Communication-sensitive multi-agent cooperation method

Abstract

The invention provides a communication-sensitive multi-agent cooperation method, which is applied to the technical field of Internet of Vehicles communication. The method comprises the following steps that: an intelligent agent encodes a locally observed message into a hidden state vector by using an information filtering module, i.e., compresses the filtered message, scores the message by using a shared medium access control module before sending the message, ranks the message value by an edge computing node according to the score, and sends the message value to an edge computing node; sending confirmation information to the intelligent agent with the topK message value, and sending the message after the intelligent agent receives the confirmation; the edge computing node receives all messages, extracts effective information by using a message distillation module, and gathers and distributes the effective information to each agent; in the process of summarizing the agent messages, a graph convolution summarizing mode based on a graph information bottleneck is utilized, topological structure information of the agents is reserved, and the summarized messages are distilled. According to the method, transmission of redundant and invalid information among the intelligent agents is reduced, communication resources are saved, and the decision-making ability and cooperation efficiency of the multiple intelligent agents are improved.

Description

technical field [0001] The invention relates to the field of vehicle networking communication technology and multi-agent collaboration technology, in particular to a method for multi-agent collaboration in a scenario where communication resources are limited. Background technique [0002] The control system architecture of an autonomous vehicle is mainly composed of a perception module, a decision module, and a control module. The perception module is responsible for sensing the surrounding environment. Under the condition of the Internet of Vehicles, the vehicle acts as both a sensor and an actuator. Vehicles perceive the surrounding environment through on-board sensors, and also use Internet of Vehicles technology to interact with other vehicles or road facilities to share perceived environmental information. Thereby collaboratively building a complete awareness of the surrounding environment. The decision-making module is mainly responsible for driving action planning....

AI Technical Summary

Problems solved by technology

However, in this technical solution, the communication between agents is based on a fixed topological structure, the agents cannot communicate freely, and the agents cannot selectively send messages, which will make the effective Information cannot be sent directly to a specific agent, and it is impossible for the agent to send redundant information to flood invalid information

The effectiveness of the information received by the agent will be limited, which is not conducive to the agent making optimal action decisions based on the received information

[0008] To sum up, in the existing technology, there is insufficient consideration of the limitation of communication resources in the real scene, the problem that the agent receives insufficient effective information, and cannot make an optimal action decision. Cooperative communication methods to improve the efficiency of vehicles to obtain effective information and make better action decisions

Images