Adaptive Attitude Estimation Using a Hybrid Model-Learning Approach. (arXiv:2207.06903v1 [eess.SP])

Attitude determination using the smartphone's inertial sensors poses a major
challenge due to the sensor low-performance grade and variate nature of the
walking pedestrian. In this paper, data-driven techniques are employed to
address that challenge. To that end, a hybrid deep learning and model based
solution for attitude estimation is proposed. Here, classical model based
equations are applied to form an adaptive complementary filter structure.
Instead of using constant or model based adaptive weights, the accelerometer
weights in each axis …

arxiv attitude hybrid learning