mlsanityData to 14 Oct 2026

Physically Parameterized Differentiable MUSIC for DoA Estimation with Uncalibrated Arrays

arXiv 2411.15144 ↗First posted 6 Nov 2024eess.SP cs.AI cs.ITcited by 5

Not on the map. Why?

Abstract (arXiv)

Direction of arrival (DoA) estimation is a common sensing problem in radar, sonar, audio, and wireless communication systems. It has gained renewed importance with the advent of the integrated sensing and communication paradigm. To fully exploit the potential of such sensing systems, it is crucial to take into account potential hardware impairments that can negatively impact the obtained performance. This study introduces a joint DoA estimation and hardware impairment learning scheme following a model-based approach. Specifically, a differentiable version of the multiple signal classification (MUSIC) algorithm is derived, allowing efficient learning of the considered impairments. The proposed approach supports both supervised and unsupervised learning strategies, showcasing its practical potential. Simulation results indicate that the proposed method successfully learns significant inaccuracies in both antenna locations and complex gains. Additionally, the proposed method outperforms the classical MUSIC algorithm in the DoA estimation task.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 17 of its 37 references that are in the map. First posted on arXiv 6 Nov 2024.

Builds on

17 of 37 references.

References · 17

  1. 2017An Introduction to Deep Learning for the Physical Layercited by 233
  2. 2020Model-Based Deep Learningcited by 141
  3. 2017Deep MIMO Detectioncited by 26
  4. 2019Massive MIMO Channel Estimation with an Untrained Deep Neural Networkcited by 21
  5. 2020Deep Networks for Direction-of-Arrival Estimation in Low SNRcited by 20
  6. 2020mpNet: variable depth unfolded neural network for massive MIMO channel estimationcited by 14
  7. 2023Learn to Rapidly and Robustly Optimize Hybrid Precodingcited by 11
  8. 2022Efficient Deep Unfolding for SISO-OFDM Channel Estimationcited by 8
  9. 2023SubspaceNet: Deep Learning-Aided Subspace Methods for DoA Estimationcited by 7
  10. 2023Model-Based End-to-End Learning for Multi-Target Integrated Sensing and Communication under Hardware Impairmentscited by 7
  11. 2023Semi-Supervised End-to-End Learning for Integrated Sensing and Communicationscited by 5
  12. 2023TransMUSIC: A Transformer-Aided Subspace Method for DOA Estimation with Low-Resolution ADCscited by 4
5 more
  1. 2023Model-based Deep Learning for Beam Prediction based on a Channel Chartcited by 4
  2. 2020Neural network approaches to point lattice decodingcited by 3
  3. 2022Three more Decades in Array Signal Processing Research: An Optimization and Structure Exploitation Perspectivecited by 3
  4. 2023Modeling and Analysis of OFDM-based 5G/6G Localization under Hardware Impairmentscited by 2
  5. 2024Probabilistic Positioning Via Ray Tracing With Noisy Angle of Arrival Measurementscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 1.

5 papers.

  1. 2025Near Field Localization via AI-Aided Subspace Methodscited by 1
  2. 2025HYPERDOA: Robust and Efficient DoA Estimation using Hyperdimensional Computingcited by 1
  3. 2024Differentiable High-Order Markov Models for Spectrum Predictioncited by 0
  4. 2025Model-based Implicit Neural Representation for sub-wavelength Radio Localizationcited by 0
  5. 2026Physically constrained unfolded multi-dimensional OMP for large MIMO systemscited by 0