Multi-Frequency Data Fusion for Attitude Estimation Based on Multi-Layer Perception and Cubature Kalman Filter

Abstract

This paper proposes multi-frequency inertial and visual data fusion for attitude estimation. The proposed strategy is based on the locally weighted linear regression (LWLR), multi-layer perception (MLP), and cubature Kalman filter (CKF). First, we analyze the discrepant-frequency and the attitude divergence problems. Second, we construct the filter equation for the visual and inertial data and attitude differential equation for inertial-only data, which are used to estimate the attitude in time series. Third, we employ LWLR to compute the vision discrepancies between actual vision data and fitted vision data. The vision discrepancy is used as the input of MLP training. In MLP, the discrepancy is used as weights of the sums through the activation function of the hidden layer. To address the divergence problem, which is inherent in a multifrequency fusion, the MLP is utilized to compensate for the inertial-only data. Finally, experimental results on different environments of pseudo-physical simulations show the superior performance of the proposed method in terms of the accuracy of attitude estimation and divergence capability.

Data Selection for Training the Neural Fuser Applied to Autonomous UAV Navigation

“…MLP is widely used by the scientific community, designed to solve linearly inseparable problems, which could not be solved by the single layer perceptron network. Due to their robustness, MLPs are also applied in data fusion [7,35].…”

The Integration of Rotary MEMS INS and GNSS with Artificial Neural Networks

“…e ANNs (artificial neural networks) were widely employed to mimic the error pattern of the INS during GNSS outages in recent years, due to their ability for the nonlinear mapping between inputs and outputs without the predefined mathematical model [11]. Different ANNs, such as MLP (multiplayer perceptron) [12], RBF (radial basis function) [13,14], and ANFIS (adaptive neuro-fuzzy inference system) [15,16], were investigated for navigations in previous studies, and they have been proved to be able to reduce the navigation errors. e limitation of MLP is that it is time-consuming to obtain the optimal number for the hidden layer and neurons [12].…”

“…Different ANNs, such as MLP (multiplayer perceptron) [12], RBF (radial basis function) [13,14], and ANFIS (adaptive neuro-fuzzy inference system) [15,16], were investigated for navigations in previous studies, and they have been proved to be able to reduce the navigation errors. e limitation of MLP is that it is time-consuming to obtain the optimal number for the hidden layer and neurons [12]. In contrast, the RBF could dynamically generate the best internal structure due to its dynamic property [13].…”