Method for determining an angle of arrival, device, computer program product and non-volatile storage medium
The present disclosure relates to a method for determining an angle of arrival, AoA, of received radio frequency, RF, measurement signals. The method comprises obtaining measurement data based on the received RF measurement signals from an antenna array, wherein the RF measurement signals are representative of multiple frequency channels. The method further comprises determining power spectra, comprising determining at least one power spectrum for each of the multiple frequency channels by using the measurement data. The method further comprises providing a machine learning algorithm, which is pre-trained to determine an AoA based on power spectra of multiple frequency channels. The method further comprises determining the AoA of the received RF measurement signals by using the machine learning algorithm and the determined power spectra.
1. A method for determining an angle of arrival (AoA) of received radio frequency (RF) measurement signals, the method comprising:
obtaining measurement data based on the received RF measurement signals from an antenna array, wherein the RF measurement signals are representative of multiple frequency channels;
determining power spectra, comprising determining at least one power spectrum for each of the multiple frequency channels by using the measurement data;
providing a machine learning algorithm, which is pre-trained to determine an AoA based on power spectra of multiple frequency channels; and
determining the AoA of the received RF measurement signals by using the machine learning algorithm and the determined power spectra.
2. The method according to claim 1 , wherein each power spectrum is a power spectral density (PSD).
3. The method according to claim 1 wherein determining the power spectra comprises performing power spectral density (PSD)-based signal processing.
4. The method according to claim 3 , wherein the PSD-based signal processing comprises at least one of a multiple signal classification (MUSIC) algorithm, a propagator direct data acquisition (PDDA) algorithm or a self-signal suppression (SSS) algorithm.
5. The method according to claim 1 , wherein the method further comprises:
determining a quality indicator by using the measurement data, wherein the quality indicator is representative of an integrity of the received RF measurement signals, and
determining the AoA of the received RF measurement signals by using the machine learning algorithm, the determined power spectra and the quality indicator.
6. The method according to claim 5 , wherein the quality indicator comprises at least one of a received signal strength indicator (RSSI), a channel state information (CSI), a cyclic redundancy check (CRC), result, a forward correction error (FEC), result or a noise analysis result of a constant tone extension.
7. The method according to claim 1 , wherein the measurement data comprises in-phase and quadrature (IQ) data.
8. The method according to claim 1 , wherein an amount of the determined power spectra is dependent on at least one of an amount of the multiple frequency channels, a number of antenna rows of the antenna array, or a polarization of the antenna array.
9. The method according to claim 1 , wherein the machine learning algorithm comprises at least one of a classification and regression tree (CART) algorithm, a convolutional neural networks (CNN), a multilayer perceptron (MLP) neural network, a random forest algorithm, a clustering algorithm, or a support support-vector machine (SVM) algorithm.
10. The method according to claim 1 , wherein the method further comprises:
concatenating the determined power spectra, and
determining the AoA of the received RF measurement signals by using the machine learning algorithm and the concatenated power spectra.
11. The method according to claim 1 , wherein the antenna array is positioned in a first environment when the RF measurement signals are received, and the machine learning algorithm is pre-trained by using pre-train data, wherein the pre-train data is determined based on the antenna array and the first environment.
12. The method according to claim 1 , wherein the machine learning algorithm is pre-trained by using pre-train data, wherein the pre-train data is determined based on multiple antenna arrays and multiple second environments.
13. A device comprising:
a processor operable to:
obtain measurement data based on received radio frequency (RF) measurement signals from an antenna array, wherein the RF measurement signals are representative of multiple frequency channels, and
determine power spectra, comprising determining at least one power spectrum for each of the multiple frequency channels by using the measurement data, and
wherein the device further comprises at least one tangible, non-transitory, computer-readable media storing a machine learning algorithm that, when executed by the processor, causes the device to determine an angle of arrival (AoA) based on power spectra of multiple frequency channels, and wherein the processor is operable to determine the AoA of the received RF measurement signals by using a pre-trained instance of the machine learning algorithm and the determined power spectra.
14. At least one tangible, non-transitory, computer-readable media storing instructions which, when executed by a computing device, cause the computing device to perform operations comprising:
obtaining measurement data based on received radio frequency (RF) measurement signals from an antenna array, wherein the RF measurement signals are representative of multiple frequency channels;
determining power spectra, comprising determining at least one power spectrum for each of the multiple frequency channels by using the measurement data; and
determining an angle of arrival (AoA) of the received RF measurement signals by using a machine learning algorithm and the determined power spectra, wherein the machine learning algorithm is pre-trained to determine an AoA based on power spectra of the multiple frequency channels.