Neural network based line of sight detection for positioning

1. A method for determining a line of sight delay, an angle of arrival, or an angle of departure value, comprising:

receiving reference signal information;

determining a channel frequency response or a channel impulse response based on the reference signal information;

processing the channel frequency response or the channel impulse response with a neural network; and

determining the line of sight delay, the angle of arrival, or the angle of departure value based on an output of the neural network, wherein the output of the neural network is based at least on the channel frequency response or the channel impulse response input into the neural network.

2. The method of claim 1 wherein the reference signal information is a sounding reference signal measurement.

3. The method of claim 1 wherein the reference signal information is a channel state information reference signal measurement.

4. The method of claim 1 further comprising determining the neural network based at least in part of a positioning method used for determining a location of a mobile device.

5. The method of claim 4 further comprising determining the neural network based at least in part on a receiver configuration.

6. The method of claim 5 wherein the receiver configuration includes an antenna configuration and a phase coherence state of the antenna configuration.

7. The method of claim 1 wherein the neural network is one of a plurality of neural networks stored in a data structure.

8. The method of claim 1 further comprising determining a required desired accuracy associated with the output of the neural network, and wherein processing the channel impulse response with the neural network includes adapting one or more weights in the neural network based on the required desired accuracy.

9. The method of claim 1 wherein the output of the neural network includes a quality estimate.

10. The method of claim 9 wherein determining the line of sight delay, the angle of arrival, or the angle of departure value is based at least in part on the quality estimate.

11. An apparatus for determining a line of sight delay, an angle of arrival, or an angle of departure value, 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:

receive reference signal information;

determine a channel frequency response or a channel impulse response based on the reference signal information;

process the channel frequency response or the channel impulse response with a neural network; and

determine the line of sight delay, the angle of arrival, or the angle of departure value based on an output of the neural network, wherein the output of the neural network is based at least on the channel frequency response or the channel impulse response input into the neural network.

12. The apparatus of claim 11 wherein the reference signal information is a sounding reference signal measurement.

13. The apparatus of claim 11 wherein the reference signal information is a channel state information reference signal measurement.

14. The apparatus of claim 11 wherein the at least one processor is further configured to determine the neural network based at least in part on a positioning method used to determine a location of a mobile device.

15. The apparatus of claim 14 wherein the at least one processor is further configured to determine the neural network based at least in part on a configuration of the at least one transceiver.

16. The apparatus of claim 15 wherein the configuration of the at least one transceiver includes an antenna configuration and a phase coherence state of the antenna configuration.

17. The apparatus of claim 11 wherein the neural network is one of a plurality of neural networks stored in a data structure.

18. The apparatus of claim 11 wherein the at least one processor is further configured to determine a required desired accuracy associated with the line of sight delay and adapt one or more weights in the neural network based on the required desired accuracy.

19. The apparatus of claim 11 wherein the output of the neural network includes a quality estimate.

20. The apparatus of claim 19 wherein the at least one processor is further configured to determine the line of sight delay, the angle of arrival, or the angle of departure value based at least in part on the quality estimate.

21. A method, performed on a mobile device, for determining a line of sight delay, an angle of arrival, or an angle of departure value, comprising:

receiving reference signal information;

determining a channel frequency response or a channel impulse response based on the reference signal information;

processing the channel frequency response or the channel impulse response with a neural network; and

determining the line of sight delay, the angle of arrival, or the angle of departure value based on an output of the neural network, wherein the output of the neural network is based at least on the channel frequency response or the channel impulse response input into the neural network.

22. The method of claim 21 wherein the reference signal information is a positioning reference signal measurement.

23. The method of claim 21 further comprising determining the neural network based at least in part on a receiver configuration in the mobile device.

24. The method of claim 23 wherein the determining the neural network includes receiving neural network information from a network server.

25. The method of claim 23 wherein determining the neural network includes receiving an indication of a selected neural network from a list of neural networks available at the mobile device.

26. The method of claim 21 wherein the neural network is one of a plurality of neural networks stored in a data structure on the mobile device.