HYPERDOA: Robust and Efficient DoA Estimation using Hyperdimensional Computing

2025-10-12

AI Summary

Direction-of-arrival (DoA) estimation suffers from low accuracy under low signal-to-noise ratio (SNR), while deep learning–based approaches exhibit poor energy efficiency and limited interpretability. Method: This paper proposes HYPERDOA, a hyperdimensional computing–based framework that reformulates DoA estimation as a pattern recognition task. It integrates mean spatial lagged autocorrelation with spatial smoothing for robust feature extraction and leverages the algebraic transparency of hypervectors to avoid the computational overhead and opacity of conventional matrix decomposition and deep neural networks. Contribution/Results: HYPERDOA achieves superior robustness and significantly improves estimation accuracy—especially for coherent sources and low-SNR scenarios. Experiments demonstrate a 35.39% reduction in angular error compared to state-of-the-art methods under low SNR. When deployed on an NVIDIA Jetson Xavier NX platform, it reduces inference energy consumption by 93%, delivering high accuracy, ultra-low power consumption, and strong model interpretability.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Hardware-aware ML
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Direction of Arrival (DoA) estimation techniques face a critical trade-off, as classical methods often lack accuracy in challenging, low signal-to-noise ratio (SNR) conditions, while modern deep learning approaches are too energy-intensive and opaque for resource-constrained, safety-critical systems. We introduce HYPERDOA, a novel estimator leveraging Hyperdimensional Computing (HDC). The framework introduces two distinct feature extraction strategies -- Mean Spatial-Lag Autocorrelation and Spatial Smoothing -- for its HDC pipeline, and then reframes DoA estimation as a pattern recognition problem. This approach leverages HDC's inherent robustness to noise and its transparent algebraic operations to bypass the expensive matrix decompositions and ``black-box'' nature of classical and deep learning methods, respectively. Our evaluation demonstrates that HYPERDOA achieves ~35.39% higher accuracy than state-of-the-art methods in low-SNR, coherent-source scenarios. Crucially, it also consumes ~93% less energy than competing neural baselines on an embedded NVIDIA Jetson Xavier NX platform. This dual advantage in accuracy and efficiency establishes HYPERDOA as a robust and viable solution for mission-critical applications on edge devices.

Problem

• Addresses low-SNR DoA estimation accuracy limitations
• Reduces energy consumption for embedded edge devices
• Replaces opaque methods with transparent pattern recognition

Innovation

• Hyperdimensional Computing reframes DoA estimation as pattern recognition
• Uses Mean Spatial-Lag Autocorrelation and Spatial Smoothing features
• Provides noise robustness and transparent operations bypassing matrix decompositions