A drone swarm mission description system with embedded AI strategies

By designing a drone swarm task description system that can embed AI strategies, the problems of uniformity and collaboration in drone swarm task description systems are solved. This achieves clear task decomposition, integration of AI strategies and rule functions, and enhances the autonomy and collaboration capabilities of drone swarms, enabling them to adapt to complex environments.

CN119668876BActive Publication Date: 2025-11-14NANJING UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411806577.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-12-10
Publication Date
2025-11-14
Estimated Expiration
2044-12-10

AI Technical Summary

Technical Problem

Existing drone swarm mission description systems lack a unified mission description system, cannot effectively support the integration of rule-driven methods and AI strategies, struggle to handle complex and ever-changing environmental information, and have shortcomings in mission decomposition, concurrent execution of multiple tasks, and autonomous drone collaboration.

Method used

A drone swarm task description system with embedded AI strategies was designed, including a platform description module, a dependency library import module, an action definition module, a drone type definition module, a single drone behavior definition module, a multi-drone task definition module, a drone swarm task module, and a communication primitive module. It adopts a flow control structure and a blackboard mechanism, and realizes task decomposition and collaborative operation through multi-level concurrent primitives and communication primitives.

Benefits of technology

It achieves clear task decomposition, integrates AI strategies and rules, supports multi-level concurrent needs, enhances the autonomy and collaboration capabilities of drone swarms, and improves adaptability to dynamic environments and mission success rate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119668876B_ABST
    Figure CN119668876B_ABST
Patent Text Reader

Abstract

This invention discloses a drone swarm task description system with embedded AI strategies, belonging to the field of computer application technology. The invention has the following features: First, by decomposing a main task into multiple multi-drone tasks, multi-drone tasks into multiple single-drone behaviors, and single-drone behaviors into multiple single-drone actions, complex tasks are broken down into clear, independent steps, facilitating independent execution and overall coordination by drones. Second, the system introduces import statements to integrate AI strategies and rule control, improving the intelligence level of tasks. Simultaneously, it employs a flow control structure and multi-level concurrent primitives to support sequential and multi-level concurrent execution of tasks. Finally, the system enhances the autonomous coordination capabilities of drones through communication primitives based on a blackboard mechanism, enabling information sharing and coordinated operations without a central scheduler, significantly improving the coordination efficiency and task success rate of the drone swarm.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of computer application technology, specifically to a drone swarm task description system that can be embedded with AI strategies. Background Technology

[0002] In recent years, drones have demonstrated broad application prospects in various fields, including but not limited to aerial photography, environmental monitoring, disaster relief, agricultural production, and security patrols. With the rapid development of artificial intelligence and drone technology, the ability of drone swarms to perform complex tasks in different fields has been significantly enhanced.

[0003] However, with the increasing number of drones and the growing complexity of their missions, the traditional manual control of drone swarms has gradually revealed its lack of flexibility. This approach is poorly adaptable to dynamic environments and struggles to effectively handle complex and ever-changing environmental information. Therefore, in order to enhance the autonomy and intelligence of drones and enable them to better cope with dynamic environments, the introduction of AI strategies has become particularly important.

[0004] Although some studies have attempted to apply rule-driven methods and AI strategies to drone swarm missions, these studies still face a common problem: the lack of a unified mission description system that can support both methods simultaneously. In addition, existing drone swarm mission description systems have significant shortcomings in describing task decomposition, concurrent execution of multiple tasks, and autonomous cooperation among drones, and cannot meet practical needs. Summary of the Invention

[0005] The purpose of this invention is to provide a drone swarm mission description system that can be embedded with AI strategies to solve the problems raised in the prior art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a drone swarm task description system that can be embedded with AI strategies, the system including a platform description module, a dependency library import module, an action definition module, a drone type definition module, a single drone behavior definition module, a multi-drone task definition module, a drone swarm task module, and a communication primitive module;

[0007] The platform description module describes the simulation software platform on which the program is based.

[0008] The dependency import module is used to import external dependency packages;

[0009] The drone type definition module is used to describe the actions a drone can perform, and consists of action names;

[0010] The UAV swarm mission module is used to describe UAV swarm missions and issue calling instructions to the UAV type definition module and the multi-UAV mission definition module respectively.

[0011] The multi-aircraft mission definition module breaks down the drone swarm mission into multiple multi-aircraft missions through a process control structure.

[0012] The single-machine behavior definition module breaks down each multi-machine task into multiple single-machine behaviors through a flow control structure.

[0013] The action definition module is used to break down each single-machine behavior into multiple single-machine actions;

[0014] The communication primitive module publishes messages on the blackboard during the execution of drone swarm missions, based on the blackboard mechanism.

[0015] Furthermore, the flow control structure includes an initialization structure, a target structure, and a routine structure, wherein the initialization structure, the target structure, and the routine structure are all prefixed with the @ symbol;

[0016] The initialization structure is used to initialize tasks and behaviors in the multi-machine task definition module and the single-machine behavior definition module, and the initialization is executed only once;

[0017] The target structure is used to determine whether the multi-machine task executed by the multi-machine task definition module has achieved the task target and whether the single-machine behavior executed by the single-machine behavior definition module has achieved the behavior target.

[0018] The routine structure is executed after the initialization. It is determined whether to repeat the routine structure based on the target structure. The multi-machine task definition module realizes the concurrency of multi-machine group tasks through the multi-level concurrency primitives in the routine structure. The single-machine behavior definition module describes the concurrency between multiple devices on a drone through the multi-level concurrency primitives in the routine structure.

[0019] Furthermore, multi-level concurrency primitives include the each statement and the || concurrency primitive;

[0020] The each statement is used to describe how all drones in the same drone swarm concurrently complete a single drone action. The structure of the each statement consists of the calling statements of all drones in the same drone swarm and the calling statement of the single drone action.

[0021] The two parts of the structure adjacent to the || concurrency primitive are executed concurrently. If the || concurrency primitive is located in the routine structure of the multi-machine task definition module, it represents the concurrency of different drone groups. If the || concurrency primitive is located in the routine structure of the single-machine behavior definition module, it represents the concurrency between multiple devices of a single drone.

[0022] By adopting "process control" to manage the execution order of tasks, the readability of tasks is improved. At the same time, in response to the multi-level concurrency requirements in tasks, the each and || multi-level concurrency primitives were designed to support the concurrent description of tasks between multiple drone swarms, between multiple drones within a drone swarm, and between multiple devices on a drone.

[0023] Furthermore, the UAV swarm task module includes a UAV type definition module calling unit and a multi-UAV task definition module calling unit;

[0024] The drone type definition module calling unit declares the type and number of drones participating in the drone swarm mission;

[0025] The multi-machine task definition module calling unit declares the type and number of the drones participating in the same multi-machine task.

[0026] Furthermore, the multi-machine task definition module includes multi-machine task definition units, and each of the multi-machine task definition units can call the single-machine behavior definition module and the other multi-machine task definition units;

[0027] Each of the multi-machine task definition units has a flow control structure. The multi-machine task process is defined by executing the flow control structure. The multi-machine task process includes:

[0028] Step S5-1: Initialize the multi-machine task using the initialization structure;

[0029] Step S5-2: After the multi-machine task is initialized, the steps in the routine structure are executed. The routine structure includes the concurrency primitive, each statement and order statement. The concurrency primitive is used to realize the concurrency of different drone groups. The each statement is used to realize the concurrency of multiple drones in a drone group. The order statement is used to control the drones in a drone group to execute tasks in sequence.

[0030] Step S5-3: After executing the steps in the routine structure, execute the steps in the target structure. When the target structure is empty, end the multi-machine task. When the target structure is not empty, the last statement in the target structure must be an expression prefixed with $. Determine whether to repeat the steps in the routine structure based on the truth value of the expression. If the expression is false, repeat the steps in the routine structure. If the expression is true, end the multi-machine task.

[0031] Furthermore, the stand-alone behavior definition module includes stand-alone behavior definition units, and each stand-alone behavior definition unit can call the action definition module and other stand-alone behavior definition units;

[0032] Each of the aforementioned single-machine behavior definition units has a flow control structure. The single-machine behavior process is defined by executing the flow control structure. The definition of the single-machine behavior process includes:

[0033] Step S6-1: Initialize the structure to initialize the single-machine behavior;

[0034] Step S6-2: After the single-machine behavior initialization, the steps in the routine structure are executed, and the concurrency between multiple devices on a single UAV is realized through the || concurrency primitive in the routine structure;

[0035] Step S6-3: After executing the steps in the routine structure, execute the steps in the target structure. When the target structure is empty, end the stand-alone behavior. When the target structure is not empty, the last statement in the target structure must be an expression prefixed with $. Determine whether to repeat the steps in the routine structure based on the truth value of the expression. If the expression is false, repeat the steps in the routine structure. If the expression is true, end the stand-alone behavior.

[0036] Furthermore, the dependency import module describes the filenames of external dependency packages through the dependency import unit;

[0037] To address the above steps, the system introduces an import statement in the dependency library import module. Users can use this statement to integrate AI-based strategy modules into the task steps, such as search strategies trained through deep learning. In this way, rule control (such as takeoff, landing, and flying to a specific location) and AI strategies work together to participate in task execution, adapt to environmental changes, and improve the task success rate.

[0038] Furthermore, the action definition module includes an API call unit, which describes the process of a single API call by the UAV to a certain device, and the API call unit is defined by an external dependency file;

[0039] In this system, complex swarm tasks can be broken down into a series of steps according to the “Main-Task-Behavior-Action” hierarchical structure, enabling each UAV to execute independently and work together to complete the overall task.

[0040] Furthermore, the communication primitive module includes the POST statement, GET statement, DGET statement, and MODIFY statement;

[0041] The communication primitive module adopts a blackboard-based communication primitive to present messages on the blackboard in the form of key-value pairs. The key-value pairs are not in a one-to-one correspondence, and the values ​​can be numerical or string.

[0042] The POST statement is used to post key-value pairs on the blackboard;

[0043] The GET statement is used to retrieve a value corresponding to a key from the blackboard and store the value in a local variable;

[0044] The MODIFY statement is used to modify the value corresponding to one of the keys on the blackboard. The execution logic of the MODIFY statement is based on the execution of the GET statement, and the local variable is used in the expression.

[0045] The system incorporates communication primitives based on the blackbook mechanism, such as POST, GET, DGET, and MODIFY, to enable information sharing and coordination among UAVs. This mechanism enhances the collaborative capabilities of UAV swarms, allowing task information sharing and coordination operations to be completed without relying on a central scheduler.

[0046] Furthermore, the platform description module interacts with the simulation environment by configuring the platform statement. When the platform statement is not configured, it only executes the task logic and does not interact with the simulation environment. The platform statement is configured at most once.

[0047] Compared with the prior art, the beneficial effects of the present invention are:

[0048] 1. The task breakdown is clearly described.

[0049] This invention provides an effective task decomposition method that breaks down complex swarm tasks into independent steps that each drone can execute. By defining different types of drones and their capabilities, users can allocate drones that suit their task requirements through a drone type definition module. In this system, complex swarm tasks can be decomposed into a series of steps according to a hierarchical structure of "Main-Task-Behavior-Action", enabling each drone to execute independently and work together to complete the overall task.

[0050] 2. Integration of AI strategy reasoning and rule-based function invocation

[0051] To meet the needs of intelligent tasks, the system introduces a dependency library import module. Users can use this statement to integrate AI-based strategies into the steps. In this way, rule control and AI strategies work together to perform tasks, adapt to environmental changes, and improve task success rate.

[0052] 3. Sequential and concurrent support

[0053] The system adopts process control to manage the basic sequential execution of tasks, significantly improving task readability. In response to the multi-level concurrency requirements in tasks, it has designed the each statement and the || concurrency primitive to support the concurrent description of tasks between multiple drone swarms, between multiple drones within a swarm, and between multiple devices on a single drone.

[0054] 4. Collaboration mechanism supported by the blackboard system

[0055] To enable autonomous collaboration among multiple UAVs, the system also provides communication primitives based on the blackboard mechanism, such as POST, GET, DGET, and MODIFY, to achieve autonomous collaboration among UAVs. This mechanism enhances the collaborative capabilities of UAV swarms, enabling the sharing of task information and coordinated operations without relying on a central scheduler. Attached Figure Description

[0056] Figure 1 This is an execution flowchart of the multi-machine task definition module and the single-machine behavior definition module in a drone swarm task description system that can be embedded with AI strategies according to the present invention.

[0057] Figure 2 This is a schematic diagram illustrating the process by which the each statement controls multiple drones to concurrently perform the same behavior in a drone swarm task description system that can be embedded with AI strategies according to the present invention. Detailed Implementation

[0058] 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.

[0059] Example: Figures 1-2 As shown, the present invention provides a technical solution, a drone swarm task description system that can be embedded with AI strategies. The system includes a platform description module, a dependency library import module, an action definition module, a drone type definition module, a single drone behavior definition module, a multi-drone task definition module, a drone swarm task module, and a communication primitive module.

[0060] The platform description module describes the simulation software platform on which the program is based.

[0061] The dependency import module is used to import external dependency packages;

[0062] The drone type definition module is used to describe the actions a drone can perform, and consists of action names;

[0063] The UAV swarm mission module is used to describe UAV swarm missions and issue calling instructions to the UAV type definition module and the multi-UAV mission definition module respectively.

[0064] The multi-aircraft mission definition module breaks down the drone swarm mission into multiple multi-aircraft missions through a process control structure.

[0065] The single-machine behavior definition module breaks down each multi-machine task into multiple single-machine behaviors through a flow control structure.

[0066] The action definition module is used to break down each single-machine behavior into multiple single-machine actions;

[0067] The communication primitive module publishes messages on the blackboard during the execution of drone swarm missions, based on the blackboard mechanism.

[0068] The flow control structure includes an initialization structure, a target structure, and a routine structure, wherein the initialization structure, the target structure, and the routine structure are all prefixed with the @ symbol.

[0069] The initialization structure is used to initialize tasks and behaviors in the multi-machine task definition module and the single-machine behavior definition module, and the initialization is executed only once;

[0070] The target structure is used to determine whether the multi-machine task executed by the multi-machine task definition module has achieved the task target and whether the single-machine behavior executed by the single-machine behavior definition module has achieved the behavior target.

[0071] The routine structure is executed after the initialization. It is determined whether to repeat the routine structure based on the target structure. The multi-machine task definition module realizes the concurrency of multi-machine group tasks through the multi-level concurrency primitives in the routine structure. The single-machine behavior definition module describes the concurrency between multiple devices on a drone through the multi-level concurrency primitives in the routine structure.

[0072] Among them, multi-level concurrency primitives include the each statement and the || concurrency primitive;

[0073] The each statement is used to describe how all drones in the same drone swarm concurrently complete a single drone action. The structure of the each statement consists of the calling statements of all drones in the same drone swarm and the calling statement of the single drone action.

[0074] The two parts of the structure adjacent to the || concurrency primitive are executed concurrently. If the || concurrency primitive is located in the routine structure of the multi-machine task definition module, it represents the concurrency of different drone groups. If the || concurrency primitive is located in the routine structure of the single-machine behavior definition module, it represents the concurrency between multiple devices of a single drone.

[0075] The drone swarm task module includes a drone type definition module calling unit and a multi-drone task definition module calling unit;

[0076] The drone type definition module calling unit declares the type and number of drones participating in the drone swarm mission;

[0077] The multi-machine task definition module calling unit declares the type and number of the drones participating in the same multi-machine task.

[0078] In an embodiment of the present invention, Main is used as the program entry point, the Agent call statement declares the types of drones included in the task, and the predefined Task multi-drone task is called to start the task execution process.

[0079] The multi-machine task definition module includes multi-machine task definition units, and each of the multi-machine task definition units can call the single-machine behavior definition module and the other multi-machine task definition units.

[0080] Each of the multi-machine task definition units has a flow control structure. The multi-machine task process is defined by executing the flow control structure. The multi-machine task process includes:

[0081] Step S5-1: Initialize the multi-machine task using the initialization structure;

[0082] Step S5-2: After the multi-machine task is initialized, the steps in the routine structure are executed. The routine structure includes the concurrency primitive, each statement and order statement. The concurrency primitive is used to realize the concurrency of different drone groups. The each statement is used to realize the concurrency of multiple drones in a drone group. The order statement is used to control the drones in a drone group to execute tasks in sequence.

[0083] Step S5-3: After executing the steps in the routine structure, execute the steps in the target structure. When the target structure is empty, end the multi-machine task. When the target structure is not empty, the last statement in the target structure must be an expression prefixed with $. Determine whether to repeat the steps in the routine structure based on the truth value of the expression. If the expression is false, repeat the steps in the routine structure. If the expression is true, end the multi-machine task.

[0084] In an embodiment of the present invention, after entering the multi-machine task, the statements in the init code block are executed to initialize the task, and then the statements in the routine code block are executed to execute the task process. Finally, the value of the expression at the end of the goal code block is used to determine whether the routine code block needs to be executed repeatedly. In the routine code block, the || symbol is used to achieve concurrency of multiple machine groups, the each statement is used to achieve concurrency of multiple UAVs within a machine group, and the order statement is used to achieve sequential execution of certain statements by multiple UAVs within a machine group.

[0085] The single-machine behavior definition module includes single-machine behavior definition units, and each of the single-machine behavior definition units can call the action definition module and other single-machine behavior definition units.

[0086] Each of the aforementioned single-machine behavior definition units has a flow control structure. The single-machine behavior process is defined by executing the flow control structure. The definition of the single-machine behavior process includes:

[0087] Step S6-1: Initialize the structure to initialize the single-machine behavior;

[0088] Step S6-2: After the single-machine behavior initialization, the steps in the routine structure are executed, and the concurrency between multiple devices on a single UAV is realized through the || concurrency primitive in the routine structure;

[0089] Step S6-3: After executing the steps in the routine structure, execute the steps in the target structure. When the target structure is empty, end the stand-alone behavior. When the target structure is not empty, the last statement in the target structure must be an expression prefixed with $. Determine whether to repeat the steps in the routine structure based on the truth value of the expression. If the expression is false, repeat the steps in the routine structure. If the expression is true, end the stand-alone behavior.

[0090] In embodiments of the present invention, after entering a single-machine behavior, similar to the steps within a Task, the statements in the init code block are executed to initialize the behavior, then the statements in the routine code block are executed to execute the behavior process, and finally, the value of the expression at the end of the goal code block is used to determine whether the routine code block needs to be executed repeatedly. In the routine code block, the || symbol is used to describe the concurrency between multiple devices on a drone. In addition to calling single-machine actions, other behaviors can also be nested within the behavior.

[0091] The dependency import module describes the filenames of external dependency packages through the dependency import unit.

[0092] The action definition module includes an API call unit, which describes the process of a drone making a single API call to a certain device, and the API call unit is defined by an external dependency file.

[0093] In an embodiment of the present invention, after entering a standalone machine as an Action, the API call unit in the external dependency package imported by the import statement is executed. The Action is the smallest unit in program execution and cannot be interrupted.

[0094] The communication primitives module includes the POST statement, GET statement, DGET statement, and MODIFY statement.

[0095] The communication primitive module adopts a blackboard-based communication primitive to present messages on the blackboard in the form of key-value pairs. The key-value pairs are not in a one-to-one correspondence, and the values ​​can be numerical or string.

[0096] The POST statement is used to post key-value pairs on the blackboard;

[0097] The GET statement is used to retrieve a value corresponding to a key from the blackboard and store the value in a local variable;

[0098] The MODIFY statement is used to modify the value corresponding to one of the keys on the blackboard. The execution logic of the MODIFY statement is based on the execution of the GET statement, and the local variable is used in the expression.

[0099] The platform description module interacts with the simulation environment by configuring the platform statement. When the platform statement is not configured, it only executes the task logic and does not interact with the simulation environment. The platform statement is configured at most once.

[0100] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A drone swarm task description system that can be embedded with AI strategies, characterized in that: The system includes a platform description module, a dependency library import module, an action definition module, a drone type definition module, a single-drone behavior definition module, a multi-drone task definition module, a drone swarm task module, and a communication primitives module. The platform description module is used to describe the simulation software platform on which the system is based during operation; The dependency import module is used to import external dependency packages; The drone type definition module is used to describe the actions of a drone, which consists of action names; The UAV swarm task module is used to describe the UAV swarm task and issue calling instructions to the UAV type definition module and the multi-UAV task definition module respectively; The multi-aircraft task definition module decomposes the UAV swarm task into multiple multi-aircraft tasks through a process control structure. The single-machine behavior definition module decomposes each multi-machine task into multiple single-machine behaviors through a flow control structure. The action definition module is used to break down each single-machine behavior into multiple single-machine actions; The communication primitive module publishes messages on the blackboard during the execution of the drone swarm mission based on the blackboard mechanism.

2. The drone swarm task description system with embedded AI strategy according to claim 1, characterized in that: The flow control structure includes an initialization structure, a target structure, and a routine structure, wherein the initialization structure, the target structure, and the routine structure are all prefixed with the @ symbol; The initialization structure is used to initialize tasks and behaviors in the multi-machine task definition module and the single-machine behavior definition module, and the initialization is executed only once. The target structure is used to determine whether the multi-machine task executed by the multi-machine task definition module has achieved the task objective and whether the single-machine behavior executed by the single-machine behavior definition module has achieved the behavior objective. The routine structure is executed after the initialization. It is determined whether to repeat the routine structure based on the target structure. The multi-machine task definition module realizes the concurrency of multi-machine group tasks through the multi-level concurrency primitives in the routine structure. The single-machine behavior definition module can describe the concurrency between multiple devices on a drone through the multi-level concurrency primitives in the routine structure.

3. The drone swarm task description system with embedded AI strategy according to claim 2, characterized in that: The multi-level concurrency primitives include the each statement and the || concurrency primitive; The each statement is used to describe the concurrent completion of a single-machine action by all drones in the same drone swarm, and the structure of the each statement consists of the calling statements of all drones in the same drone swarm and the calling statement of the single-machine action. The two parts of the structure adjacent to the || concurrency primitive are executed concurrently. If the || concurrency primitive is located in the routine structure of the multi-machine task definition module, it represents the concurrency of different drone groups. If the || concurrency primitive is located in the routine structure of the single-machine behavior definition module, it represents the concurrency between multiple devices of a single drone.

4. The drone swarm task description system with embedded AI strategy according to claim 1, characterized in that: The UAV swarm task module includes a UAV type definition module calling unit and a multi-UAV task definition module calling unit; The drone type definition module calling unit declares the type and number of drones participating in the drone swarm mission; The multi-machine task definition module calling unit declares the type and number of the UAVs participating in the same multi-machine task.

5. The drone swarm task description system with embedded AI strategy according to claim 1, characterized in that: The multi-machine task definition module includes multi-machine task definition units, and each multi-machine task definition unit can call the single-machine behavior definition module and the other multi-machine task definition units; Each of the multi-machine task definition units has a flow control structure. The multi-machine task process is defined by executing the flow control structure. The multi-machine task definition process includes: Step S5-1: Initialize the multi-machine task using the initialization structure; Step S5-2: After the multi-machine task is initialized, the steps in the routine structure are executed. The routine structure includes the concurrency primitive, each statement and order statement. The concurrency primitive is used to realize the concurrency of different drone groups. The each statement is used to realize the concurrency of multiple drones in a drone group. The order statement is used to control the drones in a drone group to execute tasks in sequence. Step S5-3: After executing the steps in the routine structure, execute the steps in the target structure. When the target structure is empty, end the multi-machine task. When the target structure is not empty, the last statement in the target structure must be an expression prefixed with $. Determine whether to repeat the steps in the routine structure based on the truth value of the expression. If the expression is false, repeat the steps in the routine structure. If the expression is true, end the multi-machine task.

6. The drone swarm task description system with embedded AI strategy according to claim 1, characterized in that: The stand-alone behavior definition module includes stand-alone behavior definition units, and each stand-alone behavior definition unit can call the action definition module and other stand-alone behavior definition units. Each of the single-machine behavior definition units has a flow control structure. The single-machine behavior process is defined by executing the flow control structure. The definition of the single-machine behavior process includes: Step S6-1: Initialize the structure to initialize the single-machine behavior; Step S6-2: After the single-machine behavior initialization, the steps in the routine structure are executed, and the concurrency between multiple devices on a single UAV is realized through the || concurrency primitive in the routine structure; Step S6-3: After executing the steps in the routine structure, execute the steps in the target structure. When the target structure is empty, end the stand-alone behavior. When the target structure is not empty, the last statement in the target structure must be an expression prefixed with $. Determine whether to repeat the steps in the routine structure based on the truth value of the expression. If the expression is false, repeat the steps in the routine structure. If the expression is true, end the stand-alone behavior.

7. The drone swarm task description system with embedded AI strategy according to claim 1, characterized in that: The dependency import module describes the filenames of external dependency packages through the dependency import unit.

8. The drone swarm task description system with embedded AI strategy according to claim 1, characterized in that: The action definition module includes an API call unit, which describes the process of a single API call by the UAV to a certain device, and the API call unit is defined by an external dependency file.

9. The drone swarm task description system with embedded AI strategy according to claim 1, characterized in that: The communication primitive module includes POST, GET, DGET, and MODIFY statements; The communication primitive module adopts a blackboard-based communication primitive to present messages on the blackboard in the form of key-value pairs. The key-value pairs are not in a one-to-one correspondence, and the values ​​include numerical values ​​or strings. The POST statement is used to post key-value pairs on the blackboard; The GET statement is used to retrieve a value corresponding to a key from the blackboard and store the value in a local variable; The DGET statement is executed after the GET statement, reads the value from the local variable, and then deletes the value from the blackboard. The MODIFY statement is used to modify the value corresponding to one of the keys on the blackboard. The execution logic of the MODIFY statement is based on the execution of the GET statement, and the local variable is used in the expression.

10. A drone swarm task description system capable of embedding AI strategies according to claim 1, characterized in that: The platform description module interacts with the simulation environment by configuring the platform statement. When the platform statement is not configured, it only executes the task logic and does not interact with the simulation environment. The platform statement is configured at most once.

Citation Information

Patent Citations

  • Unmanned aerial vehicle cluster task allocation method and device and unmanned aerial vehicle cluster system

    CN112270488A

  • Distribution and scheduling method based on separable tasks in distributed network environment

    CN113238847A