Objectives Aiming at the problems of unclear application architecture, weak information interaction capability, and low efficiency of heterogeneous platform collaborative testing of heterogeneous marine unmanned clusters, an agile collaboration technology for heterogeneous marine unmanned clusters is proposed, so that the system-level marine unmanned clusters can respond to the application task requirements in an agile manner, the platform-level unmanned system monoliths can be integrated into the clusters in an agile manner, and the system-level controllers can handle the task information in an agile manner and execute in place through decoupling of software and hardware at each level.

Methods Firstly, analyze the task characteristics, network and optimization requirements for the cooperative application scenarios of marine unmanned clusters, and divide them into several node groups according to their functions. Secondly, design the heterogeneous marine unmanned cluster agile cooperative architecture based on the functional node groups, and carry out the load complementation and task coordination through the fusion configuration of the cooperative architecture. Then, based on the application requirements and architectural features, the common marine unmanned cluster application tasks are divided into three categories: time priority tasks, sequential execution tasks, and routine operation tasks, and an agile task planning method based on the self-organizing graph algorithm is proposed for the heterogeneous marine unmanned clusters. Finally, a multilevel software-hardware decoupled marine unmanned cluster agile collaborative controller is developed, which interacts with the various systems of the platform in the form of a unified interface.

Results According to the test results of dynamic target detection and tracking on the lake by heterogeneous unmanned clusters, the final average heading deviation angle between each vehicle and the target is 6.7°, which better accomplishes the cooperative detection and tracking of dynamic targets.

Conclusion This method can enable marine unmanned systems with large performance differences to quickly join and implement typical tasks, and has excellent scalability and adaptability, which can help accelerate the development and practice of marine unmanned clusters.