A method and device for large-scale unmanned aerial vehicle cluster network cooperative simulation

Abstract

This invention relates to the field of unmanned aerial vehicle (UAV) simulation technology, and discloses a method and apparatus for collaborative simulation of large-scale UAV swarm networks. The method includes: first, performing flight simulation of the UAV swarm to generate flight state data containing the real-time poses of each UAV; then, based on this data, calculating and dynamically updating the topology and link parameters in the network simulation model in real time; next, fusing flight and network states to obtain joint situational awareness information; then, based on this information and preset mission objectives, collaboratively generating flight control commands and network configuration strategies; finally, feeding the commands and strategies back to the flight simulation and network simulation steps respectively, forming a closed-loop simulation with coordinated flight, network, and control. This invention achieves high-fidelity integrated verification of the complete causal chain between flight behavior, network performance, and control effects under dynamic topology conditions, significantly improving the realism, efficiency, and reproducibility of UAV swarm system R&D testing.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) simulation technology, specifically to a method and apparatus for collaborative simulation of large-scale UAV swarm networks. Background Technology

[0002] With the widespread application of UAV swarms in tasks such as patrol monitoring and air-ground coordination, their swarm size is constantly expanding, the number of nodes is growing rapidly, and the types of tasks and communication needs are becoming increasingly complex. The network communication system is exhibiting complex characteristics of high dynamism, strong time variation, and multi-hop networking, which puts forward higher requirements for the verification capabilities of the supporting system.

[0003] However, existing flight simulation platforms generally struggle to accurately depict the impact of communication link evolution on the control process, while traditional network simulation tools lack mechanisms for coupling spatial location information to simulate highly dynamic topologies. This results in a relatively disconnect between control and communication verification links, making it difficult to conduct coordinated verification in a unified environment. For example, some existing solutions primarily focus on the collaborative situational assessment simulation of UAV swarms, but do not provide modeling methods for inter-UAV communication at the packet / link level, nor do they have mechanisms to link topology changes caused by formation maneuvers with communication links. Other solutions fail to establish network models at the packet and link levels, and do not map topology changes caused by formation maneuvers to link quality and routing behavior.

[0004] Therefore, in existing UAV swarm simulation schemes, flight simulation and network simulation are separated, making it difficult to achieve linkage verification of control and communication under dynamic topology conditions. Summary of the Invention

[0005] This invention provides a method and apparatus for collaborative simulation of large-scale UAV swarm networks, which solves the problem in existing UAV swarm simulation schemes where flight simulation and network simulation are separated, making it difficult to achieve linkage verification of control and communication under dynamic topology conditions.

[0006] In a first aspect, the present invention provides a method for collaborative simulation of large-scale unmanned aerial vehicle (UAV) swarm networks, the method comprising:

[0007] Perform flight simulation of UAV swarms to generate flight status data containing the real-time pose of each UAV; Based on the flight status data, the communication relationship between UAV nodes is calculated in real time, and the topology and link parameters in the network simulation model are dynamically updated. The flight status data and the simulation status of the dynamically updated network simulation model are acquired and fused to obtain joint situational information. Based on the joint situational information and preset mission objectives, flight control commands and network configuration strategies are generated collaboratively. The flight control commands are fed back to the flight simulation step to adjust the simulation behavior, and the network configuration strategy is fed back to the network simulation step to adjust the network simulation model, so as to form a closed-loop simulation that links flight, network and control.

[0008] This invention provides a method for collaborative simulation of large-scale UAV swarm networks. By dynamically synchronizing real-time pose data generated from flight simulation to the network simulation model, it drives real-time updates of the model's topology and link parameters. Furthermore, it integrates flight and network states to form joint situational information, thereby collaboratively generating flight control commands and network configuration strategies. This creates a closed-loop simulation link encompassing flight state changes, network link behavior, and control / mission effects. This method effectively addresses the problem in existing UAV swarm simulation schemes where flight simulation and network simulation are isolated, making it difficult to achieve coordinated verification of control and communication under dynamic topology conditions. By constructing a unified scheduling and modularly decoupled simulation architecture, this invention can support the coordinated testing of control algorithms and network strategies for large-scale UAV swarms in complex mission scenarios, providing a general infrastructure support for the design, verification, and engineering implementation of UAV swarms.

[0009] In one optional implementation, the step of calculating the communication relationships between UAV nodes in real time based on the flight status data and dynamically updating the topology and link parameters in the network simulation model includes: The distance and line-of-sight between nodes are calculated based on the real-time pose of each UAV during a preset simulation cycle. Based on the distance, the visibility, and the preset wireless channel model, the connectivity status, latency, packet loss rate, and available bandwidth of the corresponding link in the simulation network are updated synchronously.

[0010] This invention achieves accurate and synchronous updates of network topology and link parameters (such as connectivity, latency, packet loss rate, and bandwidth) by pre-setting a simulation cycle, calculating the distance and visibility between nodes in real time based on their poses, and applying a wireless channel model. This ensures a high degree of consistency between network evolution and flight status changes.

[0011] In an optional implementation, before acquiring the flight status data and the simulation status of the dynamically updated network simulation model, the method further includes: The network simulation model provides a programmable interface to support user-defined network scheduling strategies and forwarding logic. The programmable interface loads a strategy to identify data packets that need to be forwarded, and classifies the corresponding data packets into different service flows according to the protocol type, content tag, or user-defined rules of the data packets. The network configuration strategy includes defining differentiated quality of service rules for different types of service flows, and the rules are configured and loaded through the programmable interface.

[0012] This invention identifies and classifies data packets, incorporating different service flows (such as control, telemetry, and payload) into differentiated quality of service rule management, thereby achieving refined scheduling of network resources and service assurance.

[0013] In one optional implementation, the service flow includes at least a control signaling flow, a telemetry data flow, and a payload data flow; the differentiated quality of service rules include assigning the highest forwarding priority to the control signaling flow, guaranteeing its bandwidth minimum, and selecting the optimal latency path.

[0014] This invention ensures low-latency and high-reliability transmission of critical control commands by allocating the highest priority to the control signaling stream, guaranteeing the lower limit of bandwidth, and selecting the optimal path, thereby improving the stability of cluster control and the success rate of tasks.

[0015] In one optional implementation, when the network configuration policy is fed back to the network simulation step for adjustment, an atomic update mechanism is employed, including: When the update trigger conditions are met, a complete new policy configuration set is generated; At a unified simulation moment, the old policy configuration set in effect will be completely switched to the new policy configuration set; If the new policy configuration set fails to be generated or fails the verification, the system will revert to the old policy configuration set and record the exception.

[0016] This invention ensures the integrity and correctness of the network configuration switching process by employing atomic update and failure rollback mechanisms, thereby enhancing the robustness and stability of the simulation system under dynamic policy adjustments.

[0017] In one optional implementation, the step of collaboratively generating flight control commands and network configuration strategies based on the joint situational awareness information and preset mission objectives includes: Based on the joint situation information and the preset mission objectives, the flight control commands are generated to adjust the UAV's trajectory, formation, or mission sequence. Furthermore, based on the joint situational awareness information and the preset task objectives, a network configuration strategy is generated to adjust network routing paths, queue scheduling priorities, or bandwidth allocation ratios.

[0018] This invention achieves automatic, closed-loop conversion and optimization of mission intent into flight control and network strategies by collaboratively generating flight control commands and network configuration strategies based on joint situation and mission objectives, thereby improving the intelligence and adaptability of simulation.

[0019] Secondly, the present invention provides a system for collaborative simulation of large-scale UAV swarm networks, the system being used to implement the method for collaborative simulation of large-scale UAV swarm networks as described above, the system comprising: The drone simulation module contains multiple containerized simulation instances for flight simulation of drone swarms, generating flight status data containing the real-time pose of each drone. The network simulation module includes a centralized network simulation kernel, which is used to calculate the communication relationship between UAV nodes in real time based on the flight status data, and dynamically update the topology and link parameters in the network simulation model; and to perform packet forwarding in the network simulation model. The control logic module is used to fuse the flight status data and the simulation status of the network simulation module to obtain joint situation information; and to collaboratively generate flight control commands and network configuration strategies based on the joint situation information and preset mission objectives. The communication interface is used to transmit the flight status data, simulation status, flight control commands, and network configuration strategies between the UAV simulation module, network simulation module, and control logic module to achieve closed-loop interaction.

[0020] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform a method for collaborative simulation of large-scale unmanned aerial vehicle (UAV) swarm networks as described in the first aspect or any corresponding embodiment.

[0021] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute a method for collaborative simulation of a large-scale unmanned aerial vehicle (UAV) swarm network as described in the first aspect or any corresponding embodiment thereof.

[0022] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute a method for collaborative simulation of large-scale unmanned aerial vehicle (UAV) swarm networks as described in the first aspect above or any corresponding embodiment thereof. Attached Figure Description

[0023] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a system architecture diagram for collaborative simulation of large-scale unmanned aerial vehicle (UAV) swarm networks according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the closed-loop task control flow according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a closed-loop service bearer flow according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the state update closed loop according to an embodiment of the present invention; Figure 5 This is a flowchart illustrating a method for collaborative simulation of large-scale unmanned aerial vehicle (UAV) swarm networks according to an embodiment of the present invention. Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0027] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0028] With the widespread application of UAV swarms in tasks such as patrol monitoring and air-to-ground coordination, their swarm size is constantly expanding, the number of nodes is growing rapidly, and the types of tasks and communication requirements are becoming increasingly complex. Network communication systems exhibit complex characteristics of high dynamism, strong time-varying nature, and multi-hop networking, placing higher demands on the verification capabilities of supporting systems. Existing flight simulation platforms generally struggle to accurately depict the impact of communication link evolution on the control process, while traditional network simulation tools lack mechanisms for coupling spatial location information to simulate highly dynamic topologies. This results in a relatively fragmented control and communication verification link, making it difficult to conduct joint verification in a unified environment. Therefore, this invention proposes a joint simulation method and system supporting flight-network collaboration, constructing a unified scheduling, module decoupling, and scalable deployment simulation architecture to support the joint testing of control algorithms and network strategies of large-scale UAV swarms in complex task scenarios.

[0029] The purpose of this invention is to construct a large-scale flight and network collaborative simulation platform for UAV swarm scenarios, filling the gap in existing technologies for dynamic network simulation under swarm conditions and meeting the comprehensive requirements of R&D testing for realism, scalability, and reproducibility. The platform uses a unified network simulation domain as its core, incorporating inter-machine communication within the swarm into a programmable network model, and conducting group-level modeling and simulation under dynamic topologies driven by formation and maneuver. Through collaborative advancement with flight simulation using SITL / HIL equivalent access, it achieves synchronous evolution and quantitative evaluation of flight state changes, network link behavior, control, and mission effects. It provides flow-programmable and runtime-switchable latency, packet loss, jitter, bandwidth, and queuing strategies for heterogeneous service flows such as control, telemetry, and payload. It employs containerization and a layered architecture to achieve elastic deployment of tens to hundreds (expandable to thousands) of nodes. By implementing the above functions, this invention forms a systematic capability in key aspects such as dynamic network simulation, flight and network linkage, service flow differentiation assurance, semi-physical access, and large-scale deployment, providing general infrastructure support for the design, verification, and engineering implementation of UAV swarms.

[0030] As an optional application scenario of this invention, such as Figure 1 As shown, the system architecture for collaborative simulation of large-scale UAV swarm networks may include: The drone simulation module contains multiple containerized simulation instances for flight simulation of drone swarms, generating flight status data containing the real-time pose of each drone. The network simulation module contains a centralized network simulation kernel, which is used to calculate the communication relationship between UAV nodes in real time based on the flight status data, and dynamically update the topology and link parameters in the network simulation model; and to perform packet forwarding in the network simulation model. The control logic module is used to fuse the flight status data and the simulation status of the network simulation module to obtain joint situation information; and based on the joint situation information and the preset mission objectives, to collaboratively generate flight control commands and network configuration strategies. The communication interface is used to transmit flight status data, simulation status, flight control commands, and network configuration strategies between the UAV simulation module, network simulation module, and control logic module to achieve closed-loop interaction.

[0031] In one alternative implementation, the network simulation module is further configured to: The distance and line-of-sight between nodes are calculated based on the real-time pose of each UAV during the preset simulation cycle. Based on the distance, visibility, and preset wireless channel model, the connectivity status, latency, packet loss rate, and available bandwidth of the corresponding link in the simulation network are updated synchronously.

[0032] In one alternative implementation, the network simulation module is used for: When forwarding data packets in this network simulation model, the data packets are identified and classified into different service flows according to the protocol type or content tag of the data packet. This network configuration strategy includes defining differentiated quality of service rules for different categories of service flows.

[0033] In one alternative implementation, the service flow includes at least a control signaling flow, a telemetry data flow, and a payload data flow; the differentiated quality of service rules include assigning the highest forwarding priority to the control signaling flow, guaranteeing its bandwidth minimum, and selecting the optimal latency path.

[0034] In an alternative embodiment, the device is further used for: When the update trigger conditions are met, a complete new policy configuration set is generated; At a unified simulation moment, the old policy configuration set in effect will be completely switched to the new policy configuration set; If the new policy configuration set fails to be generated or fails the verification, it will revert to the old policy configuration set and the exception will be logged.

[0035] In an optional implementation, the control logic module is further configured to: Based on the joint situation information and the preset mission objectives, the flight control command is generated to adjust the UAV's trajectory, formation, or mission sequence. Furthermore, based on the joint situational awareness information and the preset mission objectives, a network configuration strategy is generated to adjust network routing paths, queue scheduling priorities, or bandwidth allocation ratios.

[0036] Furthermore, the control logic module, located at the top layer of the system, is responsible for receiving external control intentions, aggregating system situation data, and unifying policy orchestration. This module internally includes sub-functions for intention access, situation aggregation, and policy orchestration. Intention access receives task requests, control actions, and parameter adjustments from the control entry point, establishes sessions, and performs semantic parsing, converting external inputs into control intentions recognizable within the system. Situation aggregation collects flight and network status data from the UAV simulation and network simulation modules, constructing a unified system situation view. Policy orchestration generates policy decisions for the control and bearer sides based on task objectives and the current situation, and distributes these decisions to downstream modules for execution. The control logic module does not participate in the forwarding of specific business data; its responsibilities are limited to intention management, situation awareness, and policy generation.

[0037] The UAV simulation module, acting as the system's execution side, is responsible for advancing the UAV's attitude, trajectory, and formation evolution within a unified simulation environment, and for generating and receiving control signaling and service data at the node level. This module internally includes flight simulation, signaling bearer, service bearer, and status output sub-functions. Flight simulation propels the UAV's movement based on scenario parameters and control commands issued by the control logic module, generating continuous flight states. The signaling bearer receives control signaling processed by the network side and drives flight simulation execution. The service bearer handles the injection and feedback of telemetry, sensor, and payload services at the node level. Status output sends the UAV's pose, velocity, formation changes, and mission execution status to the situational awareness aggregation and simultaneously provides this data to the network simulation module to drive topology evolution. The UAV simulation module is not responsible for path selection or network policy determination; its boundaries are limited to the simulation and reporting of UAV node behavior and related services.

[0038] The network simulation module, as the core of the system's communication side, is responsible for unifying all inter-machine communication into a centralized network simulation domain, performing path selection, link modeling, and differentiated scheduling under dynamic topology conditions. This module includes sub-functions for state synchronization, topology and link orchestration, link loss, and traffic scheduling. State synchronization receives the pose status from the UAV simulation module and maintains node adjacency relationships and basic link parameters according to the simulation clock. Topology and link orchestration builds a time-evolving topology view and organizes routing and link configurations. Link loss applies link models such as latency, packet loss, and bandwidth constraints to sub-traffic. Traffic scheduling, based on the bearer strategy issued by the control logic module, performs path selection, priority adjustment, and queue and rate control on control flow, telemetry flow, and payload flow, observes end-to-end performance indicators, and reports to the situational awareness and control logic module. The network simulation module does not modify flight-side commands or service content; instead, it reflects the communication effects under the current strategy and topology conditions with a unified network model and scheduling behavior.

[0039] The overall system framework decouples the UAV simulation module from the network simulation module through containerized deployment and centralized network simulation design. Simultaneously, it maintains consistent evolution of flight and network states through state synchronization and situational awareness convergence, effectively solving the problem of separation between flight and network simulation in traditional solutions. Furthermore, the system introduces programmable network modules and flexible control logic design, enabling it to adapt to different mission requirements and provide efficient simulation and evaluation capabilities.

[0040] Furthermore, based on the aforementioned system framework, this system achieves collaborative operation between control logic, flight simulation, and network simulation through three types of data flows: task control flow, state update flow, and service bearer flow. These data flows are transmitted between different modules via standardized interfaces and form a closed loop under a unified simulation time base.

[0041] Please see Figure 2 The diagram illustrates a closed-loop task control flow. This flow transmits control intentions and policy parameters between the control entry point, the control logic module, and the UAV simulation module. External task requests enter the system through the control entry point. The intention access module establishes a session and performs semantic parsing to form an executable control intention. This intention is then organized into policies and constraints for control signaling in the policy orchestration module and distributed via the traffic scheduling module. Before entering the UAV node, all control signaling must pass through the link loss module to load the UAV network link model, which includes parameters such as latency and packet loss. This link model then enters the UAV simulation module via the signaling bearer interface to drive task execution. The execution results generated by the UAV simulation module are sent to the situation aggregation module via the status output interface to form a unified view at the task level. Through this data flow process, the system realizes the distribution of control commands and the loading of policy parameters from user intentions to the simulation environment, forming a closed-loop control system through situation reporting.

[0042] Please see Figure 3The diagram illustrates a closed-loop service bearer flow. This flow is used to transmit non-control service data during simulation, including telemetry, sensor, and payload data. After intent access and policy orchestration, service requests are loaded with the UAV network's link loss model via traffic scheduling. This model includes latency, packet loss, and bandwidth constraints. The data then enters the service bearer interface reserved in the UAV simulation module to complete service delivery and execution. Real service flows generated by the UAV simulation module send their return data back to the network simulation module via the service bearer interface. Traffic scheduling classifies and reshapes the data according to the current policy, and the returned link loss is then superimposed before being input into the situational awareness aggregation module to construct a service situational view on the task side. This link ensures that all data entering the UAV network passes through the link loss module. The service bearer flow closes in a manner of policy delivery, data delivery, and result observation, used to evaluate the real changes in service quality under dynamic topology conditions of the UAV network.

[0043] Please see Figure 4 The diagram illustrates a closed-loop state update process. The state update flow consists of flight states and network topology states generated by the UAV nodes. During simulation, the UAV simulation module continuously generates flight states such as pose, velocity, and formation changes, which are directly input into the situational awareness aggregation module via the state output interface for displaying the current flight situation on the system side. Simultaneously, the same pose state is sent to the network simulation module to maintain state synchronization and updates inter-UAV adjacency relationships and link quality according to a preset clock. The network simulation module updates the network topology and link losses for the current period accordingly and outputs the results to the situational awareness aggregation module to display the time-varying state of the network. Through this dual-path update mechanism, the system can simultaneously obtain a complete view of both flight and network situations under a unified time base, thus ensuring consistency in the display and analysis of dynamic topology.

[0044] By organizing and coordinating the three types of data flows mentioned above, this system achieves orderly interaction between the control entry point, control logic module, UAV simulation module, and network simulation module without changing the existing system framework. This allows the causal relationship between control commands, flight status, and network bearer to be fully presented in the simulation environment, providing a unified data foundation for scene construction and performance evaluation in subsequent embodiments.

[0045] Furthermore, the system employs multi-instance containers as access endpoints, allowing the simulation scale to be rapidly expanded to hundreds or even thousands of nodes through parameter configuration. The UAV simulation module generates state data based on the simulation scenario and sends it to the network simulation module via a state synchronization mechanism, dynamically updating adjacency relationships and link parameters. The network simulation module uses this data to maintain the network topology and forwarding paths, and performs queue and rate control on the data plane. The control logic module issues parameter updates based on preset targets and thresholds, maintaining the same configuration activation rules as in the aforementioned embodiments, with unchanged interfaces and boundaries, facilitating performance evaluation and parameter optimization.

[0046] In the mode of joint debugging with real flight control and business systems, the real flight control and business systems are connected to the simulation environment through container boundaries, and system time is used as the benchmark for simulation progress. Flight status is input to the network simulation module in real time to update the network view; the network simulation module maps container ports to simulation nodes and links, and executes predetermined paths and constraints in real time on the data plane. The control logic module aggregates pre-configured strategies and manual intervention operations into control commands and parameter updates. Compared with the aforementioned large-scale simulation scenarios, this mode only changes the input source from batch configuration to real-time state streams, while maintaining consistency between configuration effectiveness semantics and interfaces, thus ensuring stable integration from simulation to the real system.

[0047] In summary, at the system architecture level, this embodiment adopts a three-element modular design, consisting of a UAV simulation module, a network simulation module, and a control logic module. Each module has clearly defined responsibilities and achieves collaborative interaction through standardized interfaces. Specifically, the UAV simulation module is responsible for trajectory evolution based on the mission scenario and outputs real-time pose and other status information; the network simulation module receives this status information, dynamically updates the inter-UAV communication topology and link parameters, and performs path selection and queue forwarding in the simulation data plane; the control logic module integrates feedback information from both the flight and network sides to generate flight control commands and network configuration adjustment schemes. The three modules form a closed-loop interaction: flight status drives network evolution, network performance feedback supports control decisions, and control commands simultaneously affect both flight and network simulations, ensuring the consistency of the joint simulation process. This architecture uses real-time UAV pose data to drive the dynamic evolution of network-side node motion models, wireless propagation, and routing mechanisms, fully presenting the complete causal chain from changes in flight state to changes in links and routing to the impact on control and tasks. At the same time, through a consistent interface and time alignment mechanism, the software and hardware at the same link point achieve equivalent access and equivalent verification in the same network simulation domain, forming a continuous verification path from algorithm prototype to engineering implementation, and ensuring the consistency of simulation results throughout the entire process.

[0048] The UAV simulation module continuously outputs the identifiers and location information of each node, injecting them into the network simulation kernel in real time through a state adapter to drive dynamic updates of communication adjacency relationships and link quality parameters. When changes in flight status cause network topology or link metrics to exceed preset thresholds, the network simulation module automatically generates a new network state view and applies it synchronously. Relying on a unified simulation time base and state verification mechanism, the system can ensure the consistency of flight trajectory changes and network model updates, fundamentally avoiding a misalignment. This mechanism abandons the traditional approach of relying on distributed Linux network simulation tools and bridge configurations. All cross-node traffic is uniformly processed through the core of the network simulation module, providing a unified network domain and consistent policy implementation standards. Policy configuration has auditable and rollback characteristics, significantly reducing the risks of environmental drift and configuration deviation.

[0049] To ensure the reliability and correctness of dynamic network configuration switching, this embodiment designs an atomic update and failure rollback mechanism. When the network simulation module detects that the topology or link status meets the update conditions, it pre-generates a complete new configuration scheme and, at a predetermined simulation time, uses a single effective point strategy to completely replace the old configuration with the new configuration, preventing the half-update state caused by the overlap of old and new configurations. Simultaneously, this mechanism incorporates failure protection: if the generation or verification of the new configuration fails, the system automatically retains the previous valid configuration and records the abnormal event; if the flight status input is briefly interrupted, the network simulation module maintains the most recent valid network status and continues to provide service, and the observation and statistics functions are unaffected. The above design ensures the standardization of the entire network configuration update process and the continuity of the simulation process, providing a solid guarantee for the stable and reliable operation of long-term, large-scale simulation tasks.

[0050] In the process of transmitting task intent to the simulation system, this embodiment implements an automatic conversion mechanism for control intent into signaling. The control logic module generates bidirectional decisions based on the cluster task objective and the current joint situation: on the one hand, it outputs flight control commands to adjust UAV trajectories, formations, or task assignments; on the other hand, it outputs network configuration parameters, covering routing paths, bandwidth allocation, priority policies, etc. This mechanism automatically deconstructs high-level task intent into executable low-level commands and policies, enabling task decisions to be applied instantly to various elements in flight and network simulations. It achieves automated and integrated conversion from user intent to simulation environment control commands and policy parameters, significantly improving the intelligent decision-making efficiency and overall coordination level of the simulation system.

[0051] To address the quality of service (QoS) assurance requirements in multi-service concurrent scenarios, this embodiment proposes a differentiated scheduling strategy based on service flow classification. The network simulation module identifies and classifies various data flows entering the simulation domain, allocating differentiated transmission paths and queue scheduling strategies according to service type. For critical control signaling flows, the optimal routing path and highest priority queue are allocated to ensure low latency and high reliability transmission; for ordinary telemetry or payload data flows, suboptimal paths, lower priorities, or rate-limited forwarding can be used as needed. Through programmable path selection algorithms and queue management mechanisms, the system can achieve fine-grained control of bandwidth allocation, priority queuing, and congestion control. This strategy provides flow-level identification, classification, and management interfaces for control flows, telemetry flows, payload flows, and other service flows within a unified network simulation domain, providing standardized capabilities for the design, implementation, and evaluation of communication assurance schemes such as differentiated service mechanisms, congestion management, and resource scheduling.

[0052] To enhance the system's flexibility and scalability, this embodiment endows the simulation platform with network programmability. Users can customize and load network-side functions such as scheduling policies, forwarding logic, and protocol behaviors. Without modifying the core system architecture, they can replace or add decision-making algorithms within the control logic module and data forwarding and management strategies in the network simulation module. This design enables the system to quickly adapt to the verification needs of cutting-edge algorithms and new protocols, significantly improving the platform's R&D support capabilities. Compared to a few existing solutions with network simulation capabilities, the network programmability introduced in this embodiment breaks through the limitations of fixed protocol stacks and static policies, supporting the design, verification, and comparison of various scheduling policies and custom protocols, providing a flexible and open experimental environment for cutting-edge technology research.

[0053] In terms of deployment and environment adaptation, this embodiment provides multi-mode and flexible system operation capabilities. Each simulation module adopts an architecture design of containerized nodes and centralized network core, first centrally managing network complexity and then horizontally scaling the node scale; it supports elastic expansion in single-machine, multi-machine, and cluster environments, facilitating resource isolation and scheduling, and meeting the stable operation requirements of dozens to thousands of UAV nodes. The system is compatible with both pure software simulation and hardware-in-the-loop simulation modes and can achieve seamless switching: when real flight control, sensor, or communication equipment is connected, it is incorporated into the simulation closed loop through standard interfaces, and real devices and virtual nodes operate collaboratively under unified timing and logic, thereby providing a consistent environment for end-to-end verification from algorithm prototype to engineering deployment. This system supports both low-fidelity rapid simulation for large-scale cluster networks and semi-physical and hardware-in-the-loop high-fidelity simulation for the engineering integration phase, comprehensively covering the entire lifecycle from scheme verification to deployment. It replaces large-scale flight network tests with simulation domains, reducing test costs and risks to a controllable level while fully preserving key network behaviors and control loops, and significantly improving the efficiency of R&D iteration and the reproducibility of conclusions.

[0054] In summary, this invention provides a method for collaborative simulation of large-scale UAV swarm networks. By dynamically synchronizing real-time pose data generated from flight simulation to the network simulation model, it drives real-time updates of the model's topology and link parameters. Furthermore, it integrates flight and network states to form joint situational information, thereby collaboratively generating flight control commands and network configuration strategies. This creates a closed-loop simulation link encompassing flight state changes, network link behavior, and control / mission effects. This method effectively addresses the problem in existing UAV swarm simulation schemes where flight simulation and network simulation are isolated, making it difficult to achieve coordinated verification of control and communication under dynamic topology conditions. By constructing a unified scheduling and modularly decoupled simulation architecture, this invention can support the coordinated testing of control algorithms and network strategies for large-scale UAV swarms in complex mission scenarios, providing a general infrastructure support for the design, verification, and engineering implementation of UAV swarms.

[0055] According to an embodiment of the present invention, a method embodiment for collaborative simulation of large-scale UAV swarm networks is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0056] This embodiment provides a method for collaborative simulation of large-scale UAV swarm networks. Figure 5 This is a flowchart of a method for cooperative simulation of large-scale unmanned aerial vehicle (UAV) swarm networks according to an embodiment of the present invention, such as... Figure 5As shown, the process includes the following steps: Step S501: Perform flight simulation of the UAV swarm to generate flight status data containing the real-time pose of each UAV.

[0057] Furthermore, step S501 involves running a flight simulation program to calculate and generate precise state information for each UAV in the cluster at continuous simulation time points, based on preset trajectory planning, dynamic models, and control commands issued by the control logic module. This information constitutes flight state data, the core of which is the real-time pose of each UAV (including three-dimensional spatial coordinates, attitude angles, etc.), and may also include motion parameters such as velocity and acceleration. This step is handled by the UAV simulation module in the system architecture. Its internal flight simulation sub-function propels the UAV movement according to scene parameters and control commands, generating continuous flight states. The generated pose, velocity, and formation changes serve as the fundamental data source for all subsequent network simulations and decision analyses.

[0058] Step S502: Based on the flight status data, calculate the communication relationship between UAV nodes in real time, and dynamically update the topology and link parameters in the network simulation model.

[0059] Furthermore, step S502 receives the real-time pose data from step S501 and uses it to dynamically calculate the communication reachability relationships between UAV nodes. Specifically, the system updates the topology (i.e., which nodes can establish communication links) and the performance parameters of each link (such as signal strength, basic latency, packet loss probability, and available bandwidth limit) in real time based on factors such as the real-time distance, relative orientation, and possible environmental obstruction (line of sight) between nodes, combined with a preset wireless channel propagation model (such as free space loss and multipath effect model). This process is completed collaboratively by functional sub-modules such as state synchronization and topology and link orchestration in the network simulation module, ensuring that the network view can keep up with the spatial relationship changes brought about by UAV formation maneuvers, providing a realistic topology and link foundation for simulating highly dynamic and time-varying UAV ad hoc networks.

[0060] In one optional implementation, step S502 includes: The distance and line-of-sight between nodes are calculated based on the real-time pose of each UAV during the preset simulation cycle. Based on the distance, visibility, and preset wireless channel model, the connectivity status, latency, packet loss rate, and available bandwidth of the corresponding link in the simulation network are updated synchronously.

[0061] Furthermore, this embodiment details how to convert flight pose data into real-time updated network parameters. Its core lies in periodically executing two key calculations according to a preset simulation cycle. First, based on the real-time three-dimensional coordinates (pose) of each UAV, the Euclidean distance between any two nodes is calculated, and the existence of a direct wireless propagation path (line-of-sight) is determined, taking into account the occlusion effects of terrain or obstacles. Subsequently, the calculated distance and line-of-sight results are input into a preset wireless channel model (such as a free-space propagation model, shadow fading model, etc.). This model calculates signal attenuation, multipath interference, and other effects based on the physical laws of electromagnetic wave propagation in space, ultimately outputting a performance evaluation of each potential communication link. Based on this evaluation, the system synchronously updates multiple key parameters of the corresponding link in the network simulation model: including the link's connectivity status (on or off), latency (signal transmission and processing time), packet loss rate (the probability of data packet loss due to signal attenuation or collision), and available bandwidth (the maximum data transmission rate that the link can stably provide under the current channel conditions). This mechanism ensures that the network model can accurately reflect the direct impact of changes in spatial relationships caused by UAV maneuvers on communication quality, providing a dynamic data foundation for high-fidelity network simulation.

[0062] Step S503: Obtain the flight status data and the simulation status of the dynamically updated network simulation model, and fuse them to obtain joint situation information.

[0063] Furthermore, this embodiment is responsible for constructing a unified, panoramic situational view of the simulation system, which is a prerequisite for intelligent decision-making. This step collects status information from two sources in parallel: first, flight status data from the UAV simulation module (as described in step S501), reflecting the physical movement of the cluster; second, simulation status from the network simulation module, which includes the network topology dynamically updated based on step S502, real-time performance indicators of each link (latency, packet loss rate, throughput, etc.), and network traffic scheduling status. Subsequently, the system performs time alignment, correlation fusion, and comprehensive analysis on these heterogeneous data from different domains (control domain, network domain) to form a joint situational information. This information not only shows where and how the UAV is moving, but also clearly reveals the quality of the inter-UAV communication network under the current movement state and which links may face the risk of interruption, thus providing a direct, quantitative, and global view for understanding how flight behavior affects network performance.

[0064] In an optional implementation, before acquiring the flight status data and the simulation status of the dynamically updated network simulation model, this embodiment also provides a programmable interface in the network simulation model to support user-defined network scheduling strategies and forwarding logic. The programmable interface loads strategies to identify data packets to be forwarded and classifies them into different service flows based on their protocol type, content tags, or user-defined rules. The network configuration strategy includes defining differentiated quality of service rules for different categories of service flows. These service flows include at least control signaling flows, telemetry data flows, and payload data flows. The differentiated quality of service rules include assigning the highest forwarding priority to the control signaling flow, guaranteeing its bandwidth minimum, and selecting the optimal latency path.

[0065] Furthermore, in this embodiment, when a data packet enters the network simulation model for forwarding, the system identifies and classifies it according to predefined or user-loaded strategies. The basis for identification and classification may include data packet header information or embedded tags. Based on the identification results, the data packet is categorized into different service flows, such as control signaling flows, telemetry data flows, and payload data flows. The network simulation module identifies and classifies the various data flows entering the simulation. For these different categories of service flows, the system loads differentiated quality of service rules through a programmable strategy interface. These rules can specify corresponding transmission paths and queue scheduling strategies for different types of traffic. For example, to ensure reliable transmission of control commands, critical control flows can be assigned optimal paths and higher-priority queues to ensure low latency and high reliability. This differentiated scheduling capability based on service flow classification enables the platform to support the design and comparative verification of communication assurance strategies for highly dynamic, multi-service concurrent scenarios.

[0066] Step S504: Based on the joint situational awareness information and the preset mission objectives, flight control commands and network configuration strategies are collaboratively generated. The flight control commands are fed back to the flight simulation step to adjust the simulation behavior, and the network configuration strategies are fed back to the network simulation step to adjust the network simulation model, thus forming a closed-loop simulation that links flight, network, and control.

[0067] Furthermore, step S504 is a closed-loop process for decision-making and control based on comprehensive system perception, realizing a complete link from situational analysis to execution feedback. This step takes the joint situational information generated in step S503 as input, combined with preset cluster task objectives (such as achieving area coverage, maintaining a specific formation, and realizing relay communication), and makes collaborative decisions through strategy orchestration. The decision output is bidirectional: on the one hand, specific flight control commands are generated to adjust the UAV's trajectory, formation, or task execution sequence to optimize task completion or adapt to environmental changes; on the other hand, network configuration strategies are generated, including adjusting routing protocol parameters, changing the priority and bandwidth allocation of service flows, or switching different queue scheduling algorithms to optimize network performance to ensure the current task. Crucially, the generated flight control commands are fed back to the flight simulation input in step S501, affecting subsequent UAV movements; while the network configuration strategies are fed back to the network simulation model in step S502, changing its forwarding and scheduling behavior. This embodiment tightly couples and promotes the coordinated evolution of flight control, network communication, and mission effectiveness, ultimately achieving realistic simulation and performance evaluation of the overall behavior of complex cluster systems in dynamic environments.

[0068] In one optional implementation, step S504 includes: Based on the joint situation information and the preset mission objectives, the flight control command is generated to adjust the UAV's trajectory, formation, or mission sequence. Furthermore, based on the joint situational awareness information and the preset mission objectives, a network configuration strategy is generated to adjust network routing paths, queue scheduling priorities, or bandwidth allocation ratios.

[0069] Furthermore, this embodiment clarifies the specific content of the collaborative decision-making output. When making decisions based on joint situational information and mission objectives, the system generates two types of executable configurations. One type is flight control commands, which directly affect the motion control of individual UAVs, specifically including: track commands for adjusting the flight path of a single UAV or formation; formation commands for changing the relative spatial positions of multiple UAVs (such as changing from a diamond formation to a column formation); and task sequence commands for adjusting the order of task execution or objectives. The other type is network configuration strategies, which affect the communication network, specifically including: routing path adjustments for changing the data packet transmission path; queue scheduling priority adjustments for determining the processing order of different service flows in switches or routers; and bandwidth allocation ratio adjustments for allocating network throughput resources on each service flow or physical link. This implementation clearly delineates the dimensions of the control output, enabling the simulation system to simultaneously and precisely intervene in and optimize both physical motion logic and network communication logic.

[0070] In one optional implementation, when the network configuration policy is fed back to the network simulation step for adjustment, an atomic update mechanism is employed, including: When the update trigger conditions are met, a complete new policy configuration set is generated; At a unified simulation moment, the old policy configuration set in effect will be completely switched to the new policy configuration set; If the new policy configuration set fails to be generated or fails the verification, it will revert to the old policy configuration set and the exception will be logged.

[0071] Furthermore, in this embodiment, firstly, when the system determines that a policy update is needed (such as due to a drastic topology change or manual command), it triggers the generation of a complete new policy configuration set. This configuration set includes the coordinated settings of all parameters such as routing, queues, and bandwidth that need to be changed. Secondly, the update is not implemented piecemeal, parameter by parameter, but rather, at a unified simulation moment, the currently effective old policy configuration set is replaced entirely with the new configuration set. This overall switch ensures that the system is always under a complete and self-consistent policy at any given time, without any intermediate mixed states. Finally, failure protection is introduced. If the new policy configuration set fails to be generated due to logical errors or resource conflicts, or fails the pre-application verification, the system will automatically revert to the previously stable old policy configuration set and record the abnormal events for analysis. This greatly enhances the robustness and reliability of the simulation system when frequently reconfiguring policies.

[0072] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0073] The following is a detailed reference. Figure 6 This diagram illustrates a suitable structural design for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0074] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0075] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the method for cooperative simulation of large-scale UAV swarm networks according to embodiments of the present invention.

[0076] Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0077] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, it implements the method for collaborative simulation of large-scale UAV swarm networks shown in the above embodiments.

[0078] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0079] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and all such modifications and variations fall within the scope defined by the invention.

Claims

1. A method for large-scale unmanned aerial vehicle cluster network coordination simulation, characterized in that, The method includes: Perform flight simulation of UAV swarms to generate flight status data containing the real-time pose of each UAV; Based on the flight status data, the communication relationship between UAV nodes is calculated in real time, and the topology and link parameters in the network simulation model are dynamically updated. The flight status data and the simulation status of the dynamically updated network simulation model are acquired and fused to obtain joint situational information. Based on the joint situational information and preset mission objectives, flight control commands and network configuration strategies are generated collaboratively. The flight control commands are fed back to the flight simulation step to adjust the simulation behavior, and the network configuration strategy is fed back to the network simulation step to adjust the network simulation model, so as to form a closed-loop simulation that links flight, network and control.

2. The method of claim 1, wherein, The process of calculating the communication relationships between UAV nodes in real time based on the flight status data and dynamically updating the topology and link parameters in the network simulation model includes: The distance and line-of-sight between nodes are calculated based on the real-time pose of each UAV during a preset simulation cycle. Based on the distance, the visibility, and the preset wireless channel model, the connectivity status, latency, packet loss rate, and available bandwidth of the corresponding link in the simulation network are updated synchronously.

3. The method according to claim 1 or 2, characterized in that, Before acquiring the flight status data and the simulation status of the dynamically updated network simulation model, the method further includes: The network simulation model provides a programmable interface to support user-defined network scheduling strategies and forwarding logic. The programmable interface loads a strategy to identify data packets that need to be forwarded, and classifies the corresponding data packets into different service flows according to the protocol type, content tag, or user-defined rules of the data packets. The network configuration strategy includes defining differentiated quality of service rules for different types of service flows, and the rules are configured and loaded through the programmable interface.

4. The method of claim 3, wherein, The service flow includes at least a control signaling flow, a telemetry data flow, and a payload data flow; the differentiated quality of service rules include assigning the highest forwarding priority to the control signaling flow, guaranteeing its bandwidth minimum, and selecting the optimal latency path.

5. The method of claim 1, wherein, When the network configuration strategy is fed back to the network simulation step for adjustment, an atomic update mechanism is used, including: When the update trigger conditions are met, a complete new policy configuration set is generated; At a unified simulation moment, the old policy configuration set in effect will be completely switched to the new policy configuration set; If the new policy configuration set fails to be generated or fails the verification, the system will revert to the old policy configuration set and record the exception.

6. The method of claim 1, wherein, The step of collaboratively generating flight control commands and network configuration strategies based on the joint situational awareness information and preset mission objectives includes: Based on the joint situation information and the preset mission objectives, the flight control commands are generated to adjust the UAV's trajectory, formation, or mission sequence. Furthermore, based on the joint situational awareness information and the preset task objectives, a network configuration strategy is generated to adjust network routing paths, queue scheduling priorities, or bandwidth allocation ratios.

7. A system for large-scale UAV swarm network coordination simulation, characterized in that, The system is used to implement the method for collaborative simulation of large-scale UAV swarm networks according to any one of claims 1 to 6, and the system includes: The drone simulation module contains multiple containerized simulation instances for flight simulation of drone swarms, generating flight status data containing the real-time pose of each drone. The network simulation module includes a centralized network simulation kernel, which is used to calculate the communication relationship between UAV nodes in real time based on the flight status data, and dynamically update the topology and link parameters in the network simulation model; and to perform packet forwarding in the network simulation model. The control logic module is used to fuse the flight status data and the simulation status of the network simulation module to obtain joint situation information; and to collaboratively generate flight control commands and network configuration strategies based on the joint situation information and preset mission objectives. The communication interface is used to transmit the flight status data, simulation status, flight control commands, and network configuration strategies between the UAV simulation module, network simulation module, and control logic module to achieve closed-loop interaction.

8. An electronic device, comprising: include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform a method for collaborative simulation of large-scale unmanned aerial vehicle (UAV) swarm networks as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute a method for collaborative simulation of large-scale unmanned aerial vehicle (UAV) swarm networks according to any one of claims 1 to 6.

10. A computer program product, characterised in that, Includes computer instructions for causing a computer to execute a method for collaborative simulation of large-scale unmanned aerial vehicle (UAV) swarm networks as described in any one of claims 1 to 6.

Images