LMFormer: Lane based Motion Prediction Transformer
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909579134107648 |
|---|---|
| author | Yadav, Harsh Schaefer, Maximilian Zhao, Kun Meisen, Tobias |
| author_facet | Yadav, Harsh Schaefer, Maximilian Zhao, Kun Meisen, Tobias |
| contents | Motion prediction plays an important role in autonomous driving. This study presents LMFormer, a lane-aware transformer network for trajectory prediction tasks. In contrast to previous studies, our work provides a simple mechanism to dynamically prioritize the lanes and shows that such a mechanism introduces explainability into the learning behavior of the network. Additionally, LMFormer uses the lane connection information at intersections, lane merges, and lane splits, in order to learn long-range dependency in lane structure. Moreover, we also address the issue of refining the predicted trajectories and propose an efficient method for iterative refinement through stacked transformer layers. For benchmarking, we evaluate LMFormer on the nuScenes dataset and demonstrate that it achieves SOTA performance across multiple metrics. Furthermore, the Deep Scenario dataset is used to not only illustrate cross-dataset network performance but also the unification capabilities of LMFormer to train on multiple datasets and achieve better performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10275 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LMFormer: Lane based Motion Prediction Transformer Yadav, Harsh Schaefer, Maximilian Zhao, Kun Meisen, Tobias Computer Vision and Pattern Recognition Machine Learning Motion prediction plays an important role in autonomous driving. This study presents LMFormer, a lane-aware transformer network for trajectory prediction tasks. In contrast to previous studies, our work provides a simple mechanism to dynamically prioritize the lanes and shows that such a mechanism introduces explainability into the learning behavior of the network. Additionally, LMFormer uses the lane connection information at intersections, lane merges, and lane splits, in order to learn long-range dependency in lane structure. Moreover, we also address the issue of refining the predicted trajectories and propose an efficient method for iterative refinement through stacked transformer layers. For benchmarking, we evaluate LMFormer on the nuScenes dataset and demonstrate that it achieves SOTA performance across multiple metrics. Furthermore, the Deep Scenario dataset is used to not only illustrate cross-dataset network performance but also the unification capabilities of LMFormer to train on multiple datasets and achieve better performance. |
| title | LMFormer: Lane based Motion Prediction Transformer |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2504.10275 |