Neural network based line of sight detection and angle estimation for positioning
Techniques are provide for neural network based positioning of a mobile device. An example method for determining a line of sight delay, an angle of arrival, or an angle of departure value includes receiving reference signal information, determining one or more windowed channel impulse responses based on the reference signal information and one or more window functions, processing the one or more windowed channel impulse responses with a neural network, and determining an output of the neural network.
1. A method for measuring a channel in a wireless communication system, comprising:
transmitting an indication of positioning signal processing capabilities including an indication of timing window uncertainty capabilities or an indication of bandwidth stitching capabilities;
receiving reference signal information;
determining one or more windowed channel impulse responses based on the reference signal information and one or more window functions;
processing the one or more windowed channel impulse responses with a neural network; and
determining an output of the neural network.
2. The method of claim 1 wherein the output of the neural network is at least one of a line of sight delay, an angle of arrival, or an angle of departure value.
3. The method of claim 2 wherein the output of the neural network includes an uncertainty value associated with at least one of the line of sight delay, the angle of arrival, or the angle of departure value.
4. The method of claim 1 wherein the output of the neural network is based on receiving the reference signal information via a line of sight path or a non-line of sight path.
5. The method of claim 1 wherein the reference signal information is at least one of a synchronization signal block (SSB), a channel state information reference signal (CSI-RS), a positioning reference signal (PRS), a sounding reference signal (SRS), a tracking reference signal (TRS), a demodulation reference signal (DMRS), and a physical random access channel (PRACH) signal.
6. The method of claim 1 wherein the one or more window functions include at least one of a Hamming window, a root raised cosine window, a B-spline window, or a Gaussian window.
7. The method of claim 1 wherein the reference signal information includes reference signal information for a transmit beam and a receive beam pair.
8. An apparatus, comprising:
a memory;
at least one transceiver;
at least one processor communicatively coupled to the memory and the at least one transceiver and configured to:
transmit an indication of positioning signal processing capabilities including an indication of timing window uncertainty capabilities or an indication of bandwidth stitching capabilities, receive reference signal information;
determine one or more windowed channel impulse responses based on the reference signal information and one or more window functions;
process the one or more windowed channel impulse responses with a neural network; and
determine an output of the neural network.
9. The apparatus of claim 8 wherein the output of the neural network is at least one of a line of sight delay, an angle of arrival, or an angle of departure value.
10. The apparatus of claim 9 wherein the output of the neural network includes an uncertainty value associated with at least one of the line of sight delay, the angle of arrival, or the angle of departure value.
11. The apparatus of claim 8 wherein the output of the neural network is based on receiving the reference signal information via a line of sight path or a non-line of sight path.
12. The apparatus of claim 8 wherein the reference signal information is at least one of a synchronization signal block (SSB), a channel state information reference signal (CSI-RS), a positioning reference signal (PRS), a sounding reference signal (SRS), a tracking reference signal (TRS), a demodulation reference signal (DMRS), and a physical random access channel (PRACH) signal.
13. The apparatus of claim 8 wherein the one or more window functions include at least one of a Hamming window, a root raised cosine window, a B-spline window, or a Gaussian window.
14. The apparatus of claim 8 wherein the reference signal information includes reference signal information for a transmit beam and a receive beam pair.