Adaptive Attitude Estimation Using a Hybrid Model-Learning Approach

Attitude determination using the smartphone's inertial sensors poses a major challenge due to the sensor's low-performance grade and the varying nature of the walking pedestrian. In this article, data-driven techniques are employed to address that challenge. To that end, a hybrid deep learning (DL) and model-based solution for attitude estimation is proposed. Here, classical model-based equations are applied to form an adaptive complementary filter (CF) structure. Instead of using constant or model-based adaptive weights, the accelerometer weights in each axis are determined by a unique neural network (NN). The performance of the proposed hybrid approach is evaluated relative to popular model-based approaches using experimental data.