Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding
![Thumbnail](/bitstream/handle/20.500.11850/643424/8148_real_time_motion_prediction_vi.pdf.jpg?sequence=5&isAllowed=y)
Open access
Date
2024-07Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
The real-world deployment of an autonomous driving system requires its components to run on-board and in real-time, including the motion prediction module that predicts the future trajectories of surrounding traffic participants. Existing agent-centric methods have demonstrated outstanding performance on public benchmarks. However, they suffer from high computational overhead and poor scalability as the number of agents to be predicted increases. To address this problem, we introduce the K-nearest neighbor attention with relative pose encoding (KNARPE), a novel attention mechanism allowing the pairwise-relative representation to be used by Transformers. Then, based on KNARPE we present the heterogeneous polyline Transformer with relative pose encoding (HPTR), a hierarchical framework enabling asynchronous token update during the online inference. By sharing contexts among agents and reusing the unchanged contexts, our approach is as efficient as scene-centric methods, while performing on par with state-of-the-art agent-centric methods. Experiments on Waymo and Argoverse-2 datasets show that HPTR achieves superior performance among end-to-end methods that do not apply expensive post-processing or ensembling. The code is available at https://github.com/zhejz/HPTR. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000643424Publication status
publishedExternal links
Book title
Advances in Neural Information Processing Systems 36Pages / Article No.
Publisher
CurranEvent
Organisational unit
03514 - Van Gool, Luc (emeritus) / Van Gool, Luc (emeritus)
09688 - Yu, Fisher / Yu, Fisher
Related publications and datasets
Is supplemented by: https://github.com/zhejz/HPTR
Is new version of: https://doi.org/10.48550/ARXIV.2310.12970
Notes
Conference lecture on December 13, 2023.More
Show all metadata
ETH Bibliography
yes
Altmetrics