Neural network augmentation for wireless channel estimation and tracking
A method performed by a communication device includes generating an initial channel estimate of a channel for a current time step with a Kalman filter based on a first signal received at the communication device. The method also includes inferring, with a neural network, a residual of the initial channel estimate of the current time step. The method further includes updating the initial channel estimate of the current time step based on the residual.
1. A method performed by a communication device, comprising:
generating an initial channel estimate of a channel for a current time step with a Kalman filter based on a first signal received at the communication device;
inferring, with a neural network, a residual of the initial channel estimate of the current time step; and
updating the initial channel estimate of the current time step based on the residual.
2. The method of claim 1 , in which:
the initial channel estimate of the current time step comprises a mean and a covariance; and
the residual comprises a residual mean based on the mean of the initial channel estimate and a residual covariance based on the covariance of the initial channel estimate.
3. The method of claim 1 , further comprising generating the initial channel estimate of the current time step and inferring the residual based on a channel observation of the current time step.
4. The method of claim 3 , further comprising generating the channel observation from a pilot symbol or a data symbol, in which a waveform of the pilot symbol or the data symbol is known from decoding of a previous pilot symbol or a previous data symbol.
5. The method of claim 3 , further comprising generating the channel observation based on a synthetic pilot estimate in an absence of a received pilot symbol.
6. The method of claim 1 , further comprising:
generating an actual channel estimate based on updating the initial channel estimate; and
decoding a second signal received on the channel based on the actual channel estimate.
7. The method of claim 1 , further comprising generating the initial channel estimate for the current time step based on an actual channel estimate from a previous time step.
8. The method of claim 1 , in which the neural network is a recurrent neural network.
9. An apparatus at a communication device, comprising:
a processor;
a memory coupled with the processor; and
instructions stored in the memory and operable, when executed by the processor, to cause the apparatus:
to generate an initial channel estimate of a channel for a current time step with a Kalman filter based on a first signal received at the communication device;
to infer, with a neural network, a residual of the initial channel estimate of the current time step; and
to update the initial channel estimate of the current time step based on the residual.
10. The apparatus of claim 9 , in which:
the initial channel estimate of the current time step comprises a mean and a covariance; and
the residual comprises a residual mean based on the mean of the initial channel estimate and a residual covariance based on the covariance of the initial channel estimate.
11. The apparatus of claim 9 , in which execution of the instructions further cause the apparatus to generate the initial channel estimate of the current time step and inferring the residual based on a channel observation of the current time step.
12. The apparatus of claim 11 , in which execution of the instructions further cause the apparatus to generate the channel observation from a pilot symbol or a data symbol, in which a waveform of the pilot symbol or the data symbol is known from decoding of a previous pilot symbol or a previous data symbol.
13. The apparatus of claim 11 , in which execution of the instructions further cause the apparatus to generate the channel observation based on a synthetic pilot estimate in an absence of a received pilot symbol.
14. The apparatus of claim 9 , in which execution of the instructions further cause the apparatus:
to generate an actual channel estimate based on updating the initial channel estimate; and
to decode a second signal received on the channel based on the actual channel estimate.
15. The apparatus of claim 9 , in which execution of the instructions further cause the apparatus to generate the initial channel estimate for the current time step based on an actual channel estimate from a previous time step.
16. The apparatus of claim 9 , in which the neural network is a recurrent neural network.
17. A non-transitory computer-readable medium having program code recorded thereon at a communication device, the program code executed by a processor and comprising:
program code to generate an initial channel estimate of a channel for a current time step with a Kalman filter based on a first signal received at the communication device;
program code to infer, with a neural network, a residual of the initial channel estimate of the current time step; and
program code to update the initial channel estimate of the current time step based on the residual.
18. The non-transitory computer-readable medium of claim 17 , in which:
the initial channel estimate of the current time step comprises a mean and a covariance; and
the residual comprises a residual mean based on the mean of the initial channel estimate and a residual covariance based on the covariance of the initial channel estimate.
19. The non-transitory computer-readable medium of claim 17 , in which the program code further comprises program code to generate the initial channel estimate of the current time step and inferring the residual based on a channel observation of the current time step.
20. The non-transitory computer-readable medium of claim 19 , in which the program code further comprises program code to generate the channel observation from a pilot symbol or a data symbol, in which a waveform of the pilot symbol or the data symbol is known from decoding of a previous pilot symbol or a previous data symbol.
21. The non-transitory computer-readable medium of claim 19 , in which the program code further comprises program code to generate the channel observation based on a synthetic pilot estimate in an absence of a received pilot symbol.
22. The non-transitory computer-readable medium of claim 17 , in which the program code further comprises:
program code to generate an actual channel estimate based on updating the initial channel estimate; and
program code to decode a second signal received on the channel based on the actual channel estimate.
23. The non-transitory computer-readable medium of claim 17 , in which the program code further comprises program code to generate the initial channel estimate for the current time step based on an actual channel estimate from a previous time step.
24. The non-transitory computer-readable medium of claim 17 , in which the neural network is a recurrent neural network.
25. An apparatus at a communication device, comprising:
means for generating an initial channel estimate of a channel for a current time step with a Kalman filter based on a first signal received at the communication device;
means for inferring, with a neural network, a residual of the initial channel estimate of the current time step; and
means for updating the initial channel estimate of the current time step based on the residual.
26. The apparatus of claim 25 , in which:
the initial channel estimate of the current time step comprises a mean and a covariance; and
the residual comprises a residual mean based on the mean of the initial channel estimate and a residual covariance based on the covariance of the initial channel estimate.
27. The apparatus of claim 25 , further comprising means for generating the initial channel estimate of the current time step and inferring the residual based on a channel observation of the current time step.
28. The apparatus of claim 27 , further comprising means for generating the channel observation from a pilot symbol or a data symbol, in which a waveform of the pilot symbol or the data symbol is known from decoding of a previous pilot symbol or a previous data symbol.
29. The apparatus of claim 27 , further comprising means for generating the channel observation based on a synthetic pilot estimate in an absence of a received pilot symbol.
30. The apparatus of claim 25 , further comprising:
means for generating an actual channel estimate based on updating the initial channel estimate; and
means for decoding a second signal received on the channel based on the actual channel estimate.