Description

Real-world UWB configurations frequently involve NLoS connections. These links cause errors in the distance estimation. Machine learning techniques allow us to learn an environment and to correct these NLoS links such that the resulting distance is correct.

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

Advantages

1. Improved accuracy
2. Resilient against NLOS

input: distance, Channel Impulse Response (CIR), First Path index (FP_index), etc.(channel information)
output: corrected_distance

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.