Multi-agent cluster obstacle avoidance method based on reinforcement learning

Abstract

The invention discloses a multi-agent cluster obstacle avoidance method based on reinforcement learning. The method comprises the following steps: S1, establishing a motion model of a cluster system; S2, defining an obstacle avoidance factor xi and an obstacle avoidance evaluation criterion; S3, designing a state space, a behavior space and a reward function trained by a cluster formation transformation obstacle avoidance model Q-learning when ximin is less than ximin; S4, enhancing a state space, a behavior space and a reward function of learning training by the cluster autonomous collaborative obstacle avoidance model during design; S5, designing an agent behavior selection method; and S6, obtaining a Q value table obtained by training, and carrying out cluster autonomous collaborative obstacle avoidance based on the motion model defined in the S1. According to the invention, parameters such as an obstacle avoidance factor and an obstacle avoidance evaluation criterion are used for selection and judgment of an intelligent agent cluster obstacle avoidance model, and a Q-learning algorithm is combined to train a cluster autonomous collaborative obstacle avoidance model, so that an optimal cluster individual obstacle avoidance strategy and high obstacle avoidance efficiency are obtained.

Description

technical field [0001] The invention relates to multi-agent obstacle avoidance, in particular to a multi-agent group obstacle avoidance method based on reinforcement learning. Background technique [0002] In recent years, intelligent bodies such as unmanned aerial vehicles and unmanned cars have developed rapidly due to their high stability, strong adaptability, and low risk; the clustering of intelligent bodies solves the problem of limited functionality of a single intelligent body. At the same time, intelligent individuals are effectively integrated. [0003] Swarm obstacle avoidance has always been an important module of agent group control. Most obstacle avoidance algorithms tend to fall into local optimal values ​​when encountering complex obstacle environments, making agents unable to quickly avoid obstacles. Contents of the invention [0004] The purpose of the present invention is to overcome the deficiencies of the prior art, to provide a multi-agent cluster ob...

AI Technical Summary

Problems solved by technology

[0003]Swarm obstacle avoidance has always been an important module of agent group control. Most obstacle avoidance algorithms tend to fall into local optimal values ​​when encountering complex obstacle environments, so that agents cannot fast obstacle avoidance

Images