Recursive Least Squares Based Refinement Network for Vehicle Trajectory Prediction
Trajectory prediction of surrounding objects plays a pivotal role in the field of autonomous driving vehicles. In the current rollout process, it suffers from an accumulation of errors, which has a negative impact on prediction accuracy. This paper proposes a parametric-learning recursive least-squa...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/12/1859 |
| _version_ | 1797487992467619840 |
|---|---|
| author | Shengyi Li Qifan Xue Dongfeng Shi Xuanpeng Li Weigong Zhang |
| author_facet | Shengyi Li Qifan Xue Dongfeng Shi Xuanpeng Li Weigong Zhang |
| author_sort | Shengyi Li |
| collection | DOAJ |
| description | Trajectory prediction of surrounding objects plays a pivotal role in the field of autonomous driving vehicles. In the current rollout process, it suffers from an accumulation of errors, which has a negative impact on prediction accuracy. This paper proposes a parametric-learning recursive least-squares (RLS) method integrated with an encoder–decoder framework for trajectory prediction, named the recursive least-squares-based refinement network (RRN). Through the generation of several anchors in the future trajectory, RRN can capture both local and global motion patterns. We conducted experiments on the prevalent NGSIM and INTERACTION datasets, which contain various scenarios such as highways, intersections and roundabouts. The promising results indicate that RRN could improve the performance of the rollout trajectory prediction effectively. |
| first_indexed | 2024-03-09T23:56:42Z |
| format | Article |
| id | doaj.art-abb4f015b4314c7980513e6e88f61d64 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T23:56:42Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-abb4f015b4314c7980513e6e88f61d642023-11-23T16:24:53ZengMDPI AGElectronics2079-92922022-06-011112185910.3390/electronics11121859Recursive Least Squares Based Refinement Network for Vehicle Trajectory PredictionShengyi Li0Qifan Xue1Dongfeng Shi2Xuanpeng Li3Weigong Zhang4School of Instrument Science and Engineering, Southeast University, Nanjing 211189, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 211189, ChinaBeijing Remote Sensing Information Institute, Beijing 100192, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 211189, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 211189, ChinaTrajectory prediction of surrounding objects plays a pivotal role in the field of autonomous driving vehicles. In the current rollout process, it suffers from an accumulation of errors, which has a negative impact on prediction accuracy. This paper proposes a parametric-learning recursive least-squares (RLS) method integrated with an encoder–decoder framework for trajectory prediction, named the recursive least-squares-based refinement network (RRN). Through the generation of several anchors in the future trajectory, RRN can capture both local and global motion patterns. We conducted experiments on the prevalent NGSIM and INTERACTION datasets, which contain various scenarios such as highways, intersections and roundabouts. The promising results indicate that RRN could improve the performance of the rollout trajectory prediction effectively.https://www.mdpi.com/2079-9292/11/12/1859recursive refinement networktrajectory predictionparametric-learning recursive least squareanchor generator |
| spellingShingle | Shengyi Li Qifan Xue Dongfeng Shi Xuanpeng Li Weigong Zhang Recursive Least Squares Based Refinement Network for Vehicle Trajectory Prediction Electronics recursive refinement network trajectory prediction parametric-learning recursive least square anchor generator |
| title | Recursive Least Squares Based Refinement Network for Vehicle Trajectory Prediction |
| title_full | Recursive Least Squares Based Refinement Network for Vehicle Trajectory Prediction |
| title_fullStr | Recursive Least Squares Based Refinement Network for Vehicle Trajectory Prediction |
| title_full_unstemmed | Recursive Least Squares Based Refinement Network for Vehicle Trajectory Prediction |
| title_short | Recursive Least Squares Based Refinement Network for Vehicle Trajectory Prediction |
| title_sort | recursive least squares based refinement network for vehicle trajectory prediction |
| topic | recursive refinement network trajectory prediction parametric-learning recursive least square anchor generator |
| url | https://www.mdpi.com/2079-9292/11/12/1859 |
| work_keys_str_mv | AT shengyili recursiveleastsquaresbasedrefinementnetworkforvehicletrajectoryprediction AT qifanxue recursiveleastsquaresbasedrefinementnetworkforvehicletrajectoryprediction AT dongfengshi recursiveleastsquaresbasedrefinementnetworkforvehicletrajectoryprediction AT xuanpengli recursiveleastsquaresbasedrefinementnetworkforvehicletrajectoryprediction AT weigongzhang recursiveleastsquaresbasedrefinementnetworkforvehicletrajectoryprediction |