Adaptive Attitude Estimation Using a Hybrid Model-Learning Approach
This work addresses attitude estimation for pedestrian walking scenarios using smartphones, representing an incremental improvement over existing methods.
The paper tackled the challenge of accurate attitude estimation using smartphone inertial sensors by proposing a hybrid deep learning and model-based solution, achieving improved performance relative to popular model-based approaches in experimental evaluations.
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 are determined by a unique neural network. The performance of the proposed hybrid approach is evaluated relative to popular model based approaches using experimental data.