Single-Frame LiDAR Bird's-Eye View with Lightweight Transformer for Self-Driving Vehicle Trajectory Prediction Baseline Research
Frontiers in Computing and Intelligent Systems · 30.04.2026 · 16 (2) · 81-84
DOI: 10.54097/xg7py126 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Computing and Intelligent Systems, online erschienen am 30.04.2026. Verfasst von Chenhe Li. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Urban advanced driver-assistance systems (ADAS) need to predict the future trajectory of the ego-vehicle at a frequency of 10–20 Hz. Traditional methods rely on high-definition maps, which have pain points such as low freshness, high cost, and narrow coverage. This paper proposes an open-source ego-vehicle trajectory prediction baseline that uses only single-frame LiDAR and requires no high-definition maps or visual assistance. A 200×200×8 bird's-eye view pseudo-image is generated by height-sliced voxelization, and end-to-end trajectory regression is completed by a 6-layer Transformer encoder and uniform Token sampling. After 70% sparse pruning and INT8 quantization, the model size is compressed to 8 MB, and 20 future waypoints are output within 30 ms on Jetson Orin. The ADE on the nuScenes-mini test set reaches 0.54 m, which is comparable to the visual BEV baseline, with a parameter size of
Zitieren
APA
Li, C. (2026). Single-Frame LiDAR Bird's-Eye View with Lightweight Transformer for Self-Driving Vehicle Trajectory Prediction Baseline Research. Frontiers in Computing and Intelligent Systems, 16(2), 81-84. https://doi.org/10.54097/xg7py126
Vancouver
Li C. Single-Frame LiDAR Bird's-Eye View with Lightweight Transformer for Self-Driving Vehicle Trajectory Prediction Baseline Research. Frontiers in Computing and Intelligent Systems. 2026;16(2):81-84. doi:10.54097/xg7py126
BibTeX
@article{Li2026,
author = {Li, Chenhe},
title = {Single-Frame LiDAR Bird's-Eye View with Lightweight Transformer for Self-Driving Vehicle Trajectory Prediction Baseline Research},
journal = {Frontiers in Computing and Intelligent Systems},
year = {2026},
volume = {16},
number = {2},
pages = {81--84},
doi = {10.54097/xg7py126}
}
EUVIMED