Neural Network Based Finite-Time Attitude Tracking Control of Spacecraft With Angular Velocity Sensor Failures and Actuator Saturation

This article investigates the finite-time attitude tracking control problem of spacecraft with angular velocity sensor failures and actuator saturation. A model-free angular velocity observer is proposed first to reconstruct the unmeasurable angular velocity in finite time. Invoking the reconstructed information, a saturated finite-time attitude tracking controller is then designed via the fast terminal sliding mode control technique, while the Legendre polynomial-based neural network is incorporated to approximate the unknown nonlinear dynamics. The finite-time stability of the closed-loop attitude tracking system from the proposed observer and the controller is proved despite the external disturbances. The main feature of the proposed controller is that it can accomplish the attitude tracking maneuver without model and angular velocity information. Numerical and experimental results are presented to verify the effectiveness of the proposed scheme.