{"ID":2871727,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.10080","arxiv_id":"2509.10080","title":"BEVTraj: Map-Free End-to-End Trajectory Prediction in Bird's-Eye View with Deformable Attention and Sparse Goal Proposals","abstract":"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.","short_abstract":"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 levera...","url_abs":"https://arxiv.org/abs/2509.10080","url_pdf":"https://arxiv.org/pdf/2509.10080v2","authors":"[\"Minsang Kong\",\"Myeongjun Kim\",\"Sang Gu Kang\",\"Hejiu Lu\",\"Yupeng Zhong\",\"Sang Hun Lee\"]","published":"2025-09-12T09:17:54Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":609893,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2871727,"paper_url":"https://arxiv.org/abs/2509.10080","paper_title":"BEVTraj: Map-Free End-to-End Trajectory Prediction in Bird's-Eye View with Deformable Attention and Sparse Goal Proposals","repo_url":"https://github.com/Kongminsang/bevtraj","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}