Summary
Systems that combine communication and sensing need to figure out where signals come from to send their beams accurately. The authors compared traditional and deep learning methods to see which works best for fast and accurate direction finding in real time. They found that while deep learning methods are much faster than traditional ones at estimating direction, the overall speed is often limited by the next step, which involves complex math for shaping beams. One particular deep learning model, called RCNN, struck a good balance of speed and accuracy, suggesting it could be useful in real-time systems. The authors suggest future work should look into simpler beam-shaping methods to speed things up even more.
What this means in practice
- •For wireless system designers: Choose and integrate direction-finding methods that balance speed and accuracy for real-time ISAC beamforming systems.
- •For signal processing engineers: Develop beamforming algorithms that reduce or avoid computationally intensive singular value decomposition to improve latency.
Abstract
Integrated Sensing and Communication (ISAC) systems rely on accurate Direction-of-Arrival (DoA) estimation for effective beamforming and spectral-efficiency enhancement. While numerous classical and deep-learning-based DoA estimation methods have been reported in the literature, their suitability for real-time ISAC operation remains insufficiently understood because practical deployment requires consideration of both estimation accuracy and computational latency. This paper presents a unified evaluation framework for systematically comparing classical and learning-based DoA estimators within an ISAC beamforming pipeline. Representative classical and learning-based DoA estimators, together with an ensemble architecture, are integrated with Singular Value Decomposition (SVD)-based beamforming and evaluated under identical operating conditions. The impact of DoA estimation accuracy, inference latency, beamforming-weight generation time, and resulting effective spectral efficiency is investigated. Results show that different estimators occupy distinct operating points in the accuracy-latency-performance design space. Although learning-based approaches substantially reduce estimation time compared with MUSIC, the overall processing latency increasingly becomes dominated by the computational cost of SVD-based beamforming. Among the evaluated methods, the Regression Convolutional Neural Network (RCNN) exhibits a favorable balance between estimation accuracy, computational efficiency, and beamforming performance, making it a promising candidate for real-time ISAC deployment. The findings further suggest that future low-latency ISAC systems may benefit from beamforming strategies that reduce or avoid computationally intensive SVD-based beamforming-weight generation.