An intelligent control method for vertical recovery of launch vehicle based on deep reinforcement learning

Abstract

An intelligent control method for vertical recovery of launch vehicles based on deep reinforcement learning, researching the method of realizing autonomous intelligent control of launch vehicles. The main research is to solve the problem of vertical recovery attitude control and trajectory planning of launch vehicle by using intelligent control. For the aerospace industry, the autonomous intelligence of spacecraft is undoubtedly of great significance in terms of saving labor costs and reducing human errors. Establish the vertical recovery simulation model of the launch vehicle, and establish the corresponding Markov decision-making process, including the state space, action space, state transition equation, and reward function, use the neural network to fit the mapping relationship between the environment and the behavior of the agent, and Training is carried out so that the launch vehicle can recover autonomously and controllably using the trained neural network. This project can not only provide technical support for spacecraft orbit intelligent planning technology, but also provide a simulation verification platform for offensive and defensive confrontation between spacecraft based on deep reinforcement learning.

Description

technical field [0001] The invention relates to a vertical recovery control method of a carrier rocket based on deep reinforcement learning, which is applicable to the field of carrier rocket guidance and control. Background technique [0002] The standard reinforcement learning framework is that an agent continuously interacts with its environment in discrete time. It mainly consists of four elements: reward and punishment feedback function, value function, strategy selection, and interactive environment. like figure 2 shown. [0003] The process of the agent interacting with the environment is as follows: (1) The agent (Agent) perceives the current state of the environment (state); (2) According to the current state and the reward value (reward), the agent selects an action (action) and executes it. The action; (3) When the action selected by the agent acts on the environment, the environment is transferred to a new state and a new reward is given; (4) The agent calculat...

AI Technical Summary

Problems solved by technology

Under such a major premise, the trajectory planning and control of the launch vehicle is very dependent on manpower, and any human error may cause huge losses

Images