Self-organizing system and method of UAV swarm network based on task cognition

Abstract

The invention discloses a self-organizing system and method for a swarm network of unmanned aerial vehicles based on task cognition. The system includes: an application layer, which is used to establish a representation method and model from the swarm task domain to the network information domain, and obtain information exchange within the swarm. The network layer is used to construct the network logical topology relationship based on the information association relationship of each node in the cluster established by the application layer, and generate the network topology relationship diagram; the link layer is used to realize the network structural design and generation, The network link is constructed by using the network logical topology relationship constructed based on the network layer, and dynamic network link reconstruction is performed when dynamic network changes are generated; the physical layer is used to build a simulation environment to simulate the performance of the cluster network. . The invention can significantly improve the search and delivery efficiency, information dimension and control accuracy of the large-scale unmanned aerial vehicle system, improve the reliability and efficiency of the unmanned intelligent group system, and can flexibly respond to complex environments and emergencies.

Description

technical field [0001] The invention relates to the technical field of swarm control of unmanned aerial vehicles, in particular to a self-organizing system and method of swarm network of unmanned aerial vehicles based on task cognition. Background technique [0002] The UAV swarm is a distributed system that integrates a large number of UAVs under an open system architecture, based on the collaborative control between platforms, and aims to improve the ability of collaborative tasks. The UAV system is gradually developing from a "big and complete" single platform with high autonomy to a "small and sophisticated" low-cost micro-small group intelligence. The development of micro-small UAV swarms has attracted much attention. The application of UAV swarms is based on network communication. Due to the constraints of volume, weight, energy, and software and hardware technology, the current level of UAV autonomy is generally not high (≤5), resulting in swarms performing dynamic ta...

AI Technical Summary

Problems solved by technology

At present, the UAV mission process is usually abstracted into a particle behavior model with certain probability distribution characteristics, and all kinds of information concurrently interacting between nodes are uniformly expressed as the transmission capacity value between nodes, which makes the theoretical research of network architecture out of the Awareness of cluster tasks

[0005] 2. In terms of the link communication layer, the research focus in the prior art is on the communication waveform design, channel design and access technology, without considering the information service type and transfer characteristics in the cluster task process, and without considering the information from the cluster The association transfer mapping and characterization from the task domain to the information domain cannot guide the design and construction of the cluster network architecture from the information requirements of the task process

[0006] 3. There is a contradiction between the loose cluster organization and the tight intra-group communication, which poses a great challenge to the generation of the cluster network

The network generation method in the prior art cannot determine the coupling mechanism between mission behavior and information services based on the behavior characteristics of the UAV group, so it cannot match the mutual coupling characteristics of the link layer, network layer, transport layer, and application layer to realize network generation.

[0007] 4. UAVs take both tasks and communication into account. In complex dynamic scenarios, there is a contradiction between task re-planning and network optimization, and network robustness and transmission stability face challenges.

However, each UAV in the cluster is both a task performer and a network participant, and it is impossible to solve the problem of planning and constraining UAV behavior from two different dimensions of network optimization and task execution.

The cluster control method in the prior art does not consider the role assignment and role change of each node in the cluster in the task, as well as the task correlation between nodes that change over time and space, and cannot truly represent the dynamic evolution process in the cluster control to achieve dynamic and flexible control.

Images