Multi-Branch DNN and CRLB-Ratio-Weight Fusion for Enhanced DOA Sensing via a Massive H$^2$AD MIMO Receiver

2025-06-29

AI Summary

For 6G green large-scale H²AD MIMO systems, DOA estimation faces challenges including high computational complexity, strong reliance on prior knowledge, and frequent spurious solutions under low SNR. To address these, this paper proposes two synergistic fusion methods: (1) CRLB-ratio Weighted Fusion (CRLB-ratio-WF), which approximates the inverse Cramér–Rao Lower Bound (CRLB) using the reciprocal of antenna number—significantly reducing prior requirements while matching conventional CRLB-weighted performance; and (2) a Multi-Branch Deep Neural Network (MBDNN), employing subarray-specific branches to extract localized features and a shared regression module for robust angular fusion. Experiments demonstrate that MBDNN improves DOA estimation accuracy by an order of magnitude at SNR = −15 dB. The overall framework achieves low computational complexity, high estimation accuracy, and strong adaptability to weak prior information.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Mixture of Experts (MoE)
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

As a green MIMO structure, massive H$^2$AD is viewed as a potential technology for the future 6G wireless network. For such a structure, it is a challenging task to design a low-complexity and high-performance fusion of target direction values sensed by different sub-array groups with fewer use of prior knowledge. To address this issue, a lightweight Cramer-Rao lower bound (CRLB)-ratio-weight fusion (WF) method is proposed, which approximates inverse CRLB of each subarray using antenna number reciprocals to eliminate real-time CRLB computation. This reduces complexity and prior knowledge dependence while preserving fusion performance. Moreover, a multi-branch deep neural network (MBDNN) is constructed to further enhance direction-of-arrival (DOA) sensing by leveraging candidate angles from multiple subarrays. The subarray-specific branch networks are integrated with a shared regression module to effectively eliminate pseudo-solutions and fuse true angles. Simulation results show that the proposed CRLB-ratio-WF method achieves DOA sensing performance comparable to CRLB-based methods, while significantly reducing the reliance on prior knowledge. More notably, the proposed MBDNN has superior performance in low-SNR ranges. At SNR $= -15$ dB, it achieves an order-of-magnitude improvement in estimation accuracy compared to CRLB-ratio-WF method.

Problem

• Design low-complexity DOA fusion for massive H2AD MIMO
• Reduce prior knowledge dependence in CRLB-ratio fusion
• Enhance DOA sensing accuracy in low-SNR scenarios

Innovation

• Lightweight CRLB-ratio-weight fusion method
• Multi-branch DNN for DOA sensing
• Eliminates real-time CRLB computation