arXiv：cs.LG（机器学习，全量分类）· George Sebastian, Philipp Berthold, Bianca Forkel, Leon Pohl, Mirko Maehlisch·· 19 小时前AI 评分30
能否从预波束成形逐天线距离-多普勒雷达测量中学习空间结构？
On Learning Spatial Structure from Pre-Beamforming Per-Antenna Range-Doppler Radar Measurements
AI 导读
一项被 IEEE RA-L 2026 接收的研究探讨能否直接从预波束成形逐天线距离-多普勒（RD）测量中学习空间结构。实验在 6-TX x 8-RX（48 虚拟天线）车用雷达上进行，采用 A/B 线性调频序列 FMCW 发射方案，使用双 chirp 共享权重编码器端到端训练，并以 BEV 占用作为几何探针评估空间可恢复性，监督信号来自 LiDAR 且显式建模雷达视场与遮挡。
正文
Abstract:Automotive radar perception pipelines commonly construct angle-domain representations via beamforming before applying learning-based models. This work instead investigates a representational question: can meaningful spatial structure be learned directly from pre-beamforming per-antenna range-Doppler (RD) measurements? Experiments are conducted on a 6-TX x 8-RX (48 virtual antennas) commodity automotive radar employing an A/B chirp-sequence frequency-modulated continuous-wave (CS-FMCW) transmit scheme, in which the effective transmit aperture varies between chirps (single-TX vs multi-TX), enabling controlled analyses of chirp-dependent transmit configurations. We operate on pre-beamforming per-antenna RD tensors using a dual-chirp shared-weight encoder trained in an end-to-end, fully data-driven manner, and evaluate spatial recoverability using bird's-eye-view (BEV) occupancy as a geometric probe rather than a performance-driven objective. Supervision is visibility-aware and cross-modal, derived from LiDAR with explicit modeling of the radar field-of-view and occlusion-aware LiDAR observability via ray-based visibility. Through analyses of signal properties, transmit configurations (A-only, B-only, and A+B), receive aperture, and range-Doppler structure, together with physics-aligned baselines, we investigate the factors influencing spatial recoverability. The results indicate that meaningful spatial structure is recoverable from pre-beamforming per-antenna RD tensors under the studied A/B CS-FMCW radar configuration through learned spatial mixing, without relying on hand-crafted signal-processing stages.
| Comments: | Accepted for publication in IEEE Robotics and Automation Letters (RA-L), 2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Robotics (cs.RO) |
| Cite as: | arXiv:2604.01921 [cs.CV] |
| (or arXiv:2604.01921v3 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2604.01921 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.1109/LRA.2026.3739028
DOI(s) linking to related resources |
Submission history
From: George Sebastian [view email]
[v1]
Thu, 2 Apr 2026 11:39:00 UTC (1,779 KB)
[v2]
Sun, 20 Sep 2026 22:20:28 UTC (1,827 KB)
[v3]
Thu, 1 Oct 2026 06:11:10 UTC (1,827 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org