3-D Position and Velocity Estimation in 5G mmWave CRAN with Lens Antenna Arrays

Yang, Jie; Jin, Shi; Han, Yu; Matthaiou, Michail; Zhu, Yongxu

doi:10.1109/vtcfall.2019.8891333

Cited by 9 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…T is an unknown fourdimensional vector of location and velocity magnitude of the scatterer. 1 Replacing the noise-free parameters…”

Section: B Scatterer Localizationmentioning

confidence: 99%

“…Finally, we obtain the estimate x by using the model in (23). In practice, the training dataset is constructed during an offline phase, in which a site survey is conducted to collect the vectors of the received signals of all RRHs from different UEs at numerous reference points of known locations, as given in (1). Then, the channel parameters are extracted from the received signals with signal processing methods.…”

Section: A Nn-wlsmentioning

confidence: 99%

“…We define the dominant part as the unknown fixed error and the fluctuating part as the Gaussian random error. We define three dominant error settings: (1) VI. The performance of the proposed NN-WLS outperforms the WLS algorithm and the black box NN in the given simulation scenarios.…”

Section: B Nn-assisted Wls Localizationmentioning

confidence: 99%

See 2 more Smart Citations

Model-Based Learning Network for 3-D Localization in mmWave Communications

Yang

Jin

Wen

et al. 2021

IEEE Trans. Wireless Commun.

Self Cite

View full text Add to dashboard Cite

Millimeter-wave (mmWave) cloud radio access networks (CRANs) provide new opportunities for accurate cooperative localization, in which large bandwidths and antenna arrays and increased densities of base stations enhance the delay and angular resolution. This study considers the joint location and velocity estimation of user equipment (UE) and scatterers in a three-dimensional mmWave CRAN architecture. Several existing works have achieved satisfactory results by using neural networks (NNs) for localization. However, the black box NN localization method has limited robustness and accuracy and relies on a prohibitive amount of training data to increase localization accuracy. Thus, we propose a model-based learning network for localization to address these problems. In comparison with the black box NN, we combine NNs with geometric models. Specifically, we first develop an unbiased weighted least squares (WLS) estimator by utilizing hybrid delay and angular measurements, which determine the location and velocity of the UE in only one estimator, and can obtain the location and velocity of scatterers further. The proposed estimator can achieve the Cramér-Rao lower bound under small measurement noise and outperforms other state-of-the-art methods. Second, we establish a NN-assisted localization method called NN-WLS by replacing the linear approximations in the proposed WLS localization model with NNs to learn the higher-order error components, thereby enhancing the performance of the estimator, especially in a large noise environment. The solution possesses the powerful learning ability of the NN and the robustness of the proposed geometric model. Moreover, the ensemble learning is applied to improve the localization accuracy further. Comprehensive simulations show that the proposed NN-WLS is superior to the benchmark methods in terms of localization accuracy, robustness, and required time resources.

show abstract

“…T is an unknown fourdimensional vector of location and velocity magnitude of the scatterer. 1 Replacing the noise-free parameters…”

Section: B Scatterer Localizationmentioning

confidence: 99%

Section: A Nn-wlsmentioning

confidence: 99%

See 1 more Smart Citation

Model-Based Learning Network for 3-D Localization in mmWave Communications

Yang

Jin

Wen

et al. 2021

IEEE Trans. Wireless Commun.

Self Cite

View full text Add to dashboard Cite

show abstract

“…T is an unknown four-dimensional vector of location and velocity magnitude of the scatterer. 1 Replacing the noise-free parameters (31) by the noisy measurements {r s n1,l , ṙs n1,l , φ s n,l , θ s n,l } and estimated {u, u} results in the error vector…”

Section: B Scatterer Localizationmentioning

confidence: 99%

Model-based Learning Network for 3-D Localization in mmWave Communications

Yang

Jin

Wen

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Millimeter-wave (mmWave) cloud radio access networks (CRANs) provide new opportunities for accurate cooperative localization, in which large bandwidths and antenna arrays and increased densities of base stations enhance the delay and angular resolution. This study considers the joint location and velocity estimation of user equipment (UE) and scatterers in a three-dimensional mmWave CRAN architecture.Several existing works have achieved satisfactory results by using neural networks (NNs) for localization.However, the black box NN localization method has limited robustness and accuracy and relies on a prohibitive amount of training data to increase localization accuracy. Thus, we propose a model-based learning network for localization to address these problems. In comparison with the black box NN, we combine NNs with geometric models. Specifically, we first develop an unbiased weighted least squares (WLS) estimator by utilizing hybrid delay and angular measurements, which determine the location and velocity of the UE in only one estimator, and can obtain the location and velocity of scatterers further.The proposed estimator can achieve the Cramér-Rao lower bound under small measurement noise and outperforms other state-of-the-art methods. Second, we establish a NN-assisted localization method called NN-WLS by replacing the linear approximations in the proposed WLS localization model with NNs to learn the higher-order error components, thereby enhancing the performance of the estimator, especially in a large noise environment. The solution possesses the powerful learning ability of the NN and the robustness of the proposed geometric model. Moreover, the ensemble learning is applied to improve the localization accuracy further. Comprehensive simulations show that the proposed NN-WLS is superior to the benchmark methods in terms of localization accuracy, robustness, and required time resources.

show abstract

“…We intentionally consider a 2D model in order not to complicate too much the notation. Nevertheless, the extension to a 3D model is straightforward, as done in[47],[69].Authorized licensed use limited to: Universita degli Studi di Bologna. Downloaded on September 24,2021 at 15:38:32 UTC from IEEE Xplore.…”

mentioning

confidence: 99%