Multi-isomorphic unmanned vehicle distributed task allocation method for reconnaissance tasks

Abstract

The invention discloses a multi-isomorphic unmanned vehicle distributed task allocation method for reconnaissance tasks, relates to the technical field of multi-agent collaborative decision making, and aims at evaluating all tasks by each unmanned vehicle under the conditions that the capacity of the unmanned vehicles is limited and outdoor road conditions generate multi-dimensional constraints onthe unmanned vehicles. Finally, tasks are allocated according to an evaluation result. The method comprises the following steps: initializing system information; loading a map, and performing rasterization processing on the map; according to the rasterized map information and the initialized system information, acquiring environment information and the state of unmanned vehicles, and creating a matching function; and calculating the matching degree of each unmanned vehicle for all the tasks by utilizing the constructed matching function; constructing matching relationships between the unmanned vehicles and the tasks; executing a KM algorithm to perform task allocation. and executing the tasks.

Description

technical field [0001] The invention relates to the technical field of multi-agent collaborative decision-making, in particular to a multi-homogeneous unmanned vehicle distributed task assignment method for reconnaissance tasks. Background technique [0002] In a complex battlefield environment, the prerequisite for a multi-agent system to complete reconnaissance tasks quickly, efficiently and stably is to allocate existing resources reasonably and cooperate with each other. Due to the multi-dimensional constraints of the environment, the state of the unmanned vehicle, and the different task requirements, each unmanned vehicle evaluates the same task differently, resulting in different matching results in the end. [0003] At present, there are many solutions to the multi-agent task assignment problem. Commonly used are traditional auction algorithm, genetic algorithm, clustering algorithm, etc., but there are disadvantages such as local optimum. [0004] In most applicatio...

AI Technical Summary

Problems solved by technology

[0005] The current existing multi-agent task allocation schemes generally do not consider the environmental factors of reconnaissance tasks, and there is no stable communication architecture between unmanned vehicles, the system robustness is poor, and unmanned vehicles cannot be achieved through negotiation. The purpose of cooperating to complete the task, so the overall efficiency of the existing scheme is low, and it cannot be well adapted to the unmanned vehicle system for reconnaissance tasks

Images