Multi-agent sub-target division path planning method and system based on solubility potential field

Abstract

The invention provides a multi-agent sub-target division path planning method and system based on a solubility potential field. The path planning method comprises the steps of receiving scene data anda target path planning task, and building a multi-agent path planning model based on the potential field in a time-varying environment; dividing the target path planning task into a plurality of sub-tasks and allocating the sub-tasks to corresponding agents; when each agent is subjected to initial random traversing, firstly, establishing the solubility potential field by taking a set corresponding first sub-target as a target, and learning shortest path planning of reaching the corresponding first sub-target; then, storing learned environment information and knowledge in the next stage, and by taking the corresponding first sub-target as an initial position, starting to search for the next sub-target by using the solubility potential field; and after the agents learn shortest paths of reaching all the sub-targets, learning shortest paths of reaching respective targets, sharing the required information through a network, and finally learning shortest paths for the agents to reach a global target.

Description

technical field [0001] The disclosure belongs to the field of path planning, and in particular relates to a method and system for multi-agent sub-goal division path planning based on a dissolution potential field. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Currently, the modeling and simulation of agents is critical to many applications, such as surveillance of large infrastructures, military applications, and more. However, in many applications, such as monitoring to protect critical infrastructure and resources (CKIR), there is no system large enough to handle the entire CKIR system, so it is necessary to reduce the monitoring of agents in large environments to distributed intelligence in smaller areas The body environment area, that is, the application of multi-agents. Compared with single agent, multi-agent system has better pa...

AI Technical Summary

Problems solved by technology

[0005] The inventors have found that many researchers use complementary mixed strategy methods, such as: fuzzy logic-based behavior fusion path and planning algorithm, AUV global path planning ideas based on genetic algorithm and particle swarm optimization algorithm, applying Hopfield neural network to path distance Optimization can effectively solve some problems, but there are still shortcomings, such as slow convergence speed, relatively large amount of calculation, and difficulty in obtaining samples.

Images