Direct Covariance-to-Beamformer Mapping for Low-Latency Hybrid ISAC Beamforming with Subsequent DoA Estimation
Organizations: Department of Electronics and Communication Engineering, Amrita School of Engineering, Bengaluru, Amrita Vishwa Vidyapeetham, India · Department of Electronic Systems Engineering, Indian Institute of Science, Bangalore, India
Abstract
Integrated sensing and communication (ISAC) systems typically employ a two-stage beamforming pipeline, in which target directions are first estimated from the received covariance matrix and then used to compute the beamforming weights by solving non-convex optimization problems. Although effective, this approach introduces processing latency that can limit beam adaptation in dynamic environments. This letter proposes a beamforming deep neural network (BFDNN) for direct covariance-to-beamformer learning in ISAC systems. BFDNN is a compact regression network that maps covariance-matrix features directly to the hybrid beamforming weights produced by a hybrid ISAC beamformer, eliminating the direction-of-arrival (DoA) estimation stage during inference. Compared with MUSIC, classification-DNN, and regression-DNN based beamforming pipelines, BFDNN generates comparable beam patterns and higher effective spectral efficiencies while reducing the beamforming prediction latency by 25-30 times on the evaluated platform, demonstrating the potential of direct covariance-to-beamformer learning for low-latency ISAC beam updates. Moreover, the target directions can be inferred indirectly from the generated radiation pattern, yielding DoA accuracy competitive with that of dedicated learning-based methods in the evaluated scenario.
Figures & tables
| Method | Input Representation | Input Size | Output Representation | Output Size | Training SNRs |
|---|---|---|---|---|---|
| Proposed BFDNN | Upper triangular covariance matrix (Real, imaginary, and phase) | 360 | Beamforming weights (real and imaginary parts) | 64 | 5dB |
| Classification Method [ 3 ] | Covariance matrix (real, imaginary, phase) | Binary angle grid vector | 121 | dB | |
| RDNN [ 4 ] | Upper triangular covariance matrix (Real and imaginary) | 240 | Continuous DoA estimates | 2 | dB |
| LDNN [ 5 ] | Average of upper triangular covariance matrix elements along super-diagonals (Real and imaginary) | 30 | Continuous DoA estimates | 2 | dB |
| Methods | Prediction Time(s) | RMSE | ESE(bps/Hz) |
|---|---|---|---|
| Classification+SVD | 0.0037 | 0.1051 | 9.5204 |
| RDNN+SVD | 0.0033 | 0.2808 | 10.1183 |
| LDNN+SVD | 0.0035 | 17.7031 | 2.1756 |
| MUSIC+SVD | 0.0039 | 0.8011 | 9.1911 |
| BFDNN | 0.1135 | 13.6489 |
Integrated Sensing and Communication
Integrated sensing and communication combines wireless data links with radar-like perception using shared signals, spectrum, and hardware.
See all 55 papers