Interpretable Interaction Modeling for Trajectory Prediction via Agent Selection and Physical Coefficient
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912454963888128 |
|---|---|
| author | Huang, Shiji Ye, Lei Chen, Min Luo, Wenhai Wang, Dihong Xu, Chenqi Liang, Deyuan |
| author_facet | Huang, Shiji Ye, Lei Chen, Min Luo, Wenhai Wang, Dihong Xu, Chenqi Liang, Deyuan |
| contents | A thorough understanding of the interaction between the target agent and surrounding agents is a prerequisite for accurate trajectory prediction. Although many methods have been explored, they assign correlation coefficients to surrounding agents in a purely learning-based manner. In this study, we present ASPILin, which manually selects interacting agents and replaces the attention scores in Transformer with a newly computed physical correlation coefficient, enhancing the interpretability of interaction modeling. Surprisingly, these simple modifications can significantly improve prediction performance and substantially reduce computational costs. We intentionally simplified our model in other aspects, such as map encoding. Remarkably, experiments conducted on the INTERACTION, highD, and CitySim datasets demonstrate that our method is efficient and straightforward, outperforming other state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_13152 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Interpretable Interaction Modeling for Trajectory Prediction via Agent Selection and Physical Coefficient Huang, Shiji Ye, Lei Chen, Min Luo, Wenhai Wang, Dihong Xu, Chenqi Liang, Deyuan Computer Vision and Pattern Recognition Artificial Intelligence A thorough understanding of the interaction between the target agent and surrounding agents is a prerequisite for accurate trajectory prediction. Although many methods have been explored, they assign correlation coefficients to surrounding agents in a purely learning-based manner. In this study, we present ASPILin, which manually selects interacting agents and replaces the attention scores in Transformer with a newly computed physical correlation coefficient, enhancing the interpretability of interaction modeling. Surprisingly, these simple modifications can significantly improve prediction performance and substantially reduce computational costs. We intentionally simplified our model in other aspects, such as map encoding. Remarkably, experiments conducted on the INTERACTION, highD, and CitySim datasets demonstrate that our method is efficient and straightforward, outperforming other state-of-the-art methods. |
| title | Interpretable Interaction Modeling for Trajectory Prediction via Agent Selection and Physical Coefficient |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2405.13152 |