An adaptive gradient descent attitude estimation algorithm based on a fuzzy system for UUVs

An adaptive gradient descent algorithm (AGDA) based on a fuzzy system is proposed to improve the attitude estimation accuracy and adaptability of unmanned underwater vehicles (UUVs) under various ocean environ-ments. First, the algorithm uses current and historical gyroscope data to predict the quaternion of the current moment. Then, the accelerometer data are calibrated according to the predicted quaternion, and the gradient direction is obtained. At the same time, a fuzzy system generated by the genetic algorithm is used to solve the adaptive coefficient. Finally, the algorithm uses the gradient descent method to achieve data fusion, compen-sating for the accumulated error of the gyroscope. The experimental results show that the prediction of the quaternion and the adaptive coefficient can effectively improve the accuracy and environmental adaptability of the algorithm, and the proposed algorithm has better dynamic and static performances than traditional attitude estimation algorithms.

Automated summary

An adaptive gradient descent algorithm (AGDA) based on a fuzzy system is proposed to improve the attitude estimation accuracy and adaptability of unmanned underwater vehicles (UUVs) under various ocean environments. The algorithm predicts the quaternion using gyroscope data, calibrates accelerometer data based on the predicted quaternion, and utilizes a fuzzy system generated by genetic algorithm to solve the adaptive coefficient. The algorithm achieves data fusion using gradient descent to compensate for the accumulated error of the gyroscope.