Multiple Model Adaptive Estimator for Nonlinear System with Unknown Disturbance

Abstract

A multiple model adaptive estimator (MMAE) is presented for nonlinear systems with unknown disturbances. Multiple models are constructed with a set of process noise covariance matrices, such that the algorithm can adapt to different levels of unknown disturbances. The performance of the MMAE is analyzed for the considered system. It is proved that, under certain assumptions, the MMAE keeps the dynamics of its estimation error stable. A performance comparison among different estimators is carried out for space surveillance, where the position of a space target is estimated by using double line‐of‐sight measurements. Simulation studies illustrate that the presented algorithm outperforms the extended Kalman filter and the nonlinear robust filter.

Adaptive Iterated Extended KALMAN Filter for Relative Spacecraft Attitude and Position Estimation

“…However, the noise statistics of a practical system are often difficult to obtain [13,26,27], especially, for the considered system, as the measurement of the vision-based navigation sensor is sensitive to the jitter of the spacecraft and the illumination condition, and the characteristics of the measurement noise may be time-variant in the space mission. However, the noise statistics of a practical system are often difficult to obtain [13,26,27], especially, for the considered system, as the measurement of the vision-based navigation sensor is sensitive to the jitter of the spacecraft and the illumination condition, and the characteristics of the measurement noise may be time-variant in the space mission.…”

“…Furthermore, the performance of the state estimation depends on the statistical knowledge of the noises. However, the noise statistics of a practical system are often difficult to obtain , especially, for the considered system, as the measurement of the vision‐based navigation sensor is sensitive to the jitter of the spacecraft and the illumination condition, and the characteristics of the measurement noise may be time‐variant in the space mission. Since it is difficult to simulate the space environment on the ground, the in‐orbit characteristics of the sensor are not known exactly.…”