发表机构
University of Calgary（卡尔加里大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出AngularWM自监督无线世界建模方法，通过联合嵌入预测架构和几何正则化学习潜在角度状态，无需标签即可高精度预测AoA，大幅降低误差并减少模型参数。
AI 中文摘要
在移动性条件下可靠的到达角（AoA）跟踪支持多天线无线系统中的主动波束对齐，但直接从原始I/Q数据学习这种演变具有挑战性，因为观测将角度信息与波形、多径、信道增益、硬件和噪声变化混合在一起。本文提出AngularWM，一种自监督的无线世界建模方法，从有序的多天线I/Q观测中学习预测性潜在角度状态。联合嵌入预测架构与无标签的轨迹级几何正则化器相结合，该正则化器鼓励由天线阵列响应驱动的近似仿射、非坍缩的潜在演变。预训练期间不使用AoA、运动或位移标签。由此产生的结构化世界状态支持直接的多步编码器空间外推，并泛化到训练中未见的角度步长。在大规模空中测量中，AngularWM将八步内的平均无预测器AoA误差从29.97°降低到0.49°。预训练后，仅需三个或四个标记参考角度即可校准完整的225点AoA网格，分别实现0.48°和0.43°的平均绝对误差（MAE）。AngularWM还在增加角度位移的情况下保持鲁棒的波束对齐和频谱效率，同时将部署模型大小从1.42M参数减少到0.30M参数，并降低预测延迟。
英文摘要
Reliable angle-of-arrival (AoA) tracking under mobility supports proactive beam alignment in multi-antenna wireless systems, but learning this evolution directly from raw I/Q is challenging because the observations mix angular information with waveform, multipath, channel-gain, hardware, and noise variations. This paper proposes \emph{AngularWM}, a self-supervised wireless world-modeling approach that learns a predictive latent angular state from ordered multi-antenna I/Q observations. A joint-embedding predictive architecture is combined with a label-free trajectory-level geometric regularizer that encourages an approximately affine, non-collapsed latent evolution motivated by the antenna-array response. No AoA, motion, or displacement labels are used during pretraining. The resulting structured world state supports direct multi-step encoder-space extrapolation and generalizes to angular step sizes not seen during training. On large-scale over-the-air measurements, AngularWM reduces the mean predictor-free AoA error over eight steps from $29.97^\circ$ to $0.49^\circ$. After pretraining, only three or four labeled reference angles are required to calibrate the complete 225-point AoA grid, achieving $0.48^\circ$ and $0.43^\circ$ MAE, respectively. AngularWM also maintains robust beam alignment and spectral efficiency under increasing angular displacement, while reducing the deployed model size from 1.42M to 0.30M parameters and forecast latency.
