Transferable task planning method and system under unmanned system cluster environment coupling

• Main Authors: XIN LIMING, ZHOU XIN, YAO YURAN, XU JUNBAO, DAI HUADONG, XIE SHAORONG, PENG JINLIN
• Format: Patent
• Language: Chinese; English
• Published: 06.02.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a migratable task planning method and system under unmanned system cluster environment coupling, and relates to the technical field of unmanned system cluster control, and the method comprises the steps: obtaining unmanned system cluster environment information, carrying out the task distribution through a greedy strategy, obtaining a task distribution result set corresponding to the current iteration number, and obtaining a task distribution result set corresponding to the current iteration number; and representing a task allocation result as a graph structure, obtaining a feature matrix and a relation adjacency matrix of the graph structure and a corresponding real reward value, and pre-training the micropooling graph neural network model. And when environment coupling occurs, migrating the pre-training model to a changed environment, carrying out fine tuning training, predicting an optimal task planning result under environment coupling through the fine-tuned micropooling graph neur