A Data-Driven DOA Estimation Based Target Localization for Internet of Unmanned System
- 21 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. PP, 1
Abstract
With the rapid development of autonomous unmanned systems, the internet of unmanned agents (IUA) has emerged as a prominent research field. Direction of Arrival (DOA) estimation enables intelligent base stations (IBS) to detect the direction of unmanned device, facilitating essential functions such as target localization and tracking, and cooperative navigation, significantly enhancing the environmental perception capabilities and task execution efficiency of IUA systems. However,the traditional DOA estimation algorithms in practical complex electromagnetic mutual coupling environments are computationally intensive, incompatible with IUA’s high real-time requirements. To address these challenges, this paper proposes a data-driven (DD) DOA estimation method for unmanned device localization in IUA. The IUA localization system comprises four IBS equipped with uniform linear arrays (ULAs). Device localization is achieved through DOA estimates from these four IBS. A Deep Learning (DL) is proposed to jointly address two key challenges: IUA’s demand for real-time algorithm performance and mutual coupling effects between IBS sensors. A novel DL architecture is designed to estimate off-grid angle parameters and mutual coupling coefficients. The framework incorporates two learnable modules, one focusing on mutual coupling coefficients and another aimed at precise DOA estimation and associated confidence levels. The target unmanned device position is estimated using the least squares method applied to the DOA measurements from all IBSs. The proposed DL-based algorithm surpasses existing methods while maintaining low computational complexity. Extensive simulations demonstrate the high performance and real-time capabilities of the DD-based solution.Keywords
Funding Information
- Hainan Province Science and Technology Special Fund (ZDYF2023GXJS159, ZDYF2023GXJS168)
This publication has 56 references indexed in Scilit:
- Scheduling Techniques for Liver Segmentation: ReduceLRonPlateau vs OneCycleLR2022
- A survey on modern trainable activation functionsNeural Networks, 2021
- Natural Language Processing2020
- Comparative Study of Convolution Neural Network’s Relu and Leaky-Relu Activation Functions2019
- Real-valued DOA estimation for uniform linear array with unknown mutual couplingSignal Processing, 2012
- Acoustic vector-sensor array processingIEEE Transactions on Signal Processing, 1994
- ESPRIT-estimation of signal parameters via rotational invariance techniquesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Performance analysis of Root-MusicIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Beamforming: a versatile approach to spatial filteringIEEE ASSP Magazine, 1988
- A Mathematical Theory of Linear ArraysBell System Technical Journal, 1943