod |