Manipulator situation awareness space target recognition pre-judgment method, system and equipment based on brain-computer interface and storage medium

Abstract

The invention discloses a manipulator situation awareness space target recognition pre-judgment method, system and device based on a brain-computer interface and a storage medium, and the method comprises the following steps: S1, forming a plurality of grabbing modes based on different types of grabbing electroencephalogram signals of a user; s2, on the basis of the captured image of the captured target, predicting a moving path of the captured target and confirming a capturing mode; s3, based on the predicted moving path and grabbing mode of the grabbed target, grabbing the grabbed target; compared with the prior art, the brain-computer interface normal form of the steady-state visual evoked potential is adopted, the user gazes the instructions corresponding to various different grabbing modes on the display screen, and the instructions induce the user to generate the steady-state visual evoked potential through different flicker frequencies; the electroencephalogram signals are collected through an electroencephalogram signal amplifier and an electroencephalogram interface electrode, and typicality correlation analysis processing is carried out.

Description

Technical Field

[0001] This invention relates to the fields of brain-computer interfaces and spatial situational awareness, specifically to a method, system, device, and storage medium for spatial target recognition and prediction based on brain-computer interfaces for robotic arms. Background Technology

[0002] Currently, brain-computer interface (BCI) robotic arms integrate steady-state visual evoked potentials (SSVEPs) and blink-related electrooculography (EOG) signals, using a BCI to control the robotic arm system. In existing technology, the user selects one of 20 different stimulus frequencies to control the robotic arm's movement. The instruction set consisting of these 20 different stimulus targets controls the robotic arm's movement in three-dimensional space. When the user controls the robotic arm to grasp a target via the BCI, the computer vision system can identify the target object and assist the robotic arm in completing the grasping action. However, current brain-computer interface robotic arm control systems focus too much on the success rate of grasping stationary objects, tending to use two-finger or three-finger grippers in the selection of end effectors. In real life, however, the objects grasped by humans include not only stationary objects but also moving objects, and different grasping methods are used depending on the shape and size of the target object. Therefore, there is still considerable room for improvement in the precise control of grasping moving objects and grasping methods using brain-computer interface robotic arms. Summary of the Invention

[0003] The purpose of this invention is to address the shortcomings of existing brain-computer interface robotic hands in terms of fine control over grasping moving objects and grasping methods. To this end, a method, system, device, and storage medium for situational awareness spatial target recognition and prediction of robotic hands based on brain-computer interface are proposed.

[0004] To achieve the above objectives, the present invention adopts the following technical solution:

[0005] A brain-computer interface-based method for situational awareness and spatial target recognition and prediction in robotic arms includes the following steps:

[0006] S1. Based on different types of users, multiple capture modes are formed by capturing EEG signals.

[0007] S2. Based on the captured target image, predict the target's movement path and confirm the capture mode;

[0008] S3. Based on the predicted movement path and grasping pattern of the grasping target, grasp the grasping target.

[0009] As a further preferred embodiment of the present invention, S1 includes the following specific steps:

[0010] S1.1 Acquire the actual EEG signals when the user grabs different moving target objects;

[0011] S1.2. Set different grasping representations for the grasping posture of moving target objects of different shapes. The grasping representation includes graphic shape, size, and color.

[0012] S1.3, Obtain the user's reference EEG signals for various grasping representations;

[0013] S1.4 Based on the Pearson correlation coefficient and the Lagrange equation, the flashing frequency of different grasping representations is calculated according to the actual acquired EEG signal and the reference EEG signal.

[0014] S1.5. Based on the flashing frequency of different grasping representations, obtain the EEG signal of the user during real-time grasping to obtain the corresponding grasping mode.

[0015] As a further preferred embodiment of the present invention, step S2 includes the following specific steps:

[0016] S2.1 Based on the detection principle of the space situational awareness system, construct a mathematical model of the detection capability of the space situational awareness system;

[0017] S2.2 Establish a spatial coordinate system;

[0018] S2.3 Based on the camera on the robotic arm, capture the target and form an image of the target and its corresponding spatial coordinate system;

[0019] S2.4 Based on the mathematical model of the detection capability of the spatial situational awareness system, predict the movement path of the target to be captured in the spatial coordinate system and confirm the capture mode.

[0020] As a further preferred embodiment of the present invention, step S3 includes the following specific steps:

[0021] S3.1. Based on the grasping mode, determine the grasping pose in the spatial coordinate system corresponding to that grasping mode:

[0022] K i =(x,y,z,Flag) sky Flag land Flag (Q)

[0023] In the above formula, K i Represents the grasping pose in the spatial coordinate system; (x, y, z) represents the center point of the grasping pose of the moving target object in the spatial coordinate system; Flag sky Represents the constraint parameters of the space-based situational awareness system; Flagland Flag represents the constraint parameters of the ground-based situational awareness system; Q represents the constraint parameters of the space-based situational awareness system; Q is the capture quality score, and the larger the Q value, the higher the probability of successful capture.

[0024] S3.2 Based on the grasping pose in the spatial coordinate system, transform the original grasping pose base coordinate system of the robotic arm.

[0025] A method, system, device, and storage medium for situational awareness spatial target recognition and prediction of a robotic arm based on a brain-computer interface are characterized by including a brain-computer interface subsystem, a situational awareness subsystem, and a robotic arm subsystem.

[0026] The brain-computer interface subsystem is used to acquire the electroencephalogram (EEG) signals of the grasping pattern required by the user to grasp a moving target object.

[0027] The situational awareness subsystem is used to construct a mathematical model of the detection capability of the space situational awareness system, and to predict the movement path of the target to be captured and confirm the capture mode.

[0028] The robotic arm subsystem receives the predicted movement path and grasping mode of the target sent by the situational awareness subsystem, performs grasping posture coordinate transformation, and controls the robotic arm to grasp.

[0029] A computer device includes one or more processors and a memory for storing one or more programs; when the one or more programs are executed by the processor, the processor enables the processor to implement a brain-computer interface-based method for spatial target recognition and prediction of robotic arm situational awareness.

[0030] A computer storage medium storing at least one program instruction, wherein the at least one program instruction is loaded and executed by a processor to realize a brain-computer interface-based robotic hand situational awareness spatial target recognition and prediction method.

[0031] The present invention proposes a brain-computer interface-based method, system, device, and storage medium for spatial target recognition and prediction in robotic arms, which has the following advantages compared with existing technologies:

[0032] 1. In order to solve the problem that traditional robotic arms can only grasp static objects and cannot predict and grasp moving objects, this invention uses situational awareness technology to predict moving objects and uses a five-fingered robotic arm to grasp the target object. The dexterous structure of the five-fingered robotic arm can adopt different grasping modes and grasping postures to achieve precise grasping control of the target object.

[0033] 2. To achieve the use of a non-invasive brain-computer interface to control a five-fingered robotic hand to grasp target objects, this invention employs a method of determining the grasping mode and grasping posture to achieve precise control of the robotic hand. On one hand, the brain-computer interface is used to acquire the EEG signals of the user's desired grasping mode, and then the grasping mode is obtained by performing canonical correlation analysis on the EEG signals. On the other hand, the target user's image is captured, and then the spatial position of the target object is predicted and the grasping posture is confirmed based on the captured image using situational awareness technology, thereby enabling the five-fingered robotic hand installed at the end of the robotic arm to predict and finely control the moving target object. Attached Figure Description

[0034] Figure 1 This is a schematic diagram of the basic process of implementing the method of the present invention;

[0035] Figure 2 This is a schematic diagram illustrating the basic principle of the implementation method of the present invention;

[0036] Figure 3 This is a schematic diagram of the grasping mode corresponding to the brain-computer interface commands implemented in this invention;

[0037] Figure 4 This is a flowchart of the situational awareness spatial target prediction and judgment method in the implementation of the present invention. Detailed Implementation

[0038] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments.

[0039] Example 1: Combining Figure 1-4 A brain-computer interface-based method for situational awareness, spatial target prediction, and control of robotic arms, including:

[0040] S1. Based on the different types of users, multiple capture modes are formed by capturing EEG signals.

[0041] The system acquires EEG signals representing the grasping pattern required for a user to grasp a moving target object, and performs canonical correlation analysis on the EEG signals to obtain the grasping pattern.

[0042] Grasping moving objects of different shapes requires the five fingers of a five-fingered robotic hand to operate in different postures. These different finger postures determine the different grasping patterns required for the robotic hand to grasp moving objects. Therefore, a representation object is set for each grasping pattern on the display screen. Different grasping patterns correspond to different representation objects represented by stimulation blocks with different flashing frequencies, inducing steady-state visual evoked potentials in the user. Based on the steady-state visual evoked potentials generated by the user gazing at the stimulation blocks with different flashing frequencies corresponding to different grasping patterns on the display screen, the EEG signal indicating the user's selection of the grasping pattern can be obtained.

[0043] S1.1 Acquire the actual EEG signals when the user grabs different moving target objects.

[0044] S1.2. Set different grasping representations for the grasping posture of moving target objects of different shapes. The grasping representation includes graphic shape, size and color. Different grasping representations represent different object shapes, sizes and the number and posture of the fingers used when grasping.

[0045] In this invention, the screen is divided into six regions of different shapes to represent different grasping modes, namely grasping mode 1 to grasping mode 6. Grasping mode 1 corresponds to a rectangle, indicating a larger object to be grasped; grasping mode 2 corresponds to a square, indicating a smaller object to be grasped; grasping mode 3 corresponds to a triangle, indicating a regularly shaped object to be grasped; grasping mode 4 corresponds to a rhombus, indicating an irregularly shaped object to be grasped; grasping mode 5 corresponds to a circle, indicating that the object is grasped using three of the five fingers; grasping mode 6 corresponds to an ellipse, indicating that the object is grasped using all five fingers, such as... Figure 3 As shown.

[0046] S1.2 Obtain reference EEG signals from the user for various grasping representations.

[0047] S1.3 Based on the Pearson correlation coefficient and the Lagrange equation, the flashing frequency of different grasping representations is calculated according to the actual acquired EEG signal and the reference EEG signal.

[0048] S1.4. Based on the flashing frequency of different grasping representations, obtain the EEG signal of the user during real-time grasping to obtain the corresponding grasping mode.

[0049] Acquire the actual EEG signals M = (M1, M2, ..., M...) required for the user to grasp a moving target object. x The reference EEG signal N = (N1, N2, ..., N) corresponding to the visual stimulus frequency at which the EEG signal was acquired.y This refers to the electroencephalogram (EEG) signals generated when a user observes six regions of different shapes, where M1 to M2 are the most prominent. x These are the actual acquired EEG signals for the 1st to xth grasping modes, N1 to N... y These are the reference EEG signals corresponding to the visual stimulus frequencies of the 1st to yth grasping patterns, respectively, and we have:

[0050]

[0051]

[0052] In the above formula, N i f represents the reference EEG signal corresponding to the visual stimulus frequency of any i-th grasping pattern. i It is the flashing frequency of the i-th grasping mode, that is, the flashing frequency of the i-th different shaped region; t is an intermediate variable, k represents the number of harmonics, and F S Y is the sampling frequency. S This represents the number of sampling points.

[0053] The acquired EEG signal M and the reference EEG signal N corresponding to the visual frequency of any i-th grasping pattern are used. i The linear combination is the vector shown in the following equation:

[0054]

[0055] In the above formula, m is the combined vector of the acquired EEG signals, and W M To obtain the weight matrix of the EEG signal, n i For reference EEG signal N i The combined vector, W N The weight matrix is ​​used as a reference for EEG signals.

[0056] Establish the combined vector m of the acquired EEG signals and the reference EEG signal N as shown in the following formula. i The combined vector n i The Pearson correlation coefficient ρ(f) between them i ):

[0057]

[0058] In the above formula, E represents the expected value, and The combined vector m of the acquired EEG signals and the reference EEG signal N i The combined vector n i The Pearson correlation coefficient ρ(f) between them i Establish a weight matrix W for the acquired EEG signals. M The weight matrix W of the reference EEG signal N The function model.

[0059]

[0060] In the above formula, For M and N i The covariance matrix.

[0061] Treating the above function model as an optimization problem, we construct the Lagrange equation f(W) M W N ):

[0062]

[0063] In the above formula, λ is Lagrange multipliers, C MM Let M be its own covariance matrix, and θ be... Lagrange multipliers For N i Its own covariance matrix; and the Lagrange equation f(W) M W N Regarding the weight matrix W of the acquired EEG signals M The weight matrix W of the reference EEG signal N The partial derivatives are:

[0064]

[0065] In the above formula, For the Lagrange equation f(W) M W N Regarding the weight matrix W of the acquired EEG signals M The partial derivatives, For the Lagrange equation f(W) M W N The weight matrix W of the reference EEG signal N The partial derivatives are used to finally obtain the combined vector M of the acquired EEG signals and the reference EEG signal N. i The combined vector n i The Pearson correlation coefficient ρ(f) between them i ):

[0066] Based on the combined vector m of the acquired EEG signals and the reference EEG signal N i The combined vector n i The Pearson correlation coefficient ρ(f) between them i The blinking frequency f of the object representing the grasping pattern is obtained by solving the following formula. S :

[0067]

[0068] Then, based on the pattern, the object's blinking frequency f S The corresponding crawling mode is obtained.

[0069] S2. Based on the captured target image, predict the target's movement path and confirm the capture mode.

[0070] Specifically, the following steps are included:

[0071] S2.1 Based on the detection principle of the space situational awareness system, construct a mathematical model of the detection capability of the space situational awareness system.

[0072] The mathematical model for the detection capability of the space situational awareness system is expressed as follows:

[0073] Flag = Flag sky +Flag land

[0074]

[0075]

[0076]

[0077]

[0078]

[0079]

[0080]

[0081]

[0082]

[0083] Here, Flag represents the constraint parameters of the space situational awareness system. sky Flag represents the constraint parameters of the space-based situational awareness system. land This represents the constraint parameters of the ground-based situational awareness system, 'a' represents the number of sensors in the space-based situational awareness system, and 'flag' represents the number of sensors in the space-based situational awareness system. k,1 The flag represents the Earth occlusion constraint parameter of the k-th space-based situational awareness system. k,2 The flag represents the ground shadow constraint parameter of the k-th space-based situational awareness system. k,3 The flag represents the solar interference constraint parameter for the k-th space-based situational awareness system. k,4 The parameter 'b' represents the field-of-view constraint parameter of the k-th space-based situational awareness system, and 'b' represents the number of ground-based radars in the ground-based situational awareness system. 'flag' represents the flag. n,1The flag represents the ground-based radar elevation angle constraint parameter for the nth ground-based situational awareness system. n,2 The flag represents the ground-based radar detection yaw angle constraint parameter of the nth ground-based situational awareness system. n,3 Let r represent the ground-based radar detection range constraint parameter of the nth ground-based situational awareness system. k,s Let r represent the position vector of the k-th sensor-mounted platform of the space-based situational awareness system in the geocentric inertial frame. k,s2sun Let r represent the position vector of the k-th sensor-mounted platform of the solar relative to the space-based situational awareness system. k,view Let θ represent the observation vector of the k-th sensor in the space-based situational awareness system. k,fov This represents the maximum field of view of the k-th sensor in the space-based situational awareness system. Indicates r k,view The transpose of r k,s2T ψ represents the position vector of a space target relative to the k-th sensor-mounted platform of the space-based situational awareness system. n,h γ represents the elevation angle of the line connecting the nth ground-based radar of the ground-based situational awareness system to the space target. n The geocentric angle, [σ], represents the arc length between the nth ground-based radar and the nadir point of the space target in the ground-based situational awareness system. n,1 ,σ n,2 ] represents the elevation angle search range of the nth ground-based radar in the ground-based situational awareness system, λ n,p φ represents the longitude of the nth ground-based radar in the geocentric coordinate system of the ground-based situational awareness system. n,h [τ] represents the yaw angle of the line connecting the nth ground-based radar of the ground-based situational awareness system to the space target. n,1 ,τ n,2 R represents the yaw angle search range of the nth ground-based radar in the ground-based situational awareness system. n,OP Let r represent the distance between the nth ground-based radar of the ground-based situational awareness system and the space target. n,op This represents the maximum detection range of the nth ground-based radar in the ground-based situational awareness system.

[0084] Determining whether a space target can be predicted based on the solution results includes:

[0085] If the solution yields Flag = 0, then the spatial target is not visible to the situational awareness system.

[0086] If the obtained Flag is not equal to 0, then the spatial target is visible to the situational awareness system.

[0087] If the obtained Flag sky =0, then space targets are not visible to the space-based situational awareness system;

[0088] If the obtained Flag sky If the value is not equal to 0, then the space target is visible to the space-based situational awareness system.

[0089] If the obtained Flag land =0, then the space target is not visible to the ground-based situational awareness system;

[0090] If the obtained Flag land If the value is not equal to 0, then the space target is visible to the ground-based situational awareness system.

[0091] The space situational awareness system includes: space-based situational awareness system and ground-based situational awareness system.

[0092] The mathematical model for the detection capability of the space situational awareness system determines the predicted value of the target's movement path within the coverage area of ​​space-based and ground-based radars based on the magnitude of the solution results for whether the target is visible to space-based and ground-based radars, and thus determines the target's movement trajectory.

[0093] S2.2 Establish a spatial coordinate system.

[0094] In the robotic arm subsystem, a binocular camera is suspended at the end of the robotic arm, and the relationship between the spatial coordinate system and the robotic arm coordinate system is determined by the "eye outside the hand" and "hand-eye calibration" method.

[0095] S2.3. Based on the camera on the robotic arm, capture the target and form an image of the target and its corresponding spatial coordinate system.

[0096] S2.4 Based on the mathematical model of the detection capability of the spatial situational awareness system, predict the movement path of the target to be captured in the spatial coordinate system and confirm the capture mode.

[0097] Through the space-based and ground-based radar sensors deployed throughout the entire situational awareness system, the system obtains the time point at which the robotic arm receives the grasping command, the center point of the grasping target's grasping pose in the spatial coordinate system, and the constraint parameter Flag of the space-based situational awareness system. sky Ground-based situational awareness system constraint parameters Flag land In addition to the detection performance and accuracy of the detection radar, the movement path of the target to be captured is predicted, and the capture mode is confirmed.

[0098] S3. Based on the predicted movement path and grasping pattern of the grasping target, grasp the grasping target.

[0099] S3.1. Based on the grasping mode, determine the grasping pose in the spatial coordinate system corresponding to the grasping mode.

[0100] K i =(x,y,z,Flag) sky Flagland Flag (Q)

[0101] In the above formula, K i Represents the grasping pose in the spatial coordinate system; (x, y, z) represents the center point of the grasping pose of the moving target object in the spatial coordinate system; Flag sky Represents the constraint parameters of the space-based situational awareness system; Flag land Flag represents the constraint parameters of the ground-based situational awareness system; Q represents the constraint parameters of the space-based situational awareness system; Q is the capture quality score, and the larger the Q value, the higher the probability of successful capture.

[0102] S3.2 Based on the grasping pose in the spatial coordinate system, transform the original grasping pose base coordinate system of the robotic arm.

[0103] The transformation matrix between the base coordinate system A of the robotic arm and the coordinate system B of the robotic arm's end flange is calibrated using the following formula:

[0104]

[0105] In the above formula, The transformation matrix represents the relationship between the base coordinate system A of the robotic arm and the coordinate system B of the robotic arm's end flange. Let be the rotation transformation matrix between the base coordinate system A of the robotic arm and the coordinate system B of the robotic arm's end flange. Let be the position transformation matrix between the base coordinate system A of the robotic arm and the coordinate system B of the end flange of the robotic arm.

[0106] The transformation matrix between the base coordinate system C of the five-finger manipulator and the coordinate system B of the end flange of the manipulator is determined by the following formula:

[0107]

[0108] In the above formula, The transformation matrix represents the coordinate system C between the spatial coordinate system of the five-fingered robotic arm and the coordinate system B of the end flange of the robotic arm. Let be the rotation transformation matrix between the spatial coordinate system C of the five-finger robotic arm and the coordinate system B of the end flange of the robotic arm. Let be the position transformation matrix between the spatial coordinate system C of the five-finger manipulator and the coordinate system B of the end flange of the manipulator.

[0109] The transformation matrix between the spatial coordinate system C of the five-finger robotic hand and the base coordinate system A of the robotic arm is established according to the following formula:

[0110]

[0111] In the above formula, The transformation matrix represents the transformation between the spatial coordinate system C of the five-fingered robotic hand and the base coordinate system A of the robotic arm.

[0112] Example 2: A method, system, device, and storage medium for spatial target recognition and prediction based on brain-computer interface (BCI) for robotic arm situational awareness, characterized by comprising a BCI subsystem, a situational awareness subsystem, and a robotic arm subsystem; wherein, the BCI subsystem is used to acquire EEG signals of the grasping pattern required by the user to grasp a moving target object; the situational awareness subsystem is used to construct a mathematical model of the detection capability of the spatial situational awareness system, predict the movement path of the grasped target, and confirm the grasping pattern; the robotic arm subsystem is used to receive the predicted movement path and grasping pattern of the grasped target sent by the situational awareness subsystem, perform grasping posture coordinate transformation, and control the robotic arm to grasp.

[0113] Example 3: A computer device, the device including one or more processors and a memory, the memory being used to store one or more programs; the one or more processors and the memory are interconnected FPGA processors and DDR SDRAM memory, when the one or more programs are executed by the processor, causing the processor to implement a brain-computer interface-based robotic arm situational awareness spatial target recognition and prediction method.

[0114] Example 4: A computer storage medium storing at least one program instruction, which is loaded and executed by a processor to realize a brain-computer interface-based robotic arm situational awareness spatial target recognition and prediction method.

[0115] The present invention also provides a DDR SDRAM random access memory, wherein the random access memory medium stores Verilog programs or instructions, characterized in that the programs / instructions are programmed to execute a brain-computer interface-based robotic arm situational awareness spatial moving target prediction and control method via an FPGA processor.

[0116] The present invention also provides a Verilog program product, including a Verilog program / instruction, characterized in that the Verilog program / instruction is programmed to execute a brain-computer interface-based robotic hand situational awareness spatial moving target prediction and control method via an FPGA processor.

[0117] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the above embodiments do not limit the present invention in any way, and all technical solutions obtained by equivalent substitution or equivalent transformation fall within the protection scope of the present invention.

Claims

1. A method for spatial target recognition and prediction based on brain-computer interface for robotic arm situational awareness, characterized in that, Includes the following steps: S1. Based on different types of users, multiple capture modes are formed by capturing EEG signals. S2. Based on the captured target image, predict the target's movement path and confirm the capture mode; S3. Based on the predicted movement path and grasping pattern of the grasping target, grasp the grasping target.

2. The method for spatial target recognition and prediction based on brain-computer interface for robotic arm situational awareness according to claim 1, characterized in that, S1 includes the following specific steps: S1.1 Acquire the actual EEG signals when the user grabs different moving target objects; S1.

2. Set different grasping representations for the grasping posture of moving target objects of different shapes. The grasping representation includes graphic shape, size, and color. S1.3, Obtain the user's reference EEG signals for various grasping representations; S1.4 Based on the Pearson correlation coefficient and the Lagrange equation, the flashing frequency of different grasping representations is calculated according to the actual acquired EEG signal and the reference EEG signal. S1.

5. Based on the flashing frequency of different grasping representations, obtain the EEG signal of the user during real-time grasping to obtain the corresponding grasping mode.

3. The method for spatial target recognition and prediction based on brain-computer interface for robotic arm situational awareness according to claim 1, characterized in that, S2 includes the following specific steps: S2.1 Based on the detection principle of the space situational awareness system, construct a mathematical model of the detection capability of the space situational awareness system; S2.2 Establish a spatial coordinate system; S2.3 Based on the camera on the robotic arm, capture the target and form an image of the target and its corresponding spatial coordinate system; S2.4 Based on the mathematical model of the detection capability of the spatial situational awareness system, predict the movement path of the target to be captured in the spatial coordinate system and confirm the capture mode.

4. The method for spatial target recognition and prediction based on brain-computer interface for robotic arm situational awareness according to claim 1, characterized in that, S3 includes the following specific steps: S3.

1. Based on the grasping mode, determine the grasping pose in the spatial coordinate system corresponding to that grasping mode: K i =(x,y,z,Flag sky ,Flag land ,Flag,Q), In the above formula, K i Represents the grasping pose in the spatial coordinate system; (x, y, z) represents the center point of the grasping pose of the moving target object in the spatial coordinate system; Flag sky Represents the constraint parameters of the space-based situational awareness system; Flag land Flag represents the constraint parameters of the ground-based situational awareness system; Q represents the constraint parameters of the space-based situational awareness system; Q is the capture quality score, and the larger the Q value, the higher the probability of successful capture. S3.2 Based on the grasping pose in the spatial coordinate system, transform the original grasping pose base coordinate system of the robotic arm.

5. A system employing any one of the brain-computer interface-based robotic hand situational awareness spatial target recognition and prediction methods according to claims 1 to 4, characterized in that, This includes a brain-computer interface subsystem, a situational awareness subsystem, and a robotic arm subsystem; The brain-computer interface subsystem is used to acquire the electroencephalogram (EEG) signals of the grasping pattern required by the user to grasp a moving target object. The situational awareness subsystem is used to construct a mathematical model of the detection capability of the space situational awareness system, and to predict the movement path of the target to be captured and confirm the capture mode. The robotic arm subsystem receives the predicted movement path and grasping mode of the target sent by the situational awareness subsystem, performs grasping posture coordinate transformation, and controls the robotic arm to grasp.

6. A computer device, characterized in that, The device includes one or more processors and a memory for storing one or more programs; when the one or more programs are executed by the processor, the processor causes the processor to implement the method as described in any one of claims 1 to 4.

7. A computer storage medium, characterized in that, The computer storage medium stores at least one program instruction, which is loaded and executed by a processor to implement the method as described in any one of claims 1 to 4.

Images