Multi-aircraft formation control optimization algorithm based on reinforcement learning and virtual navigation-following method

The invention belongs to the technical field of unmanned aerial vehicle control, and particularly relates to a multi-aerial vehicle formation control optimization algorithm based on reinforcement learning and a virtual navigation-following method. The robustness of a traditional navigation-following method is very dependent on a navigator, and the problem of single-point failure is serious. The introduction of the virtual navigation-following method provides a good solution for solving the problem, but also initiates a new problem, namely how to set the position of a virtual navigator to improve the formation performance to the greatest extent. In order to solve the problem, a variable step length exploration method is provided to continuously optimize the position of the virtual navigator, then a virtual navigator position exploration task is modeled into a Markov decision model, and a deep reinforcement learning method is introduced for training. According to the method provided by the invention, the optima