Neural Network Angle of Arrival Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing Angle of Arrival and Angle of Departure algorithms, such as MUSIC, are computationally intensive and require accurate antenna array representations, making them inefficient for non-ideal arrays and impaired signals.
Innovation Solution
A neural network-based system that uses I and Q samples from an antenna array to calculate angles of arrival and departure, employing convolutional neural networks to process these samples and produce outputs indicative of azimuth and elevation angles, capable of handling non-ideal arrays and compensating for carrier frequency offsets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional MUSIC algorithm is used to determine angle of arrival, then measurement precision is improved, but computational complexity increases significantly
Solution Approach 1:
The patent replaces the traditional MUSIC algorithm's iterative spectral search mechanism with a neural network-based direct estimation system. The neural network is trained offline to learn the mapping between received signal characteristics and angle parameters, enabling direct angle estimation without iterative computation during runtime. This substitution dramatically reduces real-time computational complexity while maintaining measurement precision.
2Measurement precision
If traditional MUSIC algorithm is used to determine angle of arrival, then measurement precision is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary training of the neural network offline using labeled data containing various angle scenarios. This preliminary action pre-computes the optimal decision boundaries and feature mappings, so that during runtime, the system only needs to perform a single forward propagation through the trained network. This eliminates the need for time-consuming iterative spectral searches during actual angle determination, significantly reducing processing time while maintaining accuracy.
3Measurement precision
If traditional algorithms are used for angle determination, then accuracy is maintained, but adaptability to non-ideal conditions deteriorates
Solution Approach 1:
The patent incorporates multiple impaired signal conditions and non-ideal antenna array configurations into the training data with varying parameters. By training the neural network on diverse data samples with different noise levels, carrier frequency offsets, and array imperfections, the system learns to generalize and adapt to non-ideal conditions. This parameter variation during training enhances the model's robustness without compromising accuracy in ideal conditions.
Data Source
AI summary
A system and method of determining the angle of arrival or departure using a neural network is disclosed. The system collects a plurality of I and Q samples as a packet containing a constant tone extension is being received. The I and Q samples are used to form I and Q arrays, which are used as the input to the neural network. The neural network produces a first output representative of the azimuth angle and a second output representative of the elevation angle. In certain embodiments, the neural network is capable of detecting a plurality of angles, where, for each angle, there are three outputs, a first output representative of the azimuth angle, a second output representative of the elevation angle and a third output representative of the relative amplitude. In some embodiments, the neural network is configured to determine the carrier frequency offset of an incoming signal as well.