Multi-unmanned aerial vehicle path collaborative planning method and device based on hierarchical reinforcement learning

Abstract

The invention discloses a multi-unmanned aerial vehicle path collaborative planning method and device based on hierarchical reinforcement learning. The method comprises the steps of extracting a characteristic space of each unmanned aerial vehicle in a plurality of unmanned aerial vehicles; layering tasks needing to be executed in task targets according to the task targets of the unmanned aerial vehicles in the plurality of unmanned aerial vehicles, and dividing the tasks into a plurality of subtasks, wherein each subtask is realized by a neural network; forming each neural network composed bythe plurality of subtasks, and initializing parameters of each neural network to obtain each initial neural network; associating each neural network; taking difference between output results and target output as a loss function; carrying out parameter updating on each neural network through gradient descent; finishing training each neural network when a value of the loss function is smaller thana given threshold or the appointed step number arrives; passing each neural network through utilization of characteristic vectors in the respective characteristic space in sequence, thereby obtainingeach output value; selecting an action which enables an operation value to be maximum as a control signal of each unmanned aerial vehicle, and realizing multi-unmanned aerial vehicle path collaborative planning.

Description

technical field [0001] The invention belongs to the technical field of aircraft, and relates to complex behavior control such as multi-aircraft obstacle avoidance, collaborative path planning, and formation control based on layered reinforcement learning, in particular to a multi-UAV path collaborative planning method based on layered reinforcement learning and device Background technique [0002] With the great progress in computing power and artificial intelligence, the tasks that multi-rotor UAVs can perform are becoming more and more difficult, and the types of tasks that can be performed are becoming more and more complex, which brings great changes to people's lives and the flow of social productivity. Convenience and facilitation. Multi-UAV task coordination is a hot and difficult point in the current research on multi-agent control methods, which involves path planning and obstacle avoidance of a single agent, perception and action regulation between multi-agents. ...

AI Technical Summary

Problems solved by technology

It makes it possible to use deep reinforcement learning for multi-UAV collaborative path planning in actual engineering

Images