Mechanical arm path planning method based on emotion brain-computer interface

The robotic arm path planning method using an emotion brain-computer interface addresses high computational and training costs by decoding EEG and eye movement data to assign emotional rewards, enhancing path planning efficiency and alignment with human expectations.

CN119057783AActive Publication Date: 2024-12-03NAT UNIV OF DEFENSE TECH
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202411244443.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-06
Publication Date
2024-12-03
Estimated Expiration
2044-09-06

AI Technical Summary

Technical Problem

Existing robotic path planning methods require extensive modeling and interaction data, leading to high computational and training costs, and struggle with generalization in unmodeled scenarios.

Method used

A robotic arm path planning method using an emotion brain-computer interface that analyzes EEG signals and eye movement data to assign emotional attitudes as rewards in a three-dimensional space, planning paths with a greedy algorithm based on a total reward value graph.

Benefits of technology

Improves path planning efficiency and generalization by understanding user emotions and expectations without the need for modeling or extensive training data, resulting in paths that align better with human intentions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119057783A_ABST
    Figure CN119057783A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of man-machine interaction, in particular to a mechanical arm path planning method based on an emotion brain-computer interface, which comprises the following steps: S1, a user watches a video acquired by a camera, records a visual track of the user through an eye tracker, and synchronously acquires electroencephalogram data of the user; s2, analyzing the emotion of the user according to the electroencephalogram signals, and classifying the electroencephalogram signals into positive emotion, neutral emotion and negative emotion; s3, analyzing the eye movement data and positioning three-dimensional space coordinates watched by the user; s4, assigning the positive and negative emotions of the user to the three-dimensional space environment according to the three-dimensional space coordinates watched by the user to obtain a total reward value graph; and S5, planning the path according to a greedy algorithm and the total reward value graph until the path reaches the target position, and completing path planning. According to the method, the path planning efficiency of the mechanical arm is improved, and meanwhile, the planned path better meets the expectation of people.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of human-computer interaction, and in particular to a robot arm path planning method based on an emotion brain-computer interface. Background Art

[0002] Brain computer interface (BCI) provides technical support for robots to understand human intentions. Among them, affective brain-computer interface (aBCI) is an important branch of emotional intelligence, which aims to achieve more natural and friendly human-computer interaction by recognizing human emotions. The EEG features used to distinguish emotions are mainly power spectral density (PSD) and differential entropy (DE). The neural activity of the brain in different emotional states will show different power spectral densities in different frequency bands. The frequency bands commonly used for emotion recognition include delta (1-4 Hz), theta (4-8 Hz), alpha (8-13 Hz), beta (13-30 Hz) and gamma (30-50 Hz). In addition, differential entropy can reflect the dynamic changes of EEG signals and reflect the characteristics related to the positive and negative values ​​of emotions according to the asymmetry of the left and right cerebral hemispheres.

[0003] In the past research on path planning, it is often necessary to model the environment in advance. However, this method has poor generalization and cannot adapt well to unmodeled scenarios, and the time and computational costs of modeling are high. In addition, some studies have conducted reinforcement learning based on the interaction between the agent and the environment, setting the state space, action space and appropriate reward function for the agent, and learning a strategy with the highest reward value through continuous exploration. However, reinforcement learning usually requires a large amount of interaction data to train the model, which will result in high training costs in the real world. Summary of the invention

[0004] The present invention provides a robotic arm path planning method based on an emotion brain-computer interface to solve the technical problems mentioned in the background technology.

[0005] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0006] The present invention provides a robot arm path planning method based on an emotion brain-computer interface, comprising the following steps:

[0007] S1. The user watches the video captured by the camera in real time, and the user's visual trajectory is recorded by the eye tracker, and the user's EEG data is collected synchronously;

[0008] S2, analyzing the user's emotions according to the EEG signals, and classifying the EEG signals into positive emotions, neutral emotions, and negative emotions;

[0009] S3, analyzing the eye movement data and locating the three-dimensional spatial coordinates of the user's gaze;

[0010] S4, assigning the user's positive and negative emotions to the three-dimensional space environment according to the three-dimensional space coordinates of the user's gaze, and obtaining a total reward value map;

[0011] S5. Plan the path according to the greedy algorithm and the total reward value graph until the target location is reached, completing the path planning.

[0012] Furthermore, the S2 specifically includes the following steps:

[0013] S21, first preprocessing the original EEG signal, so as to remove the interference signal and non-EEG noise in the original EEG signal, and performing sliding window segmentation on the preprocessed EEG signal with a first set time as a step length and a second set time as a window length;

[0014] S22, extracting each segment of preprocessed EEG data into EEG signals of multiple different frequency bands through a bandpass filter;

[0015] S23. Calculate the average power spectral density of the EEG signals in each frequency band and the differential entropy of the EEG signals of each lead, and then input the average power spectral density of the EEG signals in each frequency band and the differential entropy of the EEG signals of each lead as features into a support vector machine to classify each segment of the EEG signals into positive emotions, neutral emotions and negative emotions.

[0016] Furthermore, the calculation formula of the average power spectrum density of the EEG signal of each frequency band and the differential entropy of each lead EEG signal in S23 is as follows:

[0017]

[0018] DE=log2(PSD)

[0019] Among them, PSD represents the average power spectral density of EEG signals in each frequency band, DE represents the average power spectral density of EEG signals in each frequency band and the differential entropy of the EEG signals of each lead, FFT(·) is fast Fourier transform, len(·) is the signal length, and EEG represents EEG signals.

[0020] Furthermore, the S3 specifically includes the following steps:

[0021] S31, analyzing the sampled eye movement data, determining that the user is in a fixation eye movement or a saccadic eye movement, and storing all sampling points of the fixation eye movement or the first sampling point of the saccadic eye movement into a fixation buffer;

[0022] S32, with the base of the robot as the origin, pointing to the operation space as the positive direction of the X axis, horizontally to the right as the positive direction of the Y axis, and vertically upward as the positive direction of the Z axis, construct a robot coordinate system;

[0023] S33, every first set time, extracting the eye movement data of a second set time synchronized with the EEG data;

[0024] S34, if the number of sampling points in the gaze buffer in the eye movement data taken out within the second set time is only 1, the user emotion corresponding to the EEG signal within the second set time is forcibly changed to a neutral emotion; if the number of sampling points in the gaze buffer in the eye movement data taken out within the second set time is greater than 1, the average values ​​of the horizontal coordinates and the vertical coordinates of all the data in the gaze buffer in the camera coordinate system are respectively solved, and the depth value corresponding to the average coordinate is obtained according to the depth image of the binocular camera;

[0025] S35, converting the average value of the horizontal coordinate and the vertical coordinate in the camera coordinate system and the depth value into the three-dimensional space coordinate in the robotic arm coordinate system through the calibration relationship between the camera coordinate system and the robotic arm coordinate system, thereby locating the three-dimensional space coordinate of the user's gaze within the second set time in the robotic arm coordinate system;

[0026] S36, looping S34 to S35 until all the eye movement data of the second set time taken out in S33 are processed according to the steps of S34 to S35.

[0027] Furthermore, the S31 specifically includes the following steps:

[0028] S311, first, every time a sampling point is obtained, the earliest sampling point is removed from the eye movement data buffer, and the latest sampling point is added to the eye movement data buffer;

[0029] S312. Calculate the distance between each sampling point and the previous sampling point in the eye movement data buffer point by point through a speed threshold filtering algorithm; if the distance between a certain sampling point and the previous sampling point meets the standard of fixation eye movement, it is considered that fixation eye movement has occurred, and the sampling point is added to a fixation buffer; if the distance between a certain sampling point and the previous sampling point is greater than a threshold, it is considered that saccadic eye movement has occurred, the fixation buffer is cleared, and the sampling point is used as the first point of the fixation buffer.

[0030] Furthermore, the first set time is 100-300 ms, and the second set time is 1000-4000 ms.

[0031] Furthermore, the S4 specifically includes the following steps:

[0032] S41, establishing a positive three-dimensional space matrix with all values ​​being 0 representing positive emotions, and a negative three-dimensional space matrix with all values ​​being 0 representing negative emotions; the positive three-dimensional space matrix and the negative three-dimensional space matrix constitute a three-dimensional space environment;

[0033] S42, if a certain EEG signal is determined to be a positive emotion, then according to the gaze three-dimensional coordinates analyzed from the eye movement data corresponding to the EEG signal, a value of 1 is assigned to the gaze coordinates of the positive three-dimensional space matrix; conversely, if a certain EEG signal is determined to be a negative emotion, then a value of -1 is assigned to the gaze coordinates of the negative three-dimensional space matrix;

[0034] S43, taking all non-zero coordinates as the sphere center, diffusing the positive and negative emotions to the entire three-dimensional space environment at the same diffusion attenuation speed, filling the positive three-dimensional space matrix and the negative three-dimensional space matrix, thereby forming a positive reward value map and a negative reward value map;

[0035] S44. Finally, the positive reward value graph and the negative reward value graph are added together to obtain a total reward value graph.

[0036] Furthermore, the S5 specifically includes the following steps:

[0037] S51, taking the coordinates of the manipulator center in the manipulator coordinate system as the starting point of path planning;

[0038] S52, traverse the surrounding N path points in sequence, and according to the greedy algorithm and the total reward value graph, take the coordinates of the surrounding N path points with the largest reward value as the next point in the path;

[0039] S53, loop S52 until reaching the target position, completing the path planning.

[0040] Beneficial effects of the present invention:

[0041] The present invention identifies the user's positive and negative attitudes by decoding EEG signals, and assigns the user's attitude as a reward to the three-dimensional environment space through an eye tracker. This can help the robot plan a path based on understanding the environment and user expectations, and the planned path is more in line with human expectations. At the same time, the present invention also improves the efficiency of the robot arm's path planning.

[0042] Compared with the traditional path specification through modeling, the present invention has higher generalization, does not require modeling, has no modeling time cost, and reduces the calculation cost;

[0043] In addition, compared with the traditional method of using a large model to perform path specification, the present invention does not require a large amount of interactive data to train the model, and there is no time cost for training the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a layout diagram of the robot arm coordinate system in the present invention;

[0045] Figure 2 is a positive reward value diagram in an embodiment of the present invention;

[0046] Figure 3 is a negative reward value diagram in an embodiment of the present invention;

[0047] Figure 4 is a total reward value diagram in an embodiment of the present invention;

[0048] Figure 5 Schematic diagram of the path planning obtained in the embodiment of the present invention. DETAILED DESCRIPTION

[0049] In order to facilitate the understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Preferred embodiments of the present invention are provided in the drawings. However, the present invention can be implemented in many other different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present invention more thorough and comprehensive.

[0050] Reference Figure 1 , the embodiment of the present application provides a robot arm path planning method based on emotion brain-computer interface, comprising the following steps:

[0051] S1. The user watches the video captured by the camera in real time, and the user's visual trajectory is recorded by the eye tracker, and the user's EEG data is collected synchronously;

[0052] S2, analyzing the user's emotions according to the EEG signals, and classifying the EEG signals into positive emotions, neutral emotions, and negative emotions;

[0053] S3, analyzing the eye movement data collected by the eye tracker and locating the three-dimensional spatial coordinates of the user's gaze;

[0054] S4, assigning the user's positive and negative emotions to the three-dimensional space environment according to the three-dimensional space coordinates of the user's gaze, and obtaining a total reward value map;

[0055] S5. Plan the path according to the greedy algorithm and the total reward value graph until the target location is reached, completing the path planning.

[0056] In some embodiments, S2 specifically includes the following steps:

[0057] S21, first preprocessing the original EEG signal, so as to remove the interference signal and non-EEG noise in the original EEG signal, and performing sliding window segmentation on the preprocessed EEG signal with a first set time as a step length and a second set time as a window length;

[0058] The first set time is 100-300ms, and the second set time is 1000-4000ms. Preferably, the first set time is 200ms, and the second set time is 3000ms.

[0059] Specifically, a 50 Hz notch filter is first used to remove the power frequency interference signal in the original EEG signal, and then a 0.1-50 Hz bandpass filter is used to remove the non-EEG noise in the original EEG signal to obtain the processed EEG signal, and the processed EEG signal is segmented by sliding window with a window length of 3000 ms and a step size of 200 ms.

[0060] S22, extracting each segment of preprocessed EEG data into EEG signals of multiple different frequency bands through a bandpass filter;

[0061] Specifically, feature extraction is performed on the preprocessed EEG signals, and each segment of preprocessed EEG data is extracted into signals of frequency bands delta (1-4 Hz), theta (4-8 Hz), alpha (8-13 Hz), beta (13-30 Hz), and gamma (30-50 Hz) through a bandpass filter.

[0062] S23. Calculate the average power spectral density of the EEG signals in each frequency band and the differential entropy of the EEG signals in each lead, and then input the average power spectral density of each frequency band and the differential entropy of the EEG signals in each lead as features into a support vector machine (SVM) to classify each segment of the EEG signals into positive emotions, neutral emotions, and negative emotions.

[0063] In some embodiments, the average power spectrum density of the EEG signals in each frequency band and the differential entropy of each lead EEG signal in S23 are calculated as follows:

[0064]

[0065] DE=log2(PSD)

[0066] Among them, PSD represents the average power spectral density of EEG signals in each frequency band, DE represents the average power spectral density of EEG signals in each frequency band and the differential entropy of the EEG signals of each lead, FFT(·) is fast Fourier transform, len(·) is the signal length, and EEG represents EEG signals.

[0067] In some embodiments, S3 specifically includes the following steps:

[0068] S31, analyzing the sampled eye movement data, determining that the user is in a fixation eye movement or a saccadic eye movement, and storing all sampling points of the fixation eye movement or the first sampling point of the saccadic eye movement into a fixation buffer;

[0069] S32, with the base of the robot as the origin, pointing to the operation space as the positive direction of the X axis, horizontally to the right as the positive direction of the Y axis, and vertically upward as the positive direction of the Z axis, construct a robot coordinate system;

[0070] S33, every 200ms, extract 3000ms of eye movement data synchronized with the EEG data;

[0071] S34. If the number of sampling points in the gaze buffer of the retrieved 3000ms eye movement data is only 1, the user emotion corresponding to the EEG signal synchronized with the 3000ms eye movement data is forcibly changed to a neutral emotion; if the number of sampling points in the gaze buffer of the retrieved 3000ms eye movement data is greater than 1, the average values ​​of the horizontal and vertical coordinates of all the data in the gaze buffer in the camera coordinate system are respectively solved, and the depth value corresponding to the average coordinate is obtained according to the depth image of the binocular camera;

[0072] S35, converting the average value of the horizontal coordinate and the vertical coordinate in the camera coordinate system and the depth value into the three-dimensional space coordinate in the robotic arm coordinate system through the calibration relationship between the camera coordinate system and the robotic arm coordinate system, thereby locating the three-dimensional space coordinate of the user's gaze within the 3000 ms in the robotic arm coordinate system;

[0073] S36, looping S34 to S35 until all the eye movement data of the second set time taken out in S33 are processed according to the steps of S34 to S35.

[0074] In some embodiments, the S31 specifically includes the following steps:

[0075] S311. First, each time a sampling point is obtained, the earliest sampling point is removed from the eye movement data buffer, and the latest sampling point is added to the eye movement data buffer; the sampling frequency of the eye tracker is 60 Hz;

[0076] S312. Calculate the distance between each sampling point and the previous sampling point in the eye movement data buffer point by point through a speed threshold filtering algorithm; if the distance between a certain sampling point and the previous sampling point meets the standard of fixation eye movement, it is considered that fixation eye movement has occurred, and the sampling point is added to a fixation buffer; if the distance between a certain sampling point and the previous sampling point is greater than a threshold, it is considered that saccadic eye movement has occurred, the fixation buffer is cleared, and the sampling point is used as the first point of the fixation buffer.

[0077] In some embodiments, the S4 specifically includes the following steps:

[0078] S41, establishing a positive three-dimensional space matrix with all values ​​being 0 representing positive emotions, and a negative three-dimensional space matrix with all values ​​being 0 representing negative emotions; the positive three-dimensional space matrix and the negative three-dimensional space matrix constitute a three-dimensional space environment;

[0079] S42, if a certain 3000ms EEG signal is judged as a positive emotion, then according to the gaze three-dimensional coordinates analyzed from the eye movement data corresponding to the EEG signal, a value of 1 is assigned to the gaze coordinates of the positive three-dimensional space matrix; conversely, if a certain 3000ms EEG signal is judged as a negative emotion, then a value of -1 is assigned to the gaze coordinates of the negative three-dimensional space matrix;

[0080] S43, taking all non-zero coordinates as the sphere center, diffuse the positive and negative emotions into the entire three-dimensional space environment at the same diffusion attenuation speed, fill the positive three-dimensional space matrix and the negative three-dimensional space matrix, thereby forming a positive reward value map and a negative reward value map; the schematic diagrams of the positive reward value map and the negative reward value map are shown in Figure 2 and Figure 3 ;

[0081] The diffusion decay rate has the following characteristics:

[0082] The planned path will avoid the points with a value of -1 in the negative reward value graph and reach the points with a value of 1 in the positive reward value graph. Adjusting the diffusion decay rate can adjust the planned path. The smaller the decay rate, the larger the arc of obstacle avoidance; the larger the decay rate, the smaller the arc of obstacle avoidance.

[0083] S44. Finally, the positive reward value graph and the negative reward value graph are added together to obtain a total reward value graph. Figure 4 shown.

[0084] In some embodiments, S5 specifically includes the following steps:

[0085] S51, taking the coordinates of the manipulator center in the manipulator coordinate system as the starting point of path planning;

[0086] S52, traversing the surrounding N path points in sequence, and according to the greedy algorithm and the total reward value graph, taking the coordinates of the surrounding N path points with the largest reward value as the next point in the path; preferably, the value of N is 26;

[0087] Specifically, with the current coordinate as the center, in a 3*3*3 cube, traverse the surrounding 26 path points in turn, and according to the greedy algorithm and the total reward value graph, take the coordinate with the largest reward value among the surrounding 26 path points as the next point in the path;

[0088] S53, loop S52 until the target position is reached, and the path planning is completed. An example of the completed path planning diagram is shown in Figure 5 shown.

[0089] The present invention identifies the user's positive and negative attitudes by decoding EEG signals, and assigns the user's attitude as a reward to the three-dimensional environment space through an eye tracker. This can help the robot plan a path based on understanding the environment and user expectations, and the planned path is more in line with human expectations. At the same time, the present invention also improves the efficiency of the robot arm's path planning.

[0090] Compared with the traditional path specification through modeling, the present invention has higher generalization, does not require modeling, has no modeling time cost, and reduces the calculation cost;

[0091] In addition, compared with the traditional method of using a large model to perform path specification, the present invention does not require a large amount of interactive data to train the model, and there is no time cost for training the model.

[0092] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered within the protection scope of the present invention. In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A robot arm path planning method based on emotion brain-computer interface, characterized in that: The steps include: S1. The user watches the real-time video, and the eye tracker records the user's visual trajectory and simultaneously collects the user's EEG data; S2. Analyze the user's emotions based on EEG signals and classify the EEG signals into positive emotions, neutral emotions, and negative emotions; S3, analyzing the eye movement data and locating the three-dimensional spatial coordinates of the user's gaze; S4, assigning the user's positive and negative emotions to the three-dimensional space environment according to the three-dimensional space coordinates of the user's gaze, and obtaining a total reward value map; S5. Plan the path according to the greedy algorithm and the total reward value graph until the target location is reached, completing the path planning.

2. The robot arm path planning method according to claim 1, characterized in that: The S2 specifically includes the following steps: S21, first preprocessing the original EEG signal to remove interference signals and non-EEG noise in the original EEG signal, and performing sliding window segmentation on the preprocessed EEG signal with a first set time as a step length and a second set time as a window length; S22, extracting each segment of preprocessed EEG data into EEG signals of multiple different frequency bands through a bandpass filter; S23. Calculate the average power spectral density of the EEG signals in each frequency band and the differential entropy of the EEG signals of each lead, and then input the average power spectral density of the EEG signals in each frequency band and the differential entropy of the EEG signals of each lead as features into a support vector machine to classify each segment of the EEG signals into positive emotions, neutral emotions, and negative emotions.

3. The robot arm path planning method according to claim 2, characterized in that: The calculation formulas for the average power spectrum density of the EEG signals in each frequency band in S23 and the differential entropy of the EEG signals of each lead are as follows: DE=log2(PSD) Where PSD represents the average power spectral density of EEG signals in each frequency band, DE represents the average power spectral density of EEG signals in each frequency band and the differential entropy of the EEG signals of each lead, FFT(·) is the fast Fourier transform, len(·) is the signal length, and EEG represents the EEG signal.

4. The robot arm path planning method according to claim 2, characterized in that: The S3 specifically includes the following steps: S31, analyzing the sampled eye movement data to determine whether the user is in a fixation eye movement or a saccadic eye movement, and storing all sampling points of the fixation eye movement or the first sampling point of the saccadic eye movement into a fixation buffer; S32. Construct a coordinate system for the robot arm with the base of the robot arm as the origin, the direction pointing to the operating space as the positive direction of the X axis, the horizontal right direction as the positive direction of the Y axis, and the vertical upward direction as the positive direction of the Z axis; S33, every first set time, extracting eye movement data of a second set time synchronized with the EEG data; S34. If the number of sampling points in the gaze buffer of the eye movement data retrieved within the second set time is only one, forcibly changing the user emotion corresponding to the EEG signal within the second set time to a neutral emotion; if the number of sampling points in the gaze buffer of the eye movement data retrieved within the second set time is greater than one, respectively calculating the average value of the horizontal coordinate and the vertical coordinate of all data in the gaze buffer in the camera coordinate system, and obtaining the depth value corresponding to the average coordinate based on the depth image of the binocular camera; S35. Converting the average value of the horizontal coordinate and the vertical coordinate in the camera coordinate system and the depth value into three-dimensional spatial coordinates in the robotic arm coordinate system through a calibration relationship between the camera coordinate system and the robotic arm coordinate system, thereby locating the three-dimensional spatial coordinates of the user's gaze within the second set time in the robotic arm coordinate system; S36, looping S34 to S35 until all the eye movement data of the second set time taken out in S33 are processed according to steps S34 to S35.

5. The robot arm path planning method according to claim 4, characterized in that: The S31 specifically includes the following steps: S311. First, every time a sampling point is obtained, the earliest sampling point is removed from the eye movement data buffer, and the latest sampling point is added to the eye movement data buffer; S312, calculating the distance between each sampling point and the previous sampling point in the eye movement data buffer point by point using a speed threshold filtering algorithm; if the distance between a sampling point and the previous sampling point meets the criterion for fixation eye movement, it is considered that fixation eye movement has occurred, and the sampling point is added to a fixation buffer; If the distance between a sampling point and the previous sampling point is greater than a threshold, it is considered that a saccadic eye movement has occurred, the gaze buffer is cleared, and the sampling point is used as the first point in the gaze buffer.

6. The robot arm path planning method according to claim 4, characterized in that: The first set time is 100-300ms, and the second set time is 1000-4000ms.

7. The robot arm path planning method according to claim 4, characterized in that: The S4 specifically includes the following steps: S41. Establishing a positive three-dimensional space matrix with all values ​​being 0, representing positive emotions, and a negative three-dimensional space matrix with all values ​​being 0, representing negative emotions; The positive three-dimensional space matrix and the negative three-dimensional space matrix constitute the three-dimensional space environment; S42. If a certain EEG signal segment is determined to be a positive emotion, assigning a value of 1 to the gaze coordinate in the positive three-dimensional space matrix based on the three-dimensional gaze coordinates analyzed from the eye movement data corresponding to the EEG signal segment; On the contrary, if a certain EEG signal is identified as negative emotion, the gaze coordinate of the negative three-dimensional space matrix is ​​assigned a value of -1; S43, using all coordinates containing non-zero values ​​as sphere centers, diffusing positive and negative emotions into the entire three-dimensional space environment at the same diffusion attenuation rate, filling the positive three-dimensional space matrix and the negative three-dimensional space matrix, thereby forming a positive reward value map and a negative reward value map; S44. Finally, the positive reward value graph and the negative reward value graph are added together to obtain a total reward value graph.

8. The robot arm path planning method according to any one of claims 1 to 7, characterized in that: The S5 specifically includes the following steps: S51, taking the coordinates of the manipulator center in the manipulator coordinate system as the starting point for path planning; S52, traverse the surrounding N path points in sequence, and according to the greedy algorithm and the total reward value graph, take the coordinates of the N surrounding path points with the largest reward value as the next point in the path; S53, loop S52 until the target position is reached, completing the path planning.

Citation Information

Patent Citations

  • Emotion regulation training system and method based on neural feedback technology

    CN113180669A

  • Virtual reality interactive emotion detection and regulation system based on brain-computer interface

    CN114756121A

  • Robot control method and system and electroencephalogram signal acquisition equipment

    CN117681191A

  • Intelligent emotion recognition and regulation method and system

    WO2022121113A1