Humanoid robot data processing method and system based on parallel computing

Abstract

The invention discloses a parallel computing-based humanoid robot data processing method and system. The parallel computing-based humanoid robot data processing method comprises the step of mounting sensors at key movement parts of a humanoid robot. According to the method, sensors are installed at key parts of the humanoid robot, various operation data including motion data, stress data and control data can be monitored and collected in real time, data preprocessing is carried out, the accuracy and integrity of the data are ensured, and the accuracy and integrity of the data are ensured based on calculus principle, Lagrange principle and PID control algorithm calculation. The motion position vector, the generalized force and the control quantity of the humanoid robot can be accurately obtained, the data form an operation data set, a neural network model is adopted for training, optimal operation state information can be generated, the current operation data set is compared with the optimal operation state information, correction information can be generated, and the correction accuracy is improved. This allows the robot to perform adaptive adjustments according to real-time data and historical optimal states, thereby optimizing its performance.

Description

Technical Field

[0001] The present invention relates to the technical field of humanoid robot data processing, and specifically relates to a method and system for humanoid robot data processing based on parallel computing. Background Art

[0002] With the continuous development of robot-related technologies, users have higher and higher requirements for the functionality and adaptability of robots. Most traditional industrial robots have a single application scenario and cannot be generalized to daily production and life. Therefore, humanoid robot technology has emerged.

[0003] In the prior art, when adjusting the operating state of a humanoid robot, it is usually judged based on the experience of the staff. This method is relatively troublesome, and there are easily large errors in the analysis, resulting in inaccurate analysis, making it difficult for the humanoid robot to operate in the best state and difficult to meet the needs of the staff. Summary of the Invention

[0004] To solve the above technical problems, the present invention provides a method and system for humanoid robot data processing based on parallel computing. This technical solution solves the problem that in the prior art, when adjusting the operating state of a humanoid robot, it is usually judged based on the experience of the staff. This method is relatively troublesome, and there are easily large errors in the analysis, resulting in inaccurate analysis, making it difficult for the humanoid robot to operate in the best state.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] In the first aspect of the present invention, a method for humanoid robot data processing based on parallel computing is provided, including:

[0007] Install sensors at the key motion parts of the humanoid robot to monitor the operating data of the humanoid robot. The operating data includes motion data, force data, and control data. The motion data includes displacement data, velocity data, etc., and the force data includes kinetic energy data, potential energy data, etc.;

[0008] Perform data preprocessing on the collected motion data, force data, and control data of the humanoid robot. The preprocessing includes removing and filling data outliers to obtain complete motion data, force data, and control data with research significance;

[0009] Calculate the motion position vector of the humanoid robot based on the calculus principle, calculate the generalized force corresponding to the non-conservative external force of the humanoid robot based on the Lagrange principle, and calculate the control quantity based on the PID control algorithm. Form an operating data set with the obtained motion position vector, generalized force, and control quantity;

[0010] Retrieve the operation data information of the humanoid robot from the historical database, and use a neural network model to train and generate the optimal operation state information based on the historical operation data information;

[0011] Compare the formed operation data set with the optimal operation state information, generate correction information according to the comparison result, and adjust the operation data information according to the correction information.

[0012] Preferably, the removal of data outliers specifically includes the following steps:

[0013] Arrange the operation data of all humanoid robots in the form of coordinates (x, y);

[0014] Calculate the deviation value between two adjacent coordinate data (a, b) and (c, d), denoted as k;

[0015] When the deviation value k is greater than 100%, the data (x, y) is an outlier;

[0016] Replace the data (x, y) with the mean value of adjacent data;

[0017] The calculation formula for the deviation value is:

[0018]

[0019] Preferably, the data filling specifically includes the following steps:

[0020] Arrange the operation data of all humanoid robots in the form of coordinates (x, y);

[0021] Retrieve all data coordinates (x, y);

[0022] If x or y is missing, fill in the data at this position, and the data collection is the mean value of the same position of adjacent data.

[0023] Preferably, the formula for calculating the motion position vector of the humanoid robot based on the calculus principle is:

[0024]

[0025] In the formula, Ri→ represents the motion position vector, qα represents the generalized coordinate, and qα˙ represents the generalized velocity.

[0026] Preferably, the formula for calculating the generalized force corresponding to the non-conservative external force of the humanoid robot based on the Lagrange principle is:

[0027]

[0028] Wherein, Qi represents the generalized force corresponding to non-conservative external forces, T represents kinetic energy, V represents potential energy, and qα represents generalized coordinates.

[0029] Preferably, the formula for calculating the control quantity based on the PID control algorithm is:

[0030] U(t) = Kp[e(t) + 1 / Ti ∫₀ᵗ e(t)dt + Td de(t) / dt]

[0031] Wherein, U(t) represents the control quantity, e(t) represents the error quantity, and Kp, Ti, and Td are the proportional coefficient, integral time, and differential time respectively.

[0032] Preferably, the steps of comparing the formed operation data set with the optimal operation state information and generating correction information according to the comparison result are as follows:

[0033] Compare the formed operation data set with the optimal operation state information to obtain the state deviation rate;

[0034] Judge whether the state deviation rate is greater than or equal to the set state deviation rate threshold;

[0035] If it is greater than or equal to, generate correction information and adjust the operation parameter information according to the correction information;

[0036] If it is less than, the humanoid robot continues to operate according to the operation data set.

[0037] Preferably, the steps of generating correction information and adjusting the operation data information according to the correction information are as follows:

[0038] Obtain the operation state information and generate an operation state curve according to the operation time node and the operation state information;

[0039] Calculate the curve slope of adjacent operation time nodes and optimize the operation state curve according to the change state of the curve slope;

[0040] Generate correction information according to the change state of the curve slope and adjust the operation parameter information according to the correction information.

[0041] In the second aspect of the present invention, a humanoid robot data processing system based on parallel computing is further provided, including:

[0042] An acquisition module, which is used to install sensors at key parts of the movement of the humanoid robot to monitor the operation data of the humanoid robot. The operation data includes movement data, force data, and control data. The movement data includes displacement data, velocity data, etc., and the force data includes kinetic energy data, potential energy data, etc.;

[0043] A preprocessing module, which is used to preprocess the motion data, force data, and control data of the humanoid robot collected. The preprocessing includes removing and filling data outliers to obtain complete motion data, force data, and control data with research significance;

[0044] A calculation module, which is used to calculate the motion position vector of the humanoid robot based on the calculus principle, calculate the generalized force corresponding to the non-conservative external force of the humanoid robot based on the Lagrange principle, and calculate the control quantity based on the PID control algorithm, and form an operation data set with the obtained motion position vector, generalized force, and control quantity;

[0045] An optimal operating state determination module, which is used to retrieve the humanoid robot operation data information from the historical database and generate the optimal operating state information through training using a neural network model according to the historical operation data information;

[0046] A correction module, which is used to compare the formed operation data set with the optimal operating state information, generate correction information according to the comparison result, and adjust the operation data information according to the correction information.

[0047] In the third aspect of the present invention, an electronic device is also provided. The electronic device includes at least one processor; and a memory communicatively connected to the at least one processor; the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method of the first aspect of the present invention.

[0048] Compared with the prior art, the present invention provides a humanoid robot data processing method and system based on parallel computing, which has the following beneficial effects:

[0049] By installing sensors at key parts of the humanoid robot, the present invention can monitor and collect various operation data in real time, including motion data, force data, and control data. These data provide the basis for subsequent analysis and optimization. Data preprocessing steps, such as outlier removal and filling, ensure the accuracy and integrity of the data. This is crucial for subsequent data analysis and model training, avoiding misleading conclusions caused by data errors. Based on calculations using the principles of calculus, Lagrange, and the PID control algorithm, the motion position vector, generalized force, and control amount of the humanoid robot can be accurately obtained. These data form an operation data set, providing a basis for subsequent comparison and optimization. Training using a neural network model can generate the best operation state information. Such a model can capture complex relationships and patterns in the data, providing guidance for the optimized operation of the robot. Comparing the current operation data set with the best operation state information can generate correction information, which allows the robot to make adaptive adjustments based on real-time data and the historical best state, thereby optimizing its performance. This adaptive adjustment ability enables the humanoid robot to maintain the best operation state under different environmental and task conditions, improving its flexibility and adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 Schematic diagram of the humanoid robot data processing method in the present invention;

[0051] Figure 2 Schematic diagram of the method for removing outliers from data in the present invention;

[0052] Figure 3 Schematic diagram of the method for filling data in the present invention;

[0053] Figure 4 Schematic diagram of the method for comparing the formed operation data set with the best operation state information in the present invention and generating correction information according to the comparison result;

[0054] Figure 5 Schematic diagram of the method for generating correction information and adjusting operation data information according to the correction information in the present invention;

[0055] Figure 6 Schematic diagram of the humanoid robot data processing system in the present invention;

[0056] Figure 7 Block diagram of an exemplary electronic device capable of implementing the embodiments of the present invention is shown;

[0057] Among them, 700 is the electronic device, 701 is the computing unit, 702 is the ROM, 703 is the RAM, 704 is the bus, 705 is the I / O interface, 706 is the input unit, 707 is the output unit, 708 is the storage unit, and 709 is the communication unit. Detailed implementation manners

[0058] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and other obvious variations can be conceived by those skilled in the art.

[0059] Embodiment 1

[0060] Please refer to Figure 1 As shown, in the first aspect of the present invention, a method for processing humanoid robot data based on parallel computing is provided, including:

[0061] S101. Install sensors at the key motion parts of the humanoid robot to monitor the operation data of the humanoid robot. The operation data includes motion data, force data, and control data. The motion data includes displacement data, velocity data, etc., and the force data includes kinetic energy data, potential energy data, etc.;

[0062] S102. Perform data preprocessing on the collected motion data, force data, and control data of the humanoid robot. The preprocessing includes removing and filling data outliers to obtain complete motion data, force data, and control data with research significance;

[0063] S103. Calculate the motion position vector of the humanoid robot based on the calculus principle, calculate the generalized force corresponding to the non-conservative external force of the humanoid robot based on the Lagrange principle, and calculate the control quantity based on the PID control algorithm. Form an operation data set with the obtained motion position vector, generalized force, and control quantity;

[0064] S104. Retrieve the humanoid robot operation data information from the historical database, and use the neural network model to train and generate the optimal operation state information according to the historical operation data information;

[0065] S105. Compare the formed operation data set with the optimal operation state information, generate correction information according to the comparison result, and adjust the operation data information according to the correction information.

[0066] Those skilled in the art can understand that by installing sensors at key parts of the humanoid robot, the present invention can monitor and collect various operation data in real time, including motion data, force data, and control data. These data provide the basis for subsequent analysis and optimization. Data preprocessing steps, such as outlier removal and filling, ensure the accuracy and integrity of the data. This is crucial for subsequent data analysis and model training, avoiding misleading conclusions caused by data errors. Based on the calculations of calculus principles, Lagrange principles, and PID control algorithms, the motion position vector, generalized force, and control quantity of the humanoid robot can be accurately obtained. These data form an operation data set, providing a basis for subsequent comparison and optimization. Training with a neural network model can generate the optimal operation state information. Such a model can capture complex relationships and patterns in the data, providing guidance for the optimized operation of the robot. Comparing the current operation data set with the optimal operation state information can generate correction information, which allows the robot to make adaptive adjustments based on real-time data and historical best states, thereby optimizing its performance. This adaptive adjustment ability enables the humanoid robot to maintain the optimal operation state under different environmental and task conditions, improving its flexibility and adaptability.

[0067] Please refer to Figure 2 As shown, the specific steps for outlier removal of data are as follows:

[0068] S201. Arrange the operation data of all humanoid robots in the form of coordinates (x, y);

[0069] S202. Calculate the deviation value between two adjacent coordinate data (a, b) and (c, d), denoted as k;

[0070] S203. When the deviation value k is greater than 100%, the data (x, y) is an outlier;

[0071] S204. Replace the data (x, y) with the mean value of adjacent data;

[0072] The formula for calculating the deviation value is:

[0073]

[0074] Those skilled in the art can understand that this step can effectively identify and correct outliers in the data, thereby improving the overall quality of the data. This is crucial for subsequent data analysis, model training, and decision-making. High-quality data is the basis for training accurate and reliable models. After optimizing the data through the above steps, a better-performing model can be trained for predicting, classifying, or optimizing the behavior of the humanoid robot.

[0075] Please refer to Figure 3As shown, the data filling specifically includes the following steps:

[0076] S301. Arrange the operation data of all humanoid robots in the form of coordinates (x, y);

[0077] S302. Retrieve all data coordinates (x, y);

[0078] S303. If x or y is missing, fill in the data at this position, and the data collection is the average value of the same position of adjacent data.

[0079] Those skilled in the art can understand that

[0080] The formula for calculating the motion position vector of a humanoid robot based on the calculus principle is:

[0081]

[0082] In the formula, Ri→ represents the motion position vector, qα represents the generalized coordinate, and qα˙ represents the generalized velocity.

[0083] The formula for calculating the generalized force corresponding to the non-conservative external force of a humanoid robot based on the Lagrange principle is:

[0084]

[0085] In the formula, Qi represents the generalized force corresponding to the non-conservative external force, T represents the kinetic energy, V represents the potential energy, and qα represents the generalized coordinate.

[0086] The formula for calculating the control quantity based on the PID control algorithm is:

[0087] U(t) = Kp[e(t) + 1 / Ti∫t0e(t)dt + Tdde(t) / dt]

[0088] In the formula, U(t) represents the control quantity, e(t) represents the error quantity, and Kp, Ti, and Td are the proportional coefficient, integral time, and differential time respectively.

[0089] Please refer to Figure 4 As shown, compare the formed operation data set with the optimal operation state information. According to the comparison result, generating the correction information specifically includes the following steps:

[0090] S401. Compare the formed operation data set with the optimal operation state information to obtain the state deviation rate;

[0091] S402. Determine whether the state deviation rate is greater than or equal to the set state deviation rate threshold;

[0092] S403. If it is greater than or equal to, generate correction information and adjust the operation parameter information according to the correction information;

[0093] S404. If it is less than, the humanoid robot continues to operate according to this set of operation data.

[0094] Please refer to Figure 5 As shown, generating correction information and adjusting the operation data information specifically includes the following steps:

[0095] S501. Obtain the operation status information and generate an operation status curve according to the operation time node and the operation status information;

[0096] S502. Calculate the curve slope of adjacent operation time nodes and optimize the operation status curve according to the change status of the curve slope;

[0097] S503. Generate correction information according to the change status of the curve slope and adjust the operation parameter information according to the correction information.

[0098] In the second aspect of the present invention, a humanoid robot data processing system based on parallel computing is further provided. This system 600 includes:

[0099] An acquisition module 610, which is used to install sensors at the key motion parts of the humanoid robot to monitor the operation data of the humanoid robot. The operation data includes motion data, force data, and control data. The motion data includes displacement data, speed data, etc., and the force data includes kinetic energy data, potential energy data, etc.;

[0100] A preprocessing module 620, which is used to perform data preprocessing on the motion data, force data, and control data of the humanoid robot collected. The preprocessing includes removing and filling data outliers to obtain complete motion data, force data, and control data with research significance;

[0101] A calculation module 630, which is used to calculate the motion position vector of the humanoid robot based on the principle of calculus, calculate the generalized force corresponding to the non-conservative external force of the humanoid robot based on the Lagrange principle, and calculate the control quantity based on the PID control algorithm, and form a set of operation data with the obtained motion position vector, generalized force, and control quantity;

[0102] An optimal operation state determination module 640, which is used to retrieve the operation data information of the humanoid robot from the historical database and generate the optimal operation state information through training using a neural network model according to the historical operation data information;

[0103] A correction module 650 is configured to compare the formed set of operation data with the optimal operation state information, generate correction information according to the comparison result, and adjust the operation data information according to the correction information.

[0104] In a third aspect of the present invention, an electronic device is further provided.

[0105] Figure 7 A schematic block diagram of an electronic device 700 that can be used to implement the embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as, for example, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, for example, personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0106] The electronic device 700 includes a computing unit 701 that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0107] A plurality of components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0108] The computing unit 701 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 executes the various methods and processes described above, such as methods S100 to S600. For example, in some embodiments, methods S101 to S105 can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the methods S101 to S105 described above can be executed. Alternatively, in other embodiments, the computing unit 701 can be configured to execute methods S101 to S105 in any other suitable manner (e.g., by means of firmware).

[0109] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), system-on-a-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor, receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] The program code for implementing the methods of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program codes can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0111] In the context of the present invention, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0112] To provide for interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic, speech, or tactile input).

[0113] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0114] A computer system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0115] In summary, by installing sensors at key parts of the humanoid robot, the present invention can monitor and collect various operation data in real time, including motion data, force data, and control data. These data provide a basis for subsequent analysis and optimization. Data preprocessing steps, such as outlier removal and filling, ensure the accuracy and integrity of the data. This is crucial for subsequent data analysis and model training, avoiding misleading conclusions caused by data errors. Based on calculations using the principles of calculus, Lagrange principle, and PID control algorithm, the motion position vector, generalized force, and control quantity of the humanoid robot can be accurately obtained. These data form an operation data set, providing a basis for subsequent comparison and optimization. Training using a neural network model can generate the optimal operation state information. This model can capture complex relationships and patterns in the data, providing guidance for the optimized operation of the robot. Comparing the current operation data set with the optimal operation state information can generate correction information, which allows the robot to make adaptive adjustments based on real-time data and the historical best state, thereby optimizing its performance. This adaptive adjustment ability enables the humanoid robot to maintain the optimal operation state under different environmental and task conditions, improving its flexibility and adaptability.

[0116] The above shows and describes the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A humanoid robot data processing method based on parallel computing, characterized in that ,include: Installing sensors at key movement parts of the humanoid robot to monitor operation data of the humanoid robot, wherein the operation data includes movement data, force data and control data, wherein the movement data includes displacement data, speed data, etc., and the force data includes kinetic energy data, potential energy data, etc.; Performing data preprocessing on the collected motion data, force data and control data of the humanoid robot, wherein the preprocessing includes removing and filling data outliers to obtain complete motion data, force data and control data with research significance; The motion position vector of the humanoid robot is calculated based on the principle of calculus, the generalized force corresponding to the non-conservative external force of the humanoid robot is calculated based on the Lagrange principle, and the control quantity is calculated based on the PID control algorithm, and the obtained motion position vector, generalized force and control quantity are formed into an operation data set; Retrieving the humanoid robot operation data information from the historical database, and using the neural network model to train based on the historical operation data information to generate optimal operation status information; The formed operation data set is compared with the optimal operation status information, correction information is generated according to the comparison result, and the operation data information is adjusted according to the correction information.

2. A humanoid robot data processing method based on parallel computing according to claim 1, characterized in that: The data outlier removal specifically includes the following steps: Arrange the operating data of all humanoid robots in the form of coordinates (x, y); Calculate the deviation between two adjacent coordinate data (a, b) and (c, d), denoted as k; When the deviation value k is greater than 100%, the data (x, y) is an outlier; Replace the data (x, y) with the mean of the adjacent data; The calculation formula of the deviation value is:

3. The humanoid robot data processing method based on parallel computing according to claim 1, characterized in that: The data filling specifically includes the following steps: Arrange the operating data of all humanoid robots in the form of coordinates (x, y); Retrieve all data coordinates (x, y); If there is a gap in x or y, data is filled in at that position, and the data collected is the mean of the adjacent data at the same position.

4. The humanoid robot data processing method based on parallel computing according to claim 1, characterized in that: The formula for calculating the motion position vector of the humanoid robot based on the principle of calculus is: Where Ri→ represents the motion position vector, qα represents the generalized coordinates, and qα˙ represents the generalized velocity.

5. The humanoid robot data processing method based on parallel computing according to claim 1, characterized in that: The formula for calculating the generalized force corresponding to the non-conservative external force of the humanoid robot based on the Lagrangian principle is: Where Qi represents the generalized force corresponding to the non-conservative external force, T represents the kinetic energy, V represents the potential energy, and qα represents the generalized coordinates.

6. The humanoid robot data processing method based on parallel computing according to claim 1, characterized in that: The formula for calculating the control quantity based on the PID control algorithm is: U(t)=Kp[e(t)+1Ti∫t0e(t)dt+Tdde(t)dt] In the formula, U(t) represents the control amount, e(t) represents the error amount, Kp, Ti and Td are the proportional coefficient, integral time and differential time respectively.

7. The humanoid robot data processing method based on parallel computing according to claim 1, characterized in that: The step of comparing the formed operation data set with the optimal operation state information and generating correction information according to the comparison result specifically comprises the following steps: Compare the formed operation data set with the optimal operation state information to obtain the state deviation rate; Determining whether the state deviation rate is greater than or equal to a set state deviation rate threshold; If it is greater than or equal to, then generate correction information and adjust the operating parameter information according to the correction information; If it is less than, the humanoid robot continues to operate according to the operating data set.

8. The humanoid robot data processing method based on parallel computing according to claim 1, characterized in that: Generating correction information and adjusting the operation data information according to the correction information specifically includes the following steps: Obtaining running status information, and generating a running status curve according to the running time node and the running status information; Calculate the slope of the curves of adjacent running time nodes, and optimize the running state curve according to the changing state of the slope of the curve; Correction information is generated according to the change state of the slope of the curve, and the operating parameter information is adjusted according to the correction information.

9. A humanoid robot data processing system based on parallel computing, used to implement a humanoid robot data processing method based on parallel computing as claimed in any one of claims 1 to 8, characterized in that: include: A collection module, wherein the collection module is used to install sensors at key movement parts of the humanoid robot to monitor the operation data of the humanoid robot, wherein the operation data includes movement data, force data and control data, wherein the movement data includes displacement data, speed data, etc., and the force data includes kinetic energy data, potential energy data, etc.; A preprocessing module, which is used to perform data preprocessing on the collected motion data, force data and control data of the humanoid robot, wherein the preprocessing includes data outlier removal and filling to obtain complete motion data, force data and control data with research significance; A calculation module, wherein the calculation module is used to calculate the motion position vector of the humanoid robot based on the principle of calculus, calculate the generalized force corresponding to the non-conservative external force of the humanoid robot based on the Lagrange principle, and calculate the control amount based on the PID control algorithm, and form an operation data set with the obtained motion position vector, generalized force and control amount; An optimal operating state determination module, the optimal operating state determination module is used to retrieve the operating data information of the humanoid robot from the historical database, and generate the optimal operating state information by training the neural network model according to the historical operating data information; The correction module is used to compare the formed operation data set with the optimal operation state information, generate correction information according to the comparison result, and adjust the operation data information according to the correction information.

10. An electronic device comprising at least one processor; and a memory connected to the at least one processor in communication; characterized in that: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

Images