Cargo transportation system based on multi-agent reinforcement learning

Abstract

The invention relates to a cargo transportation system based on multi-agent reinforcement learning. The cargo transportation system comprises cargo transportation agents, a grouping module and a modelconstruction module. The grouping module is used for acquiring the position coordinates of each freight intelligent agent and grouping all freight intelligent agents according to a dynamic grouping algorithm to obtain at least one freight intelligent agent group; the model construction module is used for carrying out weight division on the freight intelligent agents in each freight intelligent agent group through an implicit weight endowing algorithm, and carrying out implicit coordination control on a plurality of freight intelligent agents in each freight intelligent agent group; a neural network is constructed by adopting a centralized reviewer mode of a multi-agent depth deterministic strategy gradient algorithm, an optimized path of multiple freight agents is generated through a neural network, and the freight agents in the freight agent group bypass obstacles according to the optimized path and reach landmarks. The system can process a large number of freight intelligent agentswith large communication information amount, and is good in performance, high in efficiency and low in cost.

Description

technical field [0001] The invention belongs to the technical field of multi-agent systems, in particular to a cargo transportation system based on multi-agent reinforcement learning. Background technique [0002] With the development of artificial intelligence, communication and information technology, the research of multi-agent has been a research hotspot that many people pay attention to in recent years. Multi-agent systems can be widely used in public facilities detection, disaster environment investigation, military reconnaissance, storage and handling and other fields, and have been widely used in both military and civilian applications. In the process of cargo transportation, it is a very important issue to enable multiple freight agents to intelligently plan routes to reach multiple different locations to place goods, because this can speed up the efficiency of freight transportation and reduce labor costs. Now It is also increasingly becoming a research focus. Am...

AI Technical Summary

Problems solved by technology

But in fact, in a multi-agent environment, due to differences in distance, speed and other factors, for a single freight agent, there may be some unnecessary information or even interference information in all freight agent information, and the communication information If the amount is too large, it may slow down the convergence of the system and affect the performance and efficiency of the entire system

In addition, in the current research on multi-intelligence reinforcement learning, it cannot solve the convergence problem when the number of freight agents is large.

Images