A data-driven security control method, terminal, and storage medium for an unmanned system

Abstract

The present invention discloses a data-driven security control method, terminal and storage medium for an unmanned system, which relates to the technical field of unmanned system security control. In the offline solution stage, the connection between the unmanned control device and the controller is disconnected, and the applied control input sequence and the corresponding state data are collected; a semi-definite programming problem is constructed according to the control input sequence and the state data, and the state feedback control gain of the controller is constructed according to the optimal solution of the problem and the set unsafe region; in the online operation stage, the connection between the unmanned control device and the controller is maintained, and the state measurement data of the unmanned control device is collected; the controller generates control input data through the state feedback control gain and the state measurement data. The present invention designs the controller through the control input sequence and state data collected offline, and can realize the stable operation of the unmanned system without prior identification of the unmanned control device. It can also ensure that the state of the unmanned system meets the safety constraints and has the maximum robustness to system changes.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned system safety control, and particularly to a data-driven safety control method, a terminal, and a storage medium for an unmanned system. Background Art

[0002] Unmanned systems, with unmanned vehicles, robots, unmanned aerial vehicles, unmanned boats, etc. as carriers, integrate advanced artificial intelligence, Internet of Things, and industrial Internet technologies, and have shown important application values in multiple fields such as civilian and industrial. Intelligent cooperative control is an important application direction of artificial intelligence technology. The problems faced by the intelligent cooperation of unmanned systems include: it is difficult to construct a complex model of unmanned systems, so traditional methods based on system identification cannot obtain an accurate system model, resulting in the control algorithms designed therefrom being unable to meet the requirements of control accuracy.

[0003] Recently, with the development of big data and computing technologies, data-driven control methods have gradually emerged, and the corresponding data-driven controllers have achieved good results in terms of stability and optimization.

[0004] However, during the operation in the real world, in addition to stability and basic optimality, there are often some restrictions on the inputs and states of the system to ensure the safety of system operation. Taking an unmanned vehicle fleet as an example, if the distance between any two unmanned vehicles cannot be guaranteed to have a certain lower limit, collisions will occur between the unmanned vehicles. These restrictions indicate that it is very important to incorporate safety restrictions into the design of system controllers. However, existing data-driven control methods do not impose restrictions on the states and inputs of the system.

[0005] Therefore, there is still room for improvement and development in the prior art. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide a data-driven safety control method, a terminal, and a storage medium for an unmanned system, aiming at the above-mentioned defects of the prior art, to solve the problem that the existing data-driven safety control method for unmanned systems lacks safety restrictions on the states and inputs of the system and is difficult to ensure the safety of system operation.

[0007] The technical solution adopted by the present invention to solve the problem is as follows:

[0008] In a first aspect, an embodiment of the present invention provides a data-driven safety control method for an unmanned system, and the method includes:

[0009] For the offline solution stage, disconnect the data connection between the unmanned control device and the controller in the unmanned system, and collect the control input sequence applied to the unmanned control device and the state data of the unmanned control device;

[0010] Construct a semi - definite programming problem based on the control input sequence and the state data; and construct the state - feedback control gain of the controller based on the optimal solution of the semi - definite programming problem and the set unsafe region for the operation of the unmanned control device's state.

[0011] For the online operation stage, maintain the data connection between the unmanned control device and the controller, and collect the state measurement data of the unmanned control device.

[0012] Send the state measurement data to the controller, and generate the control input data of the unmanned control device based on the state measurement data through the state - feedback control gain of the controller.

[0013] In one embodiment, the control input sequence is a series of persistently exciting control input data.

[0014] In one embodiment, the dynamic equation of the unmanned control device to be stabilized is:

[0015] ;

[0016] Where, , , are respectively the state value of the unmanned control device at time , the control input value, and the unknown disturbance of the unmanned control device; the state value of the unmanned control device has a dimension of , the control input value has a dimension of ; the unknown disturbance has a dimension of ; the matrix is an unknown real matrix of dimension , the matrix is an unknown real matrix of dimension ; the matrix is a state - feedback control gain matrix to be designed with a dimension of .

[0017] In one embodiment, the calculation equation of the unsafe region is:

[0018] ;

[0019] Where, represents the unsafe region; represents the set of all real vectors with a dimension of ; is an integer greater than 1, representing the number of safety constraints; is a constraint vector with a dimension of . Denote the vector transpose; is a constraint scalar.

[0020] In one embodiment, constructing a semidefinite programming problem according to the control input sequence and the state data includes:

[0021] Construct a data matrix based on the collected control input sequence and state data; wherein, the data matrix includes an input data matrix, a state data matrix, and an evolved state data matrix;

[0022] Construct a semidefinite programming problem according to the data matrix.

[0023] In one embodiment, the semidefinite programming problem is established as:

[0024] ;

[0025] wherein, is a real positive definite symmetric matrix to be solved with dimension ; is a real matrix to be solved with dimension ; , , is a one-dimensional scalar to be solved; Greater than 0, representing the maximum operating range of the pre-given system state; Represents the greater than or equal sign of the matrix, Represents the less than or equal sign of the matrix;

[0026] Matrix and are defined as:

[0027] ;

[0028] ;

[0029] wherein, is a constant between 0 and 1 given in advance; for any positive integer and , represents the identity matrix with dimension , represents the all-zero matrix with dimension ; The input data matrix constructed for the applied control input sequence, for transpose; is the evolved state data matrix, for The transpose of; is the state data matrix, is the transpose of; is the real matrix to be solved, is the transpose of.

[0030] In one embodiment, the controller is established as:

[0031] ;

[0032] wherein, , are respectively the state value and control input value of the unmanned control device; , , are the optimal solutions that can be obtained for the semidefinite programming problem.

[0033] In one embodiment, collecting the state measurement data of the unmanned control device includes:

[0034] Measuring the state of the unmanned control device at each moment through a sensor to obtain state measurement data.

[0035] In a second aspect, an embodiment of the present invention further provides a terminal, where the terminal includes a memory and at least one processor; the memory stores a program; the program includes instructions for executing the unmanned system data-driven security control method as described in any one of the above; the processor is configured to execute the program.

[0036] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which multiple instructions are stored, and the instructions are suitable for being loaded and executed by a processor to implement the steps of the unmanned system data-driven security control method as described in any one of the above.

[0037] Advantages of the present invention: In the offline solution stage of the present invention, the data connection between the unmanned control device and the controller in the unmanned system is disconnected, and the control input sequence applied to the unmanned control device and the state data of the unmanned control device are collected; a semidefinite programming problem is constructed according to the control input sequence and the state data; and according to the optimal solution of the semidefinite programming problem and the unsafe area where the state of the set unmanned control device operates, the state feedback control gain of the controller is constructed; for the online operation stage, the data connection between the unmanned control device and the controller is maintained, and the state measurement data of the unmanned control device is collected; the state measurement data is sent to the controller, and the control input data of the unmanned control device is generated based on the state measurement data through the state feedback control gain of the controller. The present invention designs a controller through the open-loop and noisy control input sequence and state data collected offline, and can achieve the stable operation of the unmanned system without prior identification of the unmanned control device. And it can also ensure that the state of the unmanned system meets the safety constraints, and at the same time has the maximum robustness to system changes. Description of the Drawings

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1 It is a schematic flowchart of the data-driven safety control method for an unmanned system provided by an embodiment of the present invention.

[0040] Figure 2 It is a structural diagram of an unmanned system provided by an embodiment of the present invention.

[0041] Figure 3 It is a schematic diagram of the relationship between the state reachable set and the danger zone of the unmanned system under the designed controller provided by an embodiment of the present invention.

[0042] Figure 4 It is a schematic diagram of the evolution trajectory of the system state provided by an embodiment of the present invention.

[0043] Figure 5 It is a schematic diagram of the relationship between the system state evolution trajectory and the state reachable set provided by an embodiment of the present invention.

[0044] Figure 6 It is a schematic block diagram of the terminal provided by an embodiment of the present invention. Detailed Embodiments

[0045] The present invention discloses a data-driven security control method, terminal and storage medium for an unmanned system. To make the objectives, technical solutions and effects of the present invention clearer and more definite, the following further describes the present invention in detail with reference to the accompanying drawings and by way of examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0046] Those skilled in the art of the present technology can understand that, unless specifically stated otherwise, the singular forms "a", "an", "the" and "said" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present invention means the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups. It should be understood that when we say that an element is "connected" or "coupled" to another element, it can be directly connected or coupled to other elements, or there may also be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The phrase "and / or" used herein includes all or any unit and all combinations of one or more related listed items.

[0047] Those skilled in the art of the present technology can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the general understanding of those of ordinary skill in the field to which the present invention belongs. It should also be understood that terms such as those defined in a general dictionary should be understood to have a meaning consistent with the meaning in the context of the prior art, and will not be interpreted with an idealized or overly formal meaning unless specifically defined as here.

[0048] In view of the above defects of the prior art, the present invention provides a data-driven security control method for an unmanned system, and the method includes: for the offline solution stage, disconnect the data connection between the unmanned control device and the controller in the unmanned system, and collect the control input sequence applied to the unmanned control device and the state data of the unmanned control device; construct a semi-definite programming problem according to the control input sequence and the state data; and construct the state feedback control gain of the controller according to the optimal solution of the semi-definite programming problem and the set unsafe area for the state operation of the unmanned control device; for the online operation stage, maintain the data connection between the unmanned control device and the controller, and collect the state measurement data of the unmanned control device; send the state measurement data to the controller, and generate the control input data of the unmanned control device based on the state measurement data through the state feedback control gain of the controller. The present invention designs the controller through the open-loop and noisy control input sequence and state data collected offline, and can realize the stable operation of the unmanned system without prior identification of the unmanned control device. Moreover, it can ensure that the state of the unmanned system satisfies the safety constraints and has the maximum robustness to system changes.

[0049] As Figure 1 shown, the method specifically includes the following steps:

[0050] Step S100, for the offline solution stage, disconnect the data connection between the unmanned control device and the controller in the unmanned system, and collect the control input sequence applied to the unmanned control device and the state data of the unmanned control device;

[0051] Step S200, construct a semi-definite programming problem according to the control input sequence and the state data; and construct the state feedback control gain of the controller according to the optimal solution of the semi-definite programming problem and the set unsafe area for the state operation of the unmanned control device.

[0052] The unmanned control device in this embodiment can also be referred to as a physical process. The goal of this embodiment is to construct a controller (or a safety controller) for an unmanned system, so that the unmanned system can ensure that its state never violates the safety constraints under certain degrees of interference, attacks, or actuator failures. Taking the unmanned control device as an unmanned aerial vehicle as an example, the controller can be the on-board computer or the remote control handle of the unmanned aerial vehicle. The technical solution of this embodiment is divided into two stages, one is the offline solution stage, and the other is the online operation stage. The offline solution stage includes two processes. The first is the open-loop data collection stage, which is used to collect the control input sequence and the corresponding state data of the unmanned control device; the second is the controller solution stage, which is used to construct the state feedback control gain of the controller. Specifically, in the open-loop data collection stage, the unmanned control device is not connected to the controller, and a series of continuously excited control input data is directly applied to the unmanned control device, that is, the control input sequence (or the input sequence) is obtained, and the state data of the system is collected, and the control input data and the state data are recorded. In the controller solution stage, a data-based semi-definite programming problem is constructed using the collected data, and the state feedback control gain is constructed using the optimal solution of the semi-definite programming problem.

[0053] As Figure 1 shown, the components of the unmanned system (or the unknown unmanned system) mainly include a controller and an unmanned control device (i.e., the physical process). In addition, it can also include an actuator and a detector. This embodiment designs the controller for the unmanned system, aiming to ensure the stable operation of the unknown system while its state always satisfies the safety constraints, and at the same time has the maximum robustness to system changes.

[0054] In one implementation, the dynamic equation of the unmanned control device to be stabilized is:

[0055] ;

[0056] where , , are respectively the state value, the control input value, and the unknown disturbance of the unmanned control device at time ; the state value of the unmanned control device has a dimension of , the dimension of the control input value is ; the dimension of the unknown disturbance is ; the matrix is an unknown real matrix of dimension , and the matrix is an unknown real matrix of dimension ; the matrix The state feedback control gain matrix to be designed in terms of dimensions.

[0057] For example, based on the dynamic equations of the above-mentioned unmanned system and the unmanned control device to be stabilized, the specific process of the data collection phase is as follows: Disconnect the data connection between the physical process and the controller, directly apply T control input data to the physical process, and collect the state data of the physical process. Specifically, the unknown disturbance during the offline operation process is bounded, that is, for any offline operation time , the offline disturbance satisfies , where is a known constant. Let , and the control input sequence composed of T inputs satisfies - order persistent excitation. Bring the control input sequence into the unmanned system for operation, and collect the state data of the corresponding physical process.

[0058] Furthermore, the calculation equation of the unsafe region is:

[0059] ;

[0060] where represents the unsafe region; represents the set of all real vectors with dimension ; is an integer greater than 1, representing the number of safety constraints; is a constraint vector with dimension ; represents the transpose of the vector ; is a constraint scalar, used to ensure that the real-time state of the system never enters this unsafe region.

[0061] In one implementation, constructing a semidefinite programming problem based on the control input sequence and the state data includes:

[0062] Constructing a data matrix according to the collected control input sequence and state data; wherein, the data matrix includes an input data matrix, a state data matrix, and an evolved state data matrix;

[0063] Constructing a semidefinite programming problem according to the data matrix.

[0064] Specifically, this embodiment will construct three data matrices using the applied control input sequence and the collected states, namely the input data matrix, the state data matrix, and the evolved state data matrix, and construct a data-based semidefinite programming problem based on these three data matrices. This semidefinite programming problem is equivalent to an optimization problem. The optimization goal of this embodiment is the maximum process noise that the system can withstand. Therefore, the controller obtained by solving this semidefinite programming problem can ensure that the state of the unmanned system satisfies the safety constraints and has the maximum robustness to system changes.

[0065] For example, an input data matrix is constructed using the applied control input sequence and the collected states , the state data matrix , and the evolved state data matrix .

[0066] Furthermore, the semidefinite programming problem is established as:

[0067] ;

[0068] where is a real positive definite symmetric matrix to be solved with dimension ; is a real matrix to be solved with dimension ; , , is a one-dimensional scalar to be solved; is greater than 0, representing the maximum operating range of the pre-given system state; represents the greater than or equal sign of the matrix, represents the less than or equal sign of the matrix;

[0069] The matrices and are defined as:

[0070] ;

[0071] ;

[0072] where, for any matrix or vector , represents the transpose of the matrix , represents the transpose of the vector ; is a constant between 0 and 1 pre-given; for any positive integers and , represents the dimension being the identity matrix, denotes a zero matrix with dimensions ; the input data matrix constructed for the applied control input sequence, is the transpose of; is the evolution state data matrix, is the transpose of; is the state data matrix, is the transpose of; is the real matrix to be solved, is the transpose of.

[0073] Furthermore, the controller is established as:

[0074] ;

[0075] where , are respectively the state value and the control input value of the unmanned control device; , , are the optimal solutions that can be obtained from the semidefinite programming problem.

[0076] Step S300, for the online operation stage, maintain the data connection between the unmanned control device and the controller, and collect the state measurement data of the unmanned control device;

[0077] Step S400, send the state measurement data to the controller, and generate the control input data of the unmanned control device based on the state measurement data through the state feedback control gain of the controller.

[0078] Specifically, in the online operation stage, the unmanned control device is connected to the controller through a network, and the state measurement data of the unmanned control device is transmitted to the controller through a transmission channel. The controller uses the state sent by the system collected at each moment and directly implements closed-loop control on the unmanned control device through the offline state feedback control gain matrix, thereby forming a closed-loop system. The data-driven safety control method provided in this embodiment can meet the state constraints for the unmanned control device, and the closed-loop system can obtain greater robustness to noise.

[0079] For example, in the online operation stage, the unmanned control device is connected to the controller, and the state of the unmanned control device is measured by a sensor at each moment and the state measurement data is sent to the controller through the network. The controller is designed as . Generate control input data through the controller. For those that satisfy For unknown disturbances, the system can always operate in the safe area.

[0080] Taking a robot embodiment to verify the technical effect of the method of the present invention, as shown in FIGS. 3, Figure 4 , Figure 5 shows the effect diagram of a robot embodiment operating with the controller of this embodiment for 50 unit times, and the corresponding system matrix is:

[0081] , ;

[0082] Set parameters, T = 15, = 0.02, = 0.8.

[0083] As shown in Figure 3 , the unsafe area is defined as the union of the first subdomain and the second subdomain :

[0084] ;

[0085] ;

[0086] ;

[0087] By solving the semi - definite programming problem, the feedback gain matrix (i.e., the state - feedback control gain equivalent to the controller) is obtained:

[0088] ;

[0089] And the maximum boundary of the online noise that can be tolerated is = 0.117.

[0090] Figure 3 The dark ellipse in

[0091] Figure 4 is the reachable set of the state of the unmanned system under the designed controller, that is, the state of the system can only operate within this set. In this embodiment, the safety constraints of the system are characterized by the reachable set of the state to ensure the safety of the system state. Figure 5

[0092] Beneficial effects:

[0093] 1. The data-driven security control method provided by the present invention can obtain a data-driven controller by only solving an offline low-complexity and completely data-based semidefinite programming problem, and the overall scheme has a very low computational complexity.

[0094] 2. The data-driven security control method provided by the present invention can ensure that during the online operation stage, the state of the unmanned system always satisfies the real-time security constraints, and the unmanned system has the maximum robustness to noise.

[0095] 3. The controller designed by the data-driven security control method provided by the present invention can make the system operate stably and achieve abnormal state detection under the condition that the system matrix is unknown and considering the security constraints on the state and actuator.

[0096] Based on the above embodiments, the present invention also provides a terminal, and its principle block diagram can be as Figure 6 shown. The terminal includes a processor, a memory, a network interface, and a display screen connected through a system bus. Among them, the processor of the terminal is used to provide computing and control capabilities. The memory of the terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the terminal is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes the data-driven security control method for the unmanned system. The display screen of the terminal can be a liquid crystal display screen or an electronic ink display screen.

[0097] Those skilled in the art can understand that Figure 6 the principle block diagram shown in

[0098] is only a block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the terminal to which the solution of the present invention is applied. The specific terminal may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0099] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided by the present invention can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0100] In summary, the present invention discloses a data-driven security control method, terminal, and storage medium for an unmanned system, relating to the technical field of unmanned system security control. The method includes: for the offline solution stage, disconnect the data connection between the unmanned control device and the controller in the unmanned system, and collect the control input sequence applied to the unmanned control device and the state data of the unmanned control device; construct a semi-definite programming problem according to the control input sequence and the state data; and construct the state feedback control gain of the controller according to the optimal solution of the semi-definite programming problem and the unsafe region where the state of the set unmanned control device operates; for the online operation stage, maintain the data connection between the unmanned control device and the controller, and collect the state measurement data of the unmanned control device; send the state measurement data to the controller, and generate the control input data of the unmanned control device based on the state measurement data through the state feedback control gain of the controller. The present invention designs a controller through the open-loop, noisy control input sequence and state data collected offline, and can achieve the stable operation of the unmanned system without the need for prior identification of the unmanned control device. Moreover, it can ensure that the state of the unmanned system meets the safety constraints and has the maximum robustness to system changes.

[0101] It should be understood that the application of the present invention is not limited to the above examples. For those of ordinary skill in the art, improvements or changes can be made according to the above description, and all such improvements and changes should fall within the protection scope of the appended claims of the present invention.

Claims

1. A data-driven security control method for an unmanned system, characterized in that The method includes: For the offline solution stage, disconnect the data connection between the unmanned control device and the controller in the unmanned system, and collect the control input sequence applied to the unmanned control device and the state data of the unmanned control device; Construct a semi-definite programming problem according to the control input sequence and the state data; and construct the state feedback control gain of the controller according to the optimal solution of the semi-definite programming problem and the unsafe region where the state of the set unmanned control device operates; For the online operation stage, maintain the data connection between the unmanned control device and the controller, and collect the state measurement data of the unmanned control device; Send the state measurement data to the controller, and generate the control input data of the unmanned control device based on the state measurement data through the state feedback control gain of the controller; The dynamic equation of the unmanned control device to be stabilized is: ； Among them, , , are respectively the state value of the unmanned control device at a certain moment, the control input value, and the unknown disturbance of the unmanned control device; the state value of the unmanned control device has a dimension of , the control input value has a dimension of ; the unknown disturbance has a dimension of ; the matrix is an unknown real matrix of dimension , the matrix is an unknown real matrix of dimension ; The calculation equation of the unsafe region is: ； Among them, represents an unsafe area; represents the set of all real vectors of dimension ; is an integer greater than 1, representing the number of safety constraints; is a constraint vector of dimension ; represents the transpose of the vector ; is a constraint scalar; The semi-definite programming problem is established as: ； Among them, is a real positive definite symmetric matrix to be solved with dimension ; is a real matrix to be solved with dimension ; , , are one-dimensional scalars to be solved; is greater than 0, indicating the maximum operating range of the pre-given system state; represents the greater than or equal sign of the matrix, represents the less than or equal sign of the matrix; Matrix and are defined as: ； ； wherein, is a constant given in advance between 0 and 1; for any positive integer and , represents an identity matrix of dimension , represents a zero matrix of dimension ; is an input data matrix constructed for the applied control input sequence, is 's transpose; is an evolution state data matrix, is 's transpose; is a state data matrix, is 's transpose; is a real matrix to be solved, is 's transpose.

2. The method for data-driven security control of an unmanned system according to claim 1, characterized in that, The control input sequence is a series of persistently exciting control input data.

3. The method for data-driven security control of an unmanned system according to claim 1, characterized in that, Constructing a semi-definite programming problem according to the control input sequence and the state data includes: Construct a data matrix according to the collected control input sequence and state data; wherein, the data matrix includes an input data matrix, a state data matrix, and an evolved state data matrix; Construct a semi-definite programming problem according to the data matrix.

4. The method for data-driven security control of an unmanned system according to claim 1, characterized in that The controller is established as: ； Among them, and are the state value and control input value of the unmanned control device respectively; the matrix is a state feedback control gain matrix to be designed with , and being the optimal solutions that can be obtained for the semidefinite programming problem.

5. The data-driven security control method for an unmanned system according to claim 1, wherein Collecting the state measurement data of the unmanned control device includes: Measure the state of the unmanned control device at each moment through a sensor to obtain state measurement data.

6. A terminal, characterized in that The terminal includes a memory and at least one processor; the memory stores a program; the program contains instructions for executing the unmanned system data-driven safety control method according to any one of claims 1-5; the processor is used to execute the program.

7. A computer-readable storage medium having a plurality of instructions stored thereon, characterized in that, The instructions are adapted to be loaded and executed by the processor to implement the steps of the unmanned system data-driven safety control method according to any one of claims 1-5.

Images