Unmanned vehicle path planning method based on improved A * algorithm and deep reinforcement learning

Abstract

The invention belongs to the technical field of unmanned vehicle navigation, particularly relates to an unmanned vehicle path planning method based on an improved A * algorithm and deep reinforcementlearning. The method aims to give full play to the advantages of global optimization of global path planning and real-time obstacle avoidance of local planning, improve the rapid real-time performanceof an A * algorithm and the complex environment adaptability of a deep reinforcement learning algorithm, and rapidly plan a collision-free optimal path of an unmanned vehicle from a starting point toa target point. The planning method comprises the following steps: establishing an initialized grid cost map according to environmental information; planning a global path by using an improved A * algorithm; designing a sliding window based on the global path and the performance of the laser radar sensor, and taking the information detected by the window as the state input of the network; on thebasis of a deep reinforcement learning method, using an Actor-Critic architecture for designing a local planning network. According to the invention, knowledge and a data method are combined, an optimal path can be obtained through rapid planning, and the unmanned vehicle has higher autonomy.

Description

technical field [0001] The invention relates to the technical field of unmanned vehicle navigation, in particular to an unmanned vehicle path planning method based on improved A* algorithm and deep reinforcement learning. Background technique [0002] Nowadays, the application scenarios of unmanned vehicles show the trend of diversified forms, diversified applications and complex environments, such as Jingdong warehouse logistics vehicles, service robots, factory security patrol unmanned vehicles, rookie logistics unmanned vehicles, etc. In the future, this kind of automated and intelligent unmanned system will become more and more popular. Among them, the path planning of unmanned vehicles is one of the core algorithms that support the autonomous mobility of unmanned vehicles, and it is to solve the problem of how to make the path optimal for unmanned vehicles from the starting point to the target point. Under normal circumstances, it is required to avoid obstacles and fin...

AI Technical Summary

Problems solved by technology

Among them, the A* algorithm uses heuristic information to avoid the blindness of the Dijkstra algorithm and reduces a large amount of redundant search space. Avoid potential risks in time, and have the disadvantage of not smooth path

In addition, global path planning relies on global environmental information, which has a large amount of data storage and calculation, and its application scenarios are limited.

However, common algorithms for local path planning, such as artificial potential field method and DWA algorithm, have good real-time performance, but there is a problem that they are easy to fall into the local optimum, and because the global information is unknown, the target may be lost and fall into a state of local oscillation. , the present invention designs an unmanned vehicle path planning method based on improved A* algorithm and deep reinforcement learning to solve the problems existing in the prior art

Images