A method and system for autonomous control of spacecraft approaching operations based on online learning

Abstract

The invention relates to a method and system for autonomous control of spacecraft approaching operations based on online learning. Aiming at practical engineering problems such as line-of-sight constraints, approaching corridor constraints, and real-time online optimization of control performance in the spacecraft's approaching operation tasks, it is proposed A method for autonomous control technology of proximity operation based on online learning; the present invention comprises the following steps: firstly, based on the dual quaternion, the dynamic model of the pose integration of the spacecraft is established, and the pose motion is constrained by the dual quaternion It is described in the form of inequality; secondly, the reward function of online learning control is designed based on the properties of dual quaternions for the mission requirements of autonomous control of spacecraft proximity operations. Finally, under the framework of the dual quaternion, an online learning method is designed, so that the controller can gradually upgrade from a simple control strategy to a suboptimal controller using online data, so as to improve the mission execution ability of the spacecraft.

Description

technical field [0001] The invention relates to an autonomous control method and system for spacecraft proximity operation based on online learning, which is mainly used in tasks such as spacecraft rendezvous and docking, on-orbit supply maintenance, and coordination, and belongs to the technical field of spacecraft control. Background technique [0002] With the rapid development of aerospace technology, the diversity and complexity of spacecraft on-orbit tasks are increasing, and the mission carrier is gradually expanding from a single integrated large spacecraft system to a multi-spacecraft system. missions, derived from the emerging on-orbit missions represented by the proximity of spacecraft operations. The spacecraft proximity operation control technology is derived from important mission scenarios such as rendezvous and docking, on-orbit maintenance and replenishment. Due to factors such as flight safety, load characteristics, and mission requirements, on-orbit space...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the six-degree-of-freedom motion constraint problem caused by the optical load and the structure of the spacecraft body in the autonomous control task of the approaching operation of the spacecraft. The present invention provides an autonomous control method and equipment for the approaching operation of the spacecraft based on online learning. By designing the reward function related to the mission function, and using the online data to design the real-time learning law of the controller, the six-degree-of-freedom motion constraint problem in the spacecraft's near-operation mission is solved. Under the condition that the motion constraint is satisfied, the real-time learning Independently improve and optimize the performance of the controller, which improves the mission execution capability of the spacecraft control system of the control system

Images