BEVTraj: Map-Free End-to-End Trajectory Prediction in Bird's-Eye View with Deformable Attention and Sparse Goal Proposals
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918337393459200 |
|---|---|
| author | Kong, Minsang Kim, Myeongjun Kang, Sang Gu Lu, Hejiu Zhong, Yupeng Lee, Sang Hun |
| author_facet | Kong, Minsang Kim, Myeongjun Kang, Sang Gu Lu, Hejiu Zhong, Yupeng Lee, Sang Hun |
| contents | In autonomous driving, trajectory prediction is essential for safe and efficient navigation. While recent methods often rely on high-definition (HD) maps to provide structured environmental priors, such maps are costly to maintain, geographically limited, and unreliable in dynamic or unmapped scenarios. Directly leveraging raw sensor data in Bird's-Eye View (BEV) space offers greater flexibility, but BEV features are dense and unstructured, making agent-centric spatial reasoning challenging and computationally inefficient. To address this, we propose Bird's-Eye View Trajectory Prediction (BEVTraj), a map-free framework that employs deformable attention to adaptively aggregate task-relevant context from sparse locations in dense BEV features. We further introduce a Sparse Goal Candidate Proposal (SGCP) module that predicts a small set of realistic goals, enabling fully end-to-end multimodal forecasting without heuristic post-processing. Extensive experiments show that BEVTraj achieves performance comparable to state-of-the-art HD map-based methods while providing greater robustness and flexibility without relying on pre-built maps. The source code is available at https://github.com/Kongminsang/bevtraj. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_10080 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BEVTraj: Map-Free End-to-End Trajectory Prediction in Bird's-Eye View with Deformable Attention and Sparse Goal Proposals Kong, Minsang Kim, Myeongjun Kang, Sang Gu Lu, Hejiu Zhong, Yupeng Lee, Sang Hun Computer Vision and Pattern Recognition I.2.9; I.4.8 In autonomous driving, trajectory prediction is essential for safe and efficient navigation. While recent methods often rely on high-definition (HD) maps to provide structured environmental priors, such maps are costly to maintain, geographically limited, and unreliable in dynamic or unmapped scenarios. Directly leveraging raw sensor data in Bird's-Eye View (BEV) space offers greater flexibility, but BEV features are dense and unstructured, making agent-centric spatial reasoning challenging and computationally inefficient. To address this, we propose Bird's-Eye View Trajectory Prediction (BEVTraj), a map-free framework that employs deformable attention to adaptively aggregate task-relevant context from sparse locations in dense BEV features. We further introduce a Sparse Goal Candidate Proposal (SGCP) module that predicts a small set of realistic goals, enabling fully end-to-end multimodal forecasting without heuristic post-processing. Extensive experiments show that BEVTraj achieves performance comparable to state-of-the-art HD map-based methods while providing greater robustness and flexibility without relying on pre-built maps. The source code is available at https://github.com/Kongminsang/bevtraj. |
| title | BEVTraj: Map-Free End-to-End Trajectory Prediction in Bird's-Eye View with Deformable Attention and Sparse Goal Proposals |
| topic | Computer Vision and Pattern Recognition I.2.9; I.4.8 |
| url | https://arxiv.org/abs/2509.10080 |