Brain-computer interface and man-machine cooperative operation method and system of equipotential robot

Abstract

The invention provides a brain-computer interface (BCI) and man-machine cooperative operation method of an equipotential robot. The method comprises the following steps: an optimization step: optimizing and training a BCI system; in the starting step, a brain-computer interface BCI system and a mechanical arm control system are started and used for receiving and outputting signals; a left side operation step: when a left side operation instruction signal is received, enabling the mechanical arm to perform hooking operation; a right side operation step: when a right side operation instruction signal is received, enabling the mechanical arm to carry out dismounting operation; and a resetting step: recording and storing data of the left side operation step or the right side operation step, and resetting the mechanical arm to an initial position. In an application scene in a 220kV high-voltage dangerous environment, through intelligent operation, the robot can accurately complete high-risk operation on the premise of ensuring personnel safety, the accident risk caused by misoperation is reduced, and the working efficiency and safety can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of workpiece grasping, and specifically, to a brain-computer interface and human-computer collaborative operation method and system of an equipotential robot, and especially to a brain-computer interface and human-computer collaborative operation method and system of an equipotential robot for a substation for high-risk operations. Background Art

[0002] In the field of electric power, live working mainly refers to the maintenance, component replacement or testing of power transmission and transformation equipment without power outages. This operation method can minimize the losses caused by power outages and avoid personal electric shock accidents, and is one of the important development directions of maintenance business. However, due to the complex environment and compact working space of substations, especially in substation equipment with voltage levels of 110kV and above, the installation and removal of temporary grounding wires are restricted by many factors. In these high-voltage environments, operators not only face the risk of electric shock, but also may encounter arc explosions, which seriously threaten personal safety. In terms of operating efficiency, the traditional grounding wire installation method relies entirely on manpower. In actual outdoor work, two operators are required to cooperate in hanging the grounding wire, using an insulated ladder for semi-climbing operations, and hanging a set of grounding wires weighing 20 to 30 kilograms to a grounding point as high as 6-8 meters through a short-circuit grounding rod. This outdoor hanging and removing of grounding wires in high temperature or high noise environments is not only labor-intensive, but also increases the risk of heat stroke and fire because the equipment may overheat at high temperatures.

[0003] In addition, due to the lack of intelligent detection mechanism, the quality of hanging is completely dependent on the quality of workers, and there is a lack of authority management mechanism, resulting in free operation. In the process of use, there are often cases of missing hanging, wrong hanging, missing removal, and mistaken removal. These problems are more prominent in severe weather conditions, such as thunderstorms or storms. These problems lead to the fact that after the installation is completed, the grounding wire status can only be checked manually, which increases the uncertainty of maintenance work and brings risks to people, equipment and power grid safety. The current method of hanging the grounding wire has the disadvantages of high danger and low degree of automation, which greatly restricts the improvement of substation maintenance efficiency. This is no longer suitable for the needs of intelligent operation and inspection of the power grid and safe live work under the new situation.

[0004] Patent document with publication number CN117972545A, A motor imagery EEG signal fusion processing algorithm based on improved LMD-CSP, discloses a motor imagery EEG signal fusion processing algorithm based on improved LMD-CSP. The processing algorithm steps are as follows: S1, data preprocessing: S2, LMD decomposition: S3, frequency band selection: S4, feature extraction: S5, feature vector construction: S6, SVM classifier training: S7, classification and prediction. The present invention verifies the effectiveness of the new feature extraction method. The experiment uses the left and right hand motor imagery EEG signals of 9 subjects as data, adopts an between-subject design, ensures the fairness and objectivity of the experiment, and verifies the effectiveness of the new feature extraction method. Figure 2 Comparing the two methods of CSP and LMD-CSP, LMD-CSP performed better in classification accuracy, reaching 88.6%, while CSP was only 77.8%. This significant difference proves that the improved feature extraction method can better capture useful information in EEG signals, thereby improving classification accuracy. Therefore, it is shown that the proposed feature extraction method is effective and superior, and provides new ideas and methods for the development of the brain-computer interface field. However, this technical solution cannot control the robot or operate under high voltage.

[0005] Therefore, the development of intelligent and safe live working equipment is particularly urgent, and a brain-computer interface and human-computer collaborative operation method and system for an equipotential robot are needed. Summary of the invention

[0006] In view of the defects in the prior art, the purpose of the present invention is to provide a brain-computer interface and human-computer collaborative operation method and system for an equipotential robot.

[0007] According to the present invention, a brain-computer interface and human-computer collaborative operation method of an equipotential robot includes: Optimization steps: optimize and train the brain-computer interface (BCI) system; Startup steps: Start the brain-computer interface BCI system and the robotic arm control system; Left side operation steps: When the robot arm control system receives the left side operation command signal sent by the brain-computer interface BCI system, it instructs the robot arm to perform the hook operation; Right side operation steps: When the robot arm control system receives the right side operation command signal sent by the brain-computer interface BCI system, the robot arm is ordered to perform the dismantling operation; Reset step: After recording and saving the data of the left operation step or the right operation step, reset the robot arm to the initial position.

[0008] Preferably, the optimization step comprises: Steps for setting electrodes: according to the needs of left and right hand motor imagery MI collection, set the distribution of electrodes for collecting EEG signals; specifically, place electrodes at the 8 positions most relevant to controlling left and right hand motor imagery activities, and install the electrodes in the helmet; Extraction step: spatially filter the collected EEG signals in the trained CSP spatial filter to extract the signals corresponding to the MI features of left and right hand movement imagination; Classification processing steps: let the corresponding signal pass through the classifier to classify, and the obtained matrix data is processed in segments, and the value corresponding to the middle time of each segment of data is recorded, that is, the middle value is used as the standard for output judgment, and the difference of the data at the standard position is calculated; Control steps: Use the difference as the control signal of the external device, establish a classification program, and correspond the operation signals of the left operation instruction and the right operation instruction.

[0009] Preferably, the starting step includes: System startup steps: Turn on the brain-computer interface BCI system and the robotic arm control system, perform equipment self-check and system initialization; Signal calibration steps: collect signals through a helmet with electrodes, calibrate the motor imagery MI signal, and make the left and right EEG signals accurately classified; Robot arm positioning step: move the robot arm to a predetermined initial position.

[0010] Preferably, the left side operation steps include: Left signal input steps: The operator sends the left operation command signal through the brain-computer interface BCI system; Ground wire grabbing step: the robot arm control system performs a hooking operation according to the received operation signal instruction, and grabs one end of the ground wire using the end effector; Moving steps: The robot arm moves to the equipment position where the grounding wire needs to be hung, so that the end of the grounding wire can be accurately aligned with the hanging point; Hanging steps: Let the end effector hang the ground wire to the specified position of the equipment to ensure a firm connection.

[0011] Preferably, the right side operation includes the steps of: Right side signal input steps: the operator sends the right side operation command signal through the brain-computer interface BCI system; Grasping step: the robot control system performs the removal operation according to the received signal command, and instructs the end effector to grasp one end of the already connected grounding wire; Removal steps: Use the end effector to remove the ground wire from the equipment and move it to a safe location to ensure that the ground wire is in a safe state after the operation is completed.

[0012] According to the present invention, a brain-computer interface and human-computer collaborative operating system of an equipotential robot includes: Optimization module: optimizes and trains the brain-computer interface (BCI) system; Startup module: Start the brain-computer interface BCI system and the robotic arm control system; Left-side operation module: When the robot arm control system receives the left-side operation command signal from the brain-computer interface BCI system, it instructs the robot arm to perform the hook operation; Right-side operation module: When the robot arm control system receives the right-side operation command signal from the brain-computer interface BCI system, it instructs the robot arm to perform the dismantling operation; Reset module: After recording and saving the data of the left operation module or the right operation module, the robot arm is reset to the initial position.

[0013] Preferably, the optimization module includes: Setting the electrode module: according to the needs of left and right hand motor imagery MI collection, setting the distribution of electrodes for collecting EEG signals; specifically, placing electrodes at the 8 positions most relevant to controlling left and right hand motor imagery activities, and installing the electrodes in the helmet; Extraction module: The collected EEG signals are spatially filtered in the trained CSP spatial filter to extract the signals corresponding to the MI features of left and right hand movement imagination; Classification processing module: let the corresponding signal pass through the classifier to classify, and the obtained matrix data is processed in sections, and the value corresponding to the middle time of each section of data is recorded, that is, the middle value is used as the standard for output judgment, and the difference of the data at the standard position is calculated; Control module: Use the difference as the control signal of the external device, establish a classification program, and correspond the operation signals of the left operation instruction and the right operation instruction.

[0014] Preferably, the startup module includes: System startup module: turns on the brain-computer interface (BCI) system and the robotic arm control system, and performs equipment self-check and system initialization; Signal calibration module: collects signals through a helmet with electrodes, calibrates the motor imagery MI, and enables accurate classification of left and right EEG signals; Robotic arm positioning module: moves the robotic arm to a predetermined initial position.

[0015] Preferably, the left operation module includes: Left signal input module: The operator sends left operation command signals through the brain-computer interface BCI system; Ground wire grabbing module: The robot arm control system performs the hooking operation according to the received operation signal command, and uses the end effector to grab one end of the ground wire; Mobile module: The robot arm moves to the equipment location where the grounding wire needs to be connected, so that the end of the grounding wire can be accurately aligned with the connection point; Hanging module: enables the end effector to hang the grounding wire to the specified position of the equipment to ensure a firm connection.

[0016] Preferably, the right side operation includes modules: Right signal input module: The operator sends the right operation command signal through the brain-computer interface BCI system; Grasping module: The robot control system performs the removal operation according to the received signal command, and instructs the end effector to grab one end of the already connected grounding wire; Removal module: Instructs the end effector to remove the grounding wire from the equipment and move it to a safe location to ensure that the grounding wire is in a safe state after the operation is completed.

[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. The application scenario of the present invention in a 220kV high voltage dangerous environment fully considers various dangerous operation factors such as the risk of electric shock, arc explosion, falling risk during high-altitude operations, and severe weather conditions in the substation. Through intelligent operation, the robot can accurately complete high-risk operations while ensuring the safety of personnel, reducing the risk of accidents caused by operational errors, and effectively improving work efficiency and safety; 2. The hardware design of the EEG cap and the hardware design of the helmet with built-in EEG acquisition electrodes of the present invention ensure the accuracy of EEG signal acquisition and analysis and the safety during use; 3. The present invention is aimed at the analysis of motor imagery data, and the electrode layout is carefully selected to optimize the signal quality and improve the accuracy of data analysis; 4. The present invention analyzes and processes the matrix data after classification by the classifier, and uses the intermediate value to determine the output signal, ensuring that each segment of data is accurately determined at a key time point (intermediate value), and the output result can stably reflect the main trends within the time period, thereby improving the accuracy and reliability of external device control. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 A flow chart of the brain-computer interface and human-computer collaborative operation method of the equipotential robot of the present invention; Figure 2 This is a schematic diagram of the distribution of electrodes of the BCI EEG cap of the present invention; Figure 3 Schematic diagram of a helmet with built-in EEG acquisition electrodes. DETAILED DESCRIPTION

[0019] The present invention is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those of ordinary skill in the art, several changes and improvements can also be made without departing from the concept of the present invention. These all belong to the protection scope of the present invention.

[0020] Brain Computer Interface (BCI) achieves information exchange by establishing a connection between the brain and external devices. The common spatial pattern (CSP) algorithm and linear classification support vector machine (SVM) were used for feature extraction and classification, and the processing effect of motor imagery EEG signals was verified. The present invention proposes a brain-computer interface and human-machine collaborative operation method for a substation equipotential robot for high-risk operations. In the case of uninterrupted power supply to the substation system, the hanging work of the equipment grounding wire is restricted by many factors, resulting in high-risk operations, such as safety problems caused by human operating errors, and low efficiency of human operation. The proposed brain-computer interface collaborative operation method of the equipotential robot can effectively enhance the collaboration and operation capabilities between the equipotential robot and the operator, and has broad application prospects in power maintenance and live operations.

[0021] BCI Technology The brain-computer interface (BCI) system mainly includes signal acquisition, signal processing, interactive control and feedback. The main function of the signal acquisition system is to extract electroencephalogram (EEG) signals, which are usually composed of electrodes, signal amplifiers, analog-to-digital converters and signal transmission components. The signal processing system is responsible for analyzing, classifying and identifying EEG signals, and usually includes modules such as signal preprocessing, feature extraction and pattern recognition. The interactive control system converts the processed EEG signals into operating instructions to operate external devices. The feedback system feeds back the operating status of the external device to the user, allowing it to adjust its own status in real time, thereby changing the EEG signal.

[0022] Electrode distribution The present invention adopts the internationally used 10-20 electrode system when collecting EEG signals. Since OpenBCI supports 16-channel signal input, and the EEG signals related to left and right hand motor imagery (MI) are mainly concentrated near electrodes C3 and C4, 16 electrodes including FP1, FP2, F3, F4, F7, F8, T7, T8, C3, C4, P7, P8, P3, P4, O1, and O2 were selected in the experiment, and the earlobes on both sides were used as reference electrodes. The specific distribution of electrodes is as follows: Figure 2As shown, the eight electrode channels F3, F4, T7, C3, CZ, C4, T8 and PZ are continuously selected as the main data analysis channels according to the analysis process.

[0023] Among them, the electrode selection and distribution positions are as follows: C3 (left central area): a key electrode located in the left central area, directly covering the left motor cortex, and highly related to the activities of controlling right-hand movements and their imagination. C4 (right central area): a key electrode located in the right central area, directly covering the right motor cortex, and highly related to the activities of controlling left-hand movements and their imagination. F3 (left frontal area): located in the left frontal area, close to the prefrontal cortex. The prefrontal lobe is related to motor planning, decision-making, and motor imagination, and helps capture activities related to right-hand motor imagination. F4 (right frontal area): located in the right frontal area, corresponding to F3, mainly captures EEG signals related to left-hand motor imagination. Through F3 and F4, bilateral activities related to motor planning and control can be monitored. T7 (left temporal area): located in the left temporal area, close to motor-related subcortical structures. T7 can provide information related to language, hearing, and complex motor integration, supplement the signal capture of the C3 area, and enhance the perception of right-hand motor imagination. T8 (right temporal area): located in the right temporal area, corresponding to T7, can capture EEG signals related to complex motor integration and hearing, supplement the signal capture of the C4 area, and enhance the perception of left-hand motor imagery. Cz (central midline area): midline electrode, located in the center of the midline of the head. Cz provides a symmetrical reference for overall EEG activity, monitors EEG signals in the midline area, and compares signal changes between C3 and C4. Pz (midline of the parietal area): located in the midline of the parietal area, related to sensorimotor integration. Pz can capture EEG signals related to sensory feedback and spatial imagery, and provide overall brain activity information related to motor imagery.

[0024] Advantages of electrode position selection: 1) Accurate coverage of the motor cortex: C3 and C4 cover the left and right motor cortices, which are directly related to left and right hand movements and imagination, and are the most important electrode positions. 2) Comprehensive motor planning and control monitoring: F3 and F4 capture prefrontal activity related to motor planning and decision-making. Combined with the signals of T7 and T8, they can monitor the collaboration and integration of different brain regions during motor imagination. 3) Midline reference and symmetry: Cz and Pz serve as midline electrodes to provide an overall baseline for EEG activity and ensure the symmetry and reliability of the signal, which helps reduce the impact of artifacts. 4) Supplementation and integration: T7 and T8 capture signals related to motor integration and auditory feedback. These signals can provide more dimensional information for the EEG activity of motor imagination, which helps to improve the richness and accuracy of interpretation of EEG data.

[0025] When collecting EEG signals in complex and dangerous environments such as substations, in order to avoid personal accidents, use Figure 3The safety helmet with built-in EEG acquisition electrodes shown in the figure can effectively protect the safety of the operator while ensuring the accurate acquisition of EEG signals.

[0026] Working principle of filter in BCI system The Common Spatial Pattern (CSP) algorithm can diagonalize the covariance matrix of each set of training data at the same time, so as to successfully construct the corresponding spatial filter. The test data that has passed the spatial filter can well achieve the maximum covariance in energy, that is, the variance with one class can be maximized, while the variance with the other class can be minimized, so that the obtained eigenvector can enhance the difference between the two classes of data. Specifically, 1. Read the saved training data. Each time the CSP filter is run, the reading module needs to be changed to read the file saved in the previous step.

[0027] 2. Preprocess the original data through Butterworth bandpass filter, including removing high-frequency noise and reducing signal-to-noise ratio. This study adopts 8th-order Butterworth bandpass filter with a selected frequency of 8 to 30 Hz.

[0028] 3. Use the Identity algorithm to copy the filtered signal and output it to the next two modules.

[0029] 4. Divide the time into segments for the two separated data, with 4s as the segment time.

[0030] 5. The two separated data are output to the CSP spatial filter trainer respectively, and the coefficient matrix of the CSP filter is calculated by this trainer and written into the configuration file.

[0031] Working principle of classifier in BCI system After completing the preprocessing and segmentation of the EEG signal, the present invention uses a support vector machine (SVM) for classification. SVM is a mathematical model based on the principle of structural risk minimization, which is particularly suitable for solving binary classification problems when the number of samples is limited. Compared with traditional machine learning methods, SVM has the advantages of simple structure, good adaptability, global optimization, fast training speed and strong generalization ability. Specifically, 1. Read sample data.

[0032] 2. Use Butterworth bandpass filtering to preprocess the raw EEG signal.

[0033] 3. Use the trained CSP spatial filter to perform spatial filtering on the signal and extract the signals corresponding to the MI features of the left and right hands.

[0034] 4. Segment the EEG signal. Start collecting EEG signals 0.5 seconds after the stimulus signal appears, and segment them at intervals of 4 seconds. Then, further divide each segment into small blocks with an interval of 0.0625 seconds and a duration of 1 second. These small blocks can analyze the time-varying characteristics of the EEG signal in more detail.

[0035] 5. Perform a square operation on each data block to obtain the corresponding energy signal. Perform moving average processing on the energy signal, including logarithmic operation and normalization. This step helps smooth the signal and standardize the features, making it more suitable for subsequent feature extraction and classification.

[0036] 6. Integrate the signal blocks into feature vectors of left and right hand MI. These feature vectors represent the statistical characteristics of the EEG signal in each period, which helps to distinguish different motor imagery tasks.

[0037] 7. Train the integrated feature vector. The classifier will learn how to distinguish the ground wire loading and unloading operation instructions of the left and right manipulators based on the feature vector, and save the training results to the configuration file for subsequent use.

[0038] Control signal generation The matrix data classified by the classifier is imported into Matlab, and then the numerical matrix is ​​visualized using Matlab to generate the corresponding image and calculate the difference in the data. This difference can be used to determine the response of EEG signals to motor imagery over a period of time.

[0039] Since the data received after classification by the classifier is a two-column vector and is collected according to time, it can be used as a design basis when designing the analysis program. The data is divided into 40 segments according to time, and each segment corresponds to 20 groups of left and right stimulus arrows in the experiment. The middle value of each time segment is used as the standard time for output judgment, and the positive or negative difference between the data in the third column and the fourth column at this moment is used as the output basis to establish a classification program.

[0040] In the program, the size of the column vector in the table is first calculated, and the column vector is divided into 40 groups, corresponding to the number of arrows shown in the experiment. Then, a loop function is used to output the positive and negative values ​​as 1 and -1 according to the difference between each group of data. These signals are used as control signals for the external device, corresponding to the operation signals for attaching the left robotic arm and removing the right robotic arm.

[0041] The benefit of this design is that it ensures that each piece of data is accurately judged at the key time point (intermediate value), and the output result can stably reflect the main trend within the time period, thereby improving the accuracy and reliability of external device control.

[0042] The operation signals are divided into the grounding wire hooking operation of the left robot arm and the grounding wire removal operation of the right robot arm. The grounding wire hooking operation is that the end-actuator claw of the robot arm grabs one end of the grounding wire and hooks it to the equipment that needs to be repaired. The grounding wire removal operation is that the end-actuator claw of the robot arm grabs one end of the grounding wire and removes it from the equipment that needs to be repaired. The process includes: The brain-computer interface (BCI) system is optimized first, including electrode layout optimization and value optimization.

[0043] 1. Initialization phase 1.1 System startup: Turn on the brain-computer interface (BCI) system and robotic arm control system, and perform equipment self-check and system initialization.

[0044] 1.2 Signal calibration: The operator performs signal calibration through motor imagery to ensure that the left and right EEG signals can be accurately classified.

[0045] 1.3 Robotic arm positioning: Move the robotic arm to the predetermined initial position, ready to perform the loading and unloading of the grounding wire operation.

[0046] 2. Ground wire hooking operation (left signal) 2.1 Signal input: The operator sends the hook operation signal by imagining the movement of the left arm.

[0047] 2.2 The end effector grabs the grounding wire: The robot arm uses the end effector (gripper) to grab one end of the grounding wire according to the operation signal instruction.

[0048] 2.3 Move to the target device: The robot arm moves to the device location where the grounding wire needs to be hung, ensuring that the end of the grounding wire can be accurately aligned with the hanging point.

[0049] 2.4Hanging operation: The end effector hooks the grounding wire to the designated position of the equipment to ensure a firm connection.

[0050] 3. Ground wire removal operation (right side signal) 3.1 Signal input: The operator sends the demolition operation signal by imagining the movement of the right arm.

[0051] 3.2 The end effector grabs the grounding wire: According to the signal command, the robot arm uses the end effector (gripper) to grab one end of the already connected grounding wire.

[0052] 3.3 Move to a safe location: The robotic arm removes the grounding wire from the equipment and moves it to a safe location.

[0053] 3.4 Removal operation: The end effector removes the grounding wire from the equipment to ensure that the grounding wire is in a safe state after the operation is completed.

[0054] 4. Operation completion stage 4.1 Data recording: The system automatically records the detailed data of this operation for subsequent analysis and optimization.

[0055] 4.2 System reset: Reset the robot arm to its initial position, ready for the next operation task or system shutdown.

[0056] The present invention also provides a brain-computer interface and human-computer collaborative operation system of an equipotential robot. The brain-computer interface and human-computer collaborative operation system of the equipotential robot can be realized by executing the process steps of the brain-computer interface and human-computer collaborative operation method of the equipotential robot, that is, technical personnel in this field can understand the brain-computer interface and human-computer collaborative operation method of the equipotential robot as a preferred implementation mode of the brain-computer interface and human-computer collaborative operation system of the equipotential robot.

[0057] A brain-computer interface and human-computer collaborative operation system of an equipotential robot, comprising: an optimization module: optimizing and training a brain-computer interface (BCI) system; a startup module: starting the brain-computer interface (BCI) system and a robotic arm control system; a left-side operation module: when the robotic arm control system receives a left-side operation instruction signal from the brain-computer interface (BCI) system, the robotic arm is ordered to perform a hooking operation; a right-side operation module: when the robotic arm control system receives a right-side operation instruction signal from the brain-computer interface (BCI) system, the robotic arm is ordered to perform a dismantling operation; and a reset module: after recording and saving the data of the left-side operation module or the right-side operation module, the robotic arm is reset to the initial position.

[0058] Specifically, the optimization module includes: an electrode setting module: according to the needs of left and right hand motor imagination MI collection, the distribution of electrodes is set to collect brain wave EEG signals; specifically, electrodes are placed at 8 positions most relevant to controlling left and right hand motor imagination activities, and the electrodes are installed in a safety helmet; an extraction module: the collected brain wave EEG signals are spatially filtered in a trained CSP spatial filter to extract signals corresponding to the left and right hand motor imagination MI features; a classification processing module: the corresponding signals are classified by a classifier, and the obtained matrix data is segmented, and the value corresponding to the middle time of each data segment is recorded, that is, the middle value is used as the standard for output judgment, and the difference of data at the standard position is calculated; a control module: the difference is used as the control signal of an external device, and a classification program is established to correspond to the operation signals of the left operation instruction and the right operation instruction.

[0059] Specifically, the startup module includes: system startup module: turn on the brain-computer interface BCI system and the robotic arm control system, perform equipment self-check and system initialization; signal calibration module: collect signals through a safety helmet with electrodes, and calibrate the motor imagery MI signal so that the left and right EEG signals can be accurately classified; robotic arm positioning module: move the robotic arm to the predetermined initial position.

[0060] Specifically, the left operation module includes: left signal input module: the operator sends the left operation command signal through the brain-computer interface BCI system; grounding wire grabbing module: the robotic arm control system performs the hanging operation according to the received operation signal command, and uses the end effector to grab one end of the grounding wire; moving module: the robotic arm moves to the equipment position where the grounding wire needs to be hung, so that the end of the grounding wire can be accurately aligned with the hanging point; hanging module: the end effector hangs the grounding wire to the specified position of the equipment to ensure a firm connection.

[0061] Specifically, the right-side operation includes modules: right-side signal input module: the operator sends the right-side operation command signal through the brain-computer interface BCI system; grasping module: the robotic arm control system performs the removal operation according to the received signal command, and instructs the end effector to grab one end of the already hung grounding wire; removal module: instructs the end effector to remove the grounding wire from the equipment and move it to a safe position to ensure that the grounding wire is in a safe state after the operation is completed.

[0062] Those skilled in the art know that, in addition to realizing the system and its various devices, modules, and units provided by the present invention in a purely computer-readable program code, it is entirely possible to realize the same functions in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for realizing various functions can also be regarded as structures within the hardware component; the devices, modules, and units for realizing various functions can also be regarded as both software modules for realizing the method and structures within the hardware component.

[0063] The above describes the specific embodiments of the present invention. It should be understood that the present invention is not limited to the above specific embodiments, and those skilled in the art can make various changes or modifications within the scope of the claims, which does not affect the essence of the present invention. In the absence of conflict, the embodiments of the present application and the features in the embodiments can be combined with each other arbitrarily.

Claims

1. A brain-computer interface and human-computer collaborative operation method of an equipotential robot, characterized in that: include: Optimization steps: optimize and train the brain-computer interface (BCI) system; Startup steps: Start the brain-computer interface BCI system and the robotic arm control system; Left side operation steps: When the robot arm control system receives the left side operation command signal sent by the brain-computer interface BCI system, it instructs the robot arm to perform the hook operation; Right side operation steps: When the robot arm control system receives the right side operation command signal sent by the brain-computer interface BCI system, the robot arm is ordered to perform the dismantling operation; Reset step: After recording and saving the data of the left operation step or the right operation step, reset the robot arm to the initial position.

2. The brain-computer interface and human-computer collaborative operation method of the equipotential robot according to claim 1, characterized in that: The optimization step comprises: Steps for setting electrodes: according to the needs of left and right hand motor imagery MI collection, set the distribution of electrodes for collecting EEG signals; specifically, place electrodes at the 8 positions most relevant to controlling left and right hand motor imagery activities, and install the electrodes in the helmet; Extraction step: spatially filter the collected EEG signals in the trained CSP spatial filter to extract the signals corresponding to the MI features of left and right hand movement imagination; Classification processing steps: let the corresponding signal pass through the classifier to classify, and the obtained matrix data is processed in segments, and the value corresponding to the middle time of each segment of data is recorded, that is, the middle value is used as the standard for output judgment, and the difference of the data at the standard position is calculated; Control steps: Use the difference as the control signal of the external device, establish a classification program, and correspond the operation signals of the left operation instruction and the right operation instruction.

3. The brain-computer interface and human-computer collaborative operation method of the equipotential robot according to claim 1, characterized in that: The startup steps include: System startup steps: Turn on the brain-computer interface BCI system and the robotic arm control system, perform equipment self-check and system initialization; Signal calibration steps: collect signals through a helmet with electrodes, calibrate the motor imagery MI signal, and make the left and right EEG signals accurately classified; Robot arm positioning step: move the robot arm to a predetermined initial position.

4. The brain-computer interface and human-computer collaborative operation method of the equipotential robot according to claim 1, characterized in that: The left side operation steps include: Left signal input steps: The operator sends the left operation command signal through the brain-computer interface BCI system; Ground wire grabbing step: the robot arm control system performs a hooking operation according to the received operation signal instruction, and uses the end effector to grab one end of the ground wire; Moving steps: The robot arm moves to the equipment position where the grounding wire needs to be hung, so that the end of the grounding wire can be accurately aligned with the hanging point; Hanging steps: Let the end effector hang the ground wire to the specified position of the equipment to ensure a firm connection.

5. The brain-computer interface and human-computer collaborative operation method of the equipotential robot according to claim 1, characterized in that: The right side operation includes the steps of: Right side signal input steps: the operator sends the right side operation command signal through the brain-computer interface BCI system; Grasping step: the robot control system performs the removal operation according to the received signal command, and instructs the end effector to grasp one end of the already connected grounding wire; Removal steps: Use the end effector to remove the ground wire from the equipment and move it to a safe location to ensure that the ground wire is in a safe state after the operation is completed.

6. A brain-computer interface and human-computer collaborative operating system for an equipotential robot, characterized in that: include: Optimization module: optimizes and trains the brain-computer interface (BCI) system; Startup module: Start the brain-computer interface BCI system and the robotic arm control system; Left-side operation module: When the robot arm control system receives the left-side operation command signal from the brain-computer interface BCI system, it instructs the robot arm to perform the hook operation; Right-side operation module: When the robot arm control system receives the right-side operation command signal from the brain-computer interface BCI system, it instructs the robot arm to perform the dismantling operation; Reset module: After recording and saving the data of the left operation module or the right operation module, the robot arm is reset to the initial position.

7. The brain-computer interface and human-computer collaborative operation system of the equipotential robot according to claim 6, characterized in that: The optimization module includes: Setting the electrode module: according to the needs of left and right hand motor imagery MI collection, setting the distribution of electrodes for collecting EEG signals; specifically, placing electrodes at the 8 positions most relevant to controlling left and right hand motor imagery activities, and installing the electrodes in the helmet; Extraction module: The collected EEG signals are spatially filtered in the trained CSP spatial filter to extract the signals corresponding to the MI features of left and right hand movement imagination; Classification processing module: let the corresponding signal pass through the classifier to classify, and the obtained matrix data is processed in sections, and the value corresponding to the middle time of each section of data is recorded, that is, the middle value is used as the standard for output judgment, and the difference of the data at the standard position is calculated; Control module: Use the difference as the control signal of the external device, establish a classification program, and correspond the operation signals of the left operation instruction and the right operation instruction.

8. The brain-computer interface and human-computer collaborative operation system of the equipotential robot according to claim 6, characterized in that: The startup module includes: System startup module: turns on the brain-computer interface (BCI) system and the robotic arm control system, and performs equipment self-check and system initialization; Signal calibration module: collects signals through a helmet with electrodes, calibrates the motor imagery MI, and enables accurate classification of left and right EEG signals; Robotic arm positioning module: moves the robotic arm to a predetermined initial position.

9. The brain-computer interface and human-computer collaborative operation system of the equipotential robot according to claim 6, characterized in that: The left side operation module comprises: Left signal input module: The operator sends left operation command signals through the brain-computer interface BCI system; Ground wire grabbing module: The robot arm control system performs the hooking operation according to the received operation signal command, and uses the end effector to grab one end of the ground wire; Mobile module: The robot arm moves to the equipment location where the grounding wire needs to be connected, so that the end of the grounding wire can be accurately aligned with the connection point; Hanging module: enables the end effector to hang the grounding wire to the specified position of the equipment to ensure a firm connection.

10. The brain-computer interface and human-computer collaborative operation system of the equipotential robot according to claim 6, characterized in that: The right side operation includes modules: Right signal input module: The operator sends the right operation command signal through the brain-computer interface BCI system; Grasping module: The robot control system performs the removal operation according to the received signal command, and instructs the end effector to grab one end of the already connected grounding wire; Removal module: Instructs the end effector to remove the grounding wire from the equipment and move it to a safe location to ensure that the grounding wire is in a safe state after the operation is completed.

Images