Interactive Vehicle Trajectory Prediction for Highways Based on a Graph Attention Mechanism
Precise trajectory prediction is pivotal for autonomous vehicles operating in real-world traffic conditions, and can help them make the right decisions to ensure safety on the road. However, state-of-the-art approaches consider limited information about the historical movements of vehicles. On highw...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | World Electric Vehicle Journal |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2032-6653/15/3/96 |
| _version_ | 1797239057459183616 |
|---|---|
| author | Zhenyu Song Yubin Qian |
| author_facet | Zhenyu Song Yubin Qian |
| author_sort | Zhenyu Song |
| collection | DOAJ |
| description | Precise trajectory prediction is pivotal for autonomous vehicles operating in real-world traffic conditions, and can help them make the right decisions to ensure safety on the road. However, state-of-the-art approaches consider limited information about the historical movements of vehicles. On highways, drivers make their next judgments according to the behavior of the ambient vehicles. Thus, vehicles need to consider temporal and spatial interactions to reduce the risk of future collisions. In the current work, a trajectory prediction method is put forward in accordance with a graph attention mechanism. We add the absolute and relative motion information of vehicles to the input of the model to describe the vehicles’ past motion states more accurately. LSTM models are employed to process the historical motion information of vehicles, as well as the temporal correlations in interactions. The graph attention mechanism is applied to capture the spatial correlations between vehicles. Utilizing a decoder rooted in an LSTM framework, the future trajectory distribution is generated. Evaluation on the NGSIM US-101 and I-80 datasets substantiates the superiority of our approach over existing state-of-the-art algorithms. Moreover, the predictions of our model are analyzed. |
| first_indexed | 2024-04-24T17:45:29Z |
| format | Article |
| id | doaj.art-d46adf271c2743cd91ce88aaaf23191c |
| institution | Directory Open Access Journal |
| issn | 2032-6653 |
| language | English |
| last_indexed | 2024-04-24T17:45:29Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | World Electric Vehicle Journal |
| spelling | doaj.art-d46adf271c2743cd91ce88aaaf23191c2024-03-27T14:08:37ZengMDPI AGWorld Electric Vehicle Journal2032-66532024-03-011539610.3390/wevj15030096Interactive Vehicle Trajectory Prediction for Highways Based on a Graph Attention MechanismZhenyu Song0Yubin Qian1School of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaSchool of Mechanical and Automotive Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaPrecise trajectory prediction is pivotal for autonomous vehicles operating in real-world traffic conditions, and can help them make the right decisions to ensure safety on the road. However, state-of-the-art approaches consider limited information about the historical movements of vehicles. On highways, drivers make their next judgments according to the behavior of the ambient vehicles. Thus, vehicles need to consider temporal and spatial interactions to reduce the risk of future collisions. In the current work, a trajectory prediction method is put forward in accordance with a graph attention mechanism. We add the absolute and relative motion information of vehicles to the input of the model to describe the vehicles’ past motion states more accurately. LSTM models are employed to process the historical motion information of vehicles, as well as the temporal correlations in interactions. The graph attention mechanism is applied to capture the spatial correlations between vehicles. Utilizing a decoder rooted in an LSTM framework, the future trajectory distribution is generated. Evaluation on the NGSIM US-101 and I-80 datasets substantiates the superiority of our approach over existing state-of-the-art algorithms. Moreover, the predictions of our model are analyzed.https://www.mdpi.com/2032-6653/15/3/96autonomous vehiclestrajectory predictionvehicle interactionsgraph attention mechanism |
| spellingShingle | Zhenyu Song Yubin Qian Interactive Vehicle Trajectory Prediction for Highways Based on a Graph Attention Mechanism World Electric Vehicle Journal autonomous vehicles trajectory prediction vehicle interactions graph attention mechanism |
| title | Interactive Vehicle Trajectory Prediction for Highways Based on a Graph Attention Mechanism |
| title_full | Interactive Vehicle Trajectory Prediction for Highways Based on a Graph Attention Mechanism |
| title_fullStr | Interactive Vehicle Trajectory Prediction for Highways Based on a Graph Attention Mechanism |
| title_full_unstemmed | Interactive Vehicle Trajectory Prediction for Highways Based on a Graph Attention Mechanism |
| title_short | Interactive Vehicle Trajectory Prediction for Highways Based on a Graph Attention Mechanism |
| title_sort | interactive vehicle trajectory prediction for highways based on a graph attention mechanism |
| topic | autonomous vehicles trajectory prediction vehicle interactions graph attention mechanism |
| url | https://www.mdpi.com/2032-6653/15/3/96 |
| work_keys_str_mv | AT zhenyusong interactivevehicletrajectorypredictionforhighwaysbasedonagraphattentionmechanism AT yubinqian interactivevehicletrajectorypredictionforhighwaysbasedonagraphattentionmechanism |