Neural Augmentation of Kalman Filter with Hypernetwork for Channel Tracking
This work addresses channel tracking in wireless communications, offering a novel method that generalizes better than existing approaches like LSTM, though it is incremental in combining Kalman filters with neural networks.
The paper tackles the problem of channel tracking with varying dynamics by proposing Hypernetwork Kalman Filter (HKF), which adapts to different dynamics using neural networks, achieving around 2dB gain over genie Kalman filter at high Doppler values and matching performance with genie information across a wide range.
We propose Hypernetwork Kalman Filter (HKF) for tracking applications with multiple different dynamics. The HKF combines generalization power of Kalman filters with expressive power of neural networks. Instead of keeping a bank of Kalman filters and choosing one based on approximating the actual dynamics, HKF adapts itself to each dynamics based on the observed sequence. Through extensive experiments on CDL-B channel model, we show that the HKF can be used for tracking the channel over a wide range of Doppler values, matching Kalman filter performance with genie Doppler information. At high Doppler values, it achieves around 2dB gain over genie Kalman filter. The HKF generalizes well to unseen Doppler, SNR values and pilot patterns unlike LSTM, which suffers from severe performance degradation.