Description

AoA estimation often loses its accuracy when the bounds of [-60°, +60°] are exceeded, which makes its potential applications limited. By learning the environment using machine learning methodologies, we can further expand the range of accurate results up to [-90°, +90°].

NOTE: Transfer learning for new environments supported with few samples.

Advantages

1. Improved accuracy
2. Resilient against NLOS

input: angle, CIR, FP_index, Phase_antenna1, phase_antenna2, etc.(channel information)
output: corrected_angle

Supported languages

1. Python / Tensorflow
2. C++ / Tensorflow Lite for Microcontrollers (TinyML)

Supported hardware

Machine learning model inference can be executed on the ultra-wideband (UWB) node, an edge device, or within the cloud. The training process must be conducted on a robust edge device or within a cloud environment.