Mechanical arm neural signal capturing and processing system, method, equipment and medium

Abstract

The invention provides a mechanical arm neural signal capturing and processing system, method and equipment and a medium, and belongs to the technical field of mechanical arms. The system comprises a neural signal capturing module used for capturing a neural electric signal in real time; the signal preprocessing module is used for amplifying and filtering the signal to generate an analog signal, sampling data and converting the analog signal into a discrete digital signal; the identification analysis module is used for carrying out time domain and frequency domain analysis on the digital signals and extracting characteristic parameters; distributing a unique identification code for the characteristic parameter combination based on a preset coding rule; the signal transmission module is used for packaging the identification code and the check code, encrypting a digital signal and wirelessly transmitting the digital signal to the mechanical arm control module; and the mechanical arm control module is used for acquiring the transmission data, analyzing the human body intention represented by the digital signal according to the identification code, and adjusting the action parameters of the mechanical arm in real time by adopting an intelligent control algorithm in combination with the real-time electroneurographic signal.

Description

Technical Field

[0001] This invention belongs to the field of robotic arm technology, and more specifically relates to a robotic arm neural signal capture and processing system, method, device and medium. Background Technology

[0002] With the increasing demand for autonomy in daily life among people with disabilities, the technological development of robotic arms, as an important assistive rehabilitation device, has attracted much attention. In the daily activities of people with limb amputations, robotic arms need to accurately respond to human movement intentions to achieve complex actions such as grasping and manipulation. The core of this process lies in the effective capture and interpretation of human nerve and muscle signals. Currently, most mainstream robotic arm control systems rely on surface electromyography (EMG) signal detection technology at the residual limb, inferring movement commands by analyzing the weak electrical activity generated by muscle contraction. However, for people with amputated arms, the muscle tissue at the residual limb often exhibits varying degrees of atrophy or fibrosis, resulting in a significant reduction in EMG signal intensity. Furthermore, the signal is easily interfered with by factors such as limb posture and skin condition, leading to extremely poor signal stability and making it unreliable as a control source. At the neural signal level, the limitations of existing technologies are even more pronounced. The generation and transmission of human movement intentions essentially rely on the electrical signal conduction of nerve fibers. While residual nerve endings at the amputation site still emit weak movement-related signals, the amplitude of these signals is typically in the microvolt or even nanovolt range, far lower than electromyographic signals, and is mixed with a large amount of biological noise. Current signal capture devices generally suffer from insufficient sensitivity and weak anti-interference capabilities, failing to effectively distinguish neural signals from noise and struggling to achieve targeted acquisition of specific movement-related nerve fiber signals. Furthermore, the transmission of neural signals is transient and complex; existing detection methods lack the ability to accurately analyze the spatiotemporal distribution characteristics of signals, resulting in the loss of a large amount of valuable movement intention information, severely limiting the precision of robotic arm control. Technical deficiencies in signal transmission and processing further exacerbate the accuracy issues of robotic arms. Existing systems primarily employ traditional analog signal amplification or simple digital encoding for signal transmission, lacking standardized signal identification and analysis mechanisms. Since neural and electromyographic signals contain various characteristic parameters (such as frequency, amplitude, and pulse width), different parameters correspond to different motion intentions. Unidentified transmission methods lead to the loss or confusion of signal features during transmission. In the processing stage, existing algorithms mostly rely on single signal features for pattern recognition, failing to establish multi-feature fusion analytical models, making it difficult to handle the time-varying characteristics of signals and individual differences. When the signal exhibits slight fluctuations or interference, the system is highly susceptible to misinterpreting motion intentions, resulting in delays, deviations, or even malfunctions in the robotic arm's movements, failing to meet the needs of people with disabilities for safe and reliable assistive devices. In summary, the technical bottlenecks of existing robotic arm control systems in areas such as weak signal capture, multi-feature analysis, and precise response have become the core obstacles restricting their development towards higher reliability and adaptability. Summary of the Invention

[0003] To address the above problems, the present invention aims to provide a robotic arm neural signal capture and processing system, method, device, and medium. By capturing weak neural signals at the amputation site and utilizing identifier resolution technology, the neural signals are efficiently uploaded and accurately processed, thereby enabling the robotic arm to respond more accurately to human intentions and improving the convenience and comfort of using the robotic arm for people with disabilities.

[0004] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, embodiments of this application provide a robotic arm neural signal capture and processing system, comprising: A neural signal capture module is installed at the nerve stump at the amputation site to capture neural electrical signals in real time via neural electrodes. The signal preprocessing module is used to amplify and filter neural electrical signals, generate analog signals, sample the analog signals, and convert the analog signals into discrete digital signals. The identifier resolution module is used to perform time-domain and frequency-domain analysis on digital signals and extract feature parameters; based on preset encoding rules, it assigns a unique identifier code to the combination of feature parameters and uses the CRC algorithm to verify the digital signal; The signal transmission module is used to encapsulate the identification code and check code of the digital signal, encrypt the digital signal, generate transmission data, and send it to the robotic arm control module using wireless transmission technology. The robotic arm control module is used to acquire transmitted data, parse the human intention represented by the digital signal according to the identification code, and combine it with real-time neural electrical signals to adjust the robotic arm's motion parameters in real time using intelligent control algorithms.

[0005] In an optional implementation, the neural signal capture module includes neural electrodes and a calibration unit. The shape and size of the neural electrodes match the anatomical structure of the nerve stump, and the neural electrodes are arranged in a multi-point array. The calibration unit is used to compare the captured neural electrical signal with a standard electrical signal of known intensity using a reference signal comparison method. The sensitivity parameters of the electrodes are automatically adjusted through a feedback control circuit to ensure the accuracy of signal capture.

[0006] In an optional implementation, the signal preprocessing module is specifically used for: An operational amplifier is used to amplify the captured neural electrical signals, and the discharge factor is dynamically adjusted during amplification using an automatic gain control algorithm. A second-order active bandpass filter is used to filter the amplified neural electrical signal to generate an analog signal; Based on the Nyquist sampling theorem, the analog signal is sampled at a preset sampling frequency, and a 12-bit analog-to-digital converter is used to quantize the continuous analog signal and convert it into a discrete digital signal. The quantization step size Δ = V full / 2 n V full denoted as , where is the full-scale voltage of the analog-to-digital converter, and n is the number of bits in the analog-to-digital converter.

[0007] In an optional implementation, the identifier resolution module is specifically used for: Perform time-domain and frequency-domain analysis on digital signals, calculate the peak value, mean, variance, and impulse of the digital signals, obtain the frequency components and spectral energy of the digital signals through fast Fourier transform, and generate characteristic parameter combinations; Based on the preset encoding rules, a hash algorithm is used to convert the binary data of the feature parameter combination into a unique identification code, and generate an identified and encoded signal. The CRC algorithm is used to verify the signal after the identifier is encoded. Before the signal is transmitted, the check code is calculated and appended to the identifier code. At the signal receiving end, the check code of the received signal is recalculated and compared with the received check code. If the two match, the signal is determined to be complete and error-free. If they do not match, the retransmission mechanism is triggered.

[0008] In an optional implementation, calculating the checksum and appending it to the identifier code includes: Using the principle of polynomial division, with a pre-defined generator polynomial G(x) = X 16 +X 12 +X 15 +1 performs a division operation on the encoded signal, and the remainder is used as a check code and appended to the identifier code; where X is a formal variable used to represent different bits in the binary number.

[0009] In an optional implementation, the signal transmission module is specifically used for: Before signal transmission, the identification code and check code are encapsulated, transmission protocol header information is added, and the digital signal is encrypted using the AES encryption algorithm to generate transmission data; the transmission protocol header information includes source address, destination address, and data length; Using Wi-Fi 6, Bluetooth 5.0, or ZigBee transmission technologies, the transmitted data is uploaded to a cloud server or edge computing device and sent to the robotic arm control module.

[0010] In an optional implementation, the robotic arm control module is specifically used for: The system receives uploaded transmission data and, based on a pre-established database of mapping relationships between neural signals and robotic arm movements, matches and classifies the identifier codes using a pattern recognition algorithm to determine the type of movement the patient wants to perform; the movement types include grasping, extending, and rotating. Based on the type of action the patient wants to perform and combined with real-time changes in neural electrical signals, a fuzzy PID control algorithm is used to adjust the motion parameters of the robotic arm in real time; the motion parameters include joint angles, movement speed, and gripping force. The control rules of the fuzzy PID control algorithm include: K p = K p0 + ΔK p K i = K i0 + ΔK i K d = K d0 + ΔK d Among them, K p K i K d The proportional, integral, and derivative coefficients K of the PID controller are respectively. p0 K i0 K d0 These are the initial proportional coefficient, initial integral coefficient, and initial derivative coefficient of the PID controller; ΔK p ΔK i ΔK d This refers to the adjustment amount of the corresponding parameters obtained through fuzzy inference.

[0011] Secondly, embodiments of this application also provide a method for capturing and processing neural signals in a robotic arm, including: A neural signal capture module installed at the nerve stump of the severed arm uses neural electrodes to capture neural electrical signals in real time. The neural electrical signal is amplified and filtered by the signal preprocessing module to generate an analog signal. The analog signal is then sampled and converted into a discrete digital signal. The identifier resolution module performs time-domain and frequency-domain analysis on the digital signal to extract feature parameters; based on the preset encoding rules, a unique identifier code is assigned to the combination of feature parameters, and the CRC algorithm is used to verify the digital signal. The digital signal identification code and check code are encapsulated by the signal transmission module, the digital signal is encrypted, and after generating transmission data, it is sent to the robotic arm control module using wireless transmission technology. The robotic arm control module acquires transmitted data, parses the human intention represented by the digital signal according to the identification code, and combines it with real-time neural electrical signals to adjust the robotic arm's motion parameters in real time using intelligent control algorithms.

[0012] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the robotic arm neural signal capture and processing method described in any of the above descriptions.

[0013] Fourthly, embodiments of this application also provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the robotic arm neural signal capture and processing method described in any of the above claims.

[0014] As can be seen from the above technical solutions, the present invention has the following advantages: The robotic arm neural signal capture and processing system provided in this application accurately captures weak signals from the nerve stump at the amputation site through the high-sensitivity neural electrodes and calibration unit of the neural signal capture module. The signal is then amplified, filtered, and converted from analog to digital by the signal preprocessing module to obtain a clear digital signal. The identifier resolution module extracts feature parameters and encodes and verifies them to ensure signal accuracy. The signal transmission module encrypts and encapsulates the signal before wirelessly transmitting it to the robotic arm control module. Finally, based on the resolved human intention and real-time signal changes, an intelligent control algorithm precisely regulates the robotic arm's movements. The entire system forms a complete and efficient process from signal capture to robotic arm control, greatly improving the neural signal capture capability and processing accuracy. This enables the robotic arm to respond quickly and accurately to human intentions, significantly enhancing the convenience and comfort for people with disabilities using robotic arms, and demonstrating broad application prospects.

[0015] The neural signal capture module of this application adopts a high-sensitivity neural electrode with a multi-point array layout that matches the anatomical structure of the nerve stump, as well as a calibration unit with automatic calibration function. It can penetrate deep into the vicinity of nerve fibers and effectively capture weak and precise neural signals at the amputation site, providing high-quality raw signals for subsequent signal processing and robotic arm control. Compared with traditional technology, it greatly improves the ability to capture neural signals.

[0016] The signal preprocessing module of this application uses an operational amplifier with automatic gain control algorithm and a second-order active bandpass filter to accurately amplify and filter neural signals. Then, based on the Nyquist sampling theorem and a 12-bit analog-to-digital converter, data sampling and quantization are performed to convert analog signals into discrete digital signals, ensuring the efficiency and accuracy of signal processing and laying the foundation for timely and accurate interpretation of human intentions.

[0017] The identifier resolution module of this application extracts the characteristic parameters of digital signals through time domain and frequency domain analysis, and assigns a unique identifier code to it using hash algorithms, while using CRC check algorithms to ensure signal integrity; the signal transmission module is responsible for data encapsulation, encryption and high-speed wireless transmission technology to send signals, ensuring the reliability, security and stability of the signal during transmission, avoiding signal loss and interference, and ensuring that human intentions can be accurately transmitted to the robotic arm control module.

[0018] The robotic arm control module of this application is based on a database of mapping relationships between neural signals and robotic arm movements. It uses pattern recognition algorithms to accurately analyze human intentions and combines real-time changes in neural electrical signals. It also uses a fuzzy PID control algorithm to adjust the robotic arm's movement parameters in real time, thereby achieving precise and flexible control of the robotic arm for complex movements and greatly improving the robotic arm's operational performance and practicality.

[0019] This application establishes a complete and efficient processing flow from neural signal capture to robotic arm control. The modules work together to effectively improve the convenience and comfort of people with disabilities using the robotic arm, reduce learning and usage costs, enable them to operate the robotic arm more naturally and smoothly, and significantly improve the quality of life of patients with limb loss. Attached Figure Description

[0020] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the structure of the robotic arm neural signal capture and processing system provided in this application.

[0022] Figure 2 This is a flowchart illustrating the robotic arm neural signal capture and processing method provided in this application.

[0023] Figure 3 A schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0024] The various embodiments of this disclosure will be described more fully in the detailed description of the specific architecture and functions of the robotic arm neural signal capture and processing system below. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0025] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more combinations of the foregoing.

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] Please see Figure 1 The diagram shown is a structural schematic of a robotic arm neural signal capture and processing system in a specific embodiment. The system includes: a neural signal capture module, a signal preprocessing module, an identifier parsing module, a signal transmission module, and a robotic arm control module.

[0028] The neural signal capture module is placed at the nerve stump at the amputation site to capture neural electrical signals in real time via neural electrodes.

[0029] In a specific implementation, the neural signal capture module employs a highly sensitive neural electrode positioned near the nerve stump at the amputation site to capture weak neural electrical signals. This neural electrode is made of a special biocompatible material, which reduces stimulation of nerve tissue while improving the sensitivity and stability of signal capture.

[0030] For example, the neural signal capture module employs highly sensitive neural electrodes placed near the nerve stump at the amputation site. The electrodes are made of a special biocompatible material to reduce stimulation of the nerve tissue and improve the sensitivity and stability of signal capture. The shape and size of the electrodes are optimized according to the specific anatomical structure of the nerve stump, using a multi-point array layout to increase the effective contact area with the nerve tissue, thereby enhancing the signal capture effect. Simultaneously, the electrode surface features a microtextured structure, which helps promote a tight bond between the nerve tissue and the electrode, further improving the signal capture capability.

[0031] The neural signal capture module is specifically used for: When a patient attempts to move, the nerve stump emits a weak electrical signal. The neural electrodes capture these signals in real time and convert them into electrical signals for output. The module also features automatic calibration, periodically adjusting the electrode sensitivity. The calibration process uses a reference signal comparison method, comparing the captured signal with a standard electrical signal of known strength. A feedback control circuit automatically adjusts the electrode sensitivity parameters to ensure accurate signal capture. Furthermore, the electrodes have a temperature compensation function, employing temperature sensors such as thermistors to monitor the ambient temperature in real time and adjusting the electrode performance parameters accordingly to reduce the impact of temperature drift on signal capture.

[0032] The signal preprocessing module is used to amplify and filter neural electrical signals, generate analog signals, sample the analog signals, and convert the analog signals into discrete digital signals.

[0033] In a specific implementation, the signal preprocessing module is connected to the neural signal capture module to perform preprocessing operations such as amplification and filtering on the captured neural electrical signals. The amplification circuit uses a low-noise, high-gain operational amplifier, which can amplify weak neural electrical signals to a suitable amplitude; the filtering circuit uses a bandpass filter, which can effectively remove noise and interference from the signal and retain useful neural signal components.

[0034] For example, the signal preprocessing module is specifically used for: Connected to the neural signal capture module, a low-noise, high-gain operational amplifier amplifies the captured weak neural electrical signals. The amplification factor can be dynamically adjusted according to the actual signal strength to avoid signal distortion. The amplification circuit adopts a multi-stage amplification structure, with a high-input-impedance operational amplifier used for initial amplification in the first stage, and further amplification in the subsequent stages as needed. The dynamic adjustment of the amplification factor is achieved through an automatic gain control (AGC) algorithm, the formula of which is: Gain adjustment ΔG = K × (V) ref / V in ) Where K is the proportionality coefficient, used to adjust the rate of gain change; V ref The reference voltage is set and is usually determined according to system design requirements; V in The input signal voltage is the raw electrical signal voltage captured by the neural electrodes. By monitoring the input signal voltage in real time and calculating the gain adjustment, the gain of the amplifier circuit is automatically adjusted to stabilize the output signal amplitude within a suitable range.

[0035] A bandpass filter is used to filter the amplified signal, effectively removing high-frequency noise and low-frequency interference components while retaining useful frequency components of the neural signal. The bandpass range of the filter is precisely set according to the frequency characteristics of the neural signal; a second-order active bandpass filter is used, and its transfer function is: H(s) = (A × ω0 × s) / (s 2 +(ω0 / Q)×s+ω0²) Where A is the filter gain, which determines the amplitude amplification factor of the signal after filtering; ω0 is the center angular frequency of the filter, and its relationship with the center frequency f0 is ω0 = 2πf0; Q is the filter quality factor, reflecting the filter's selectivity. The larger the Q value, the narrower the filter's passband and the better its selectivity. By reasonably selecting the filter parameters, effective filtering of neural signals can be achieved, improving the signal-to-noise ratio.

[0036] The filtered analog signal is sampled to convert the continuous analog signal into a discrete digital signal. The sampling frequency is determined based on the highest frequency component of the neural signal, following the Nyquist sampling theorem, and the sampling frequency f is... s ≥2f max , where f max This represents the highest frequency of the neural signal. Simultaneously, the sampled signal undergoes quantization processing using a 12-bit or higher precision analog-to-digital converter (ADC) to convert the amplitude of the analog signal into a digital value. The quantization precision can be selected according to actual needs, with a quantization step size Δ = V. full / 2 n V full is the full-scale voltage of the ADC, i.e., the maximum input voltage that the ADC can handle; n is the number of bits in the ADC, which determines the resolution of the quantized digital signal. By improving the quantization accuracy, the amplitude information of the analog signal can be represented more accurately, and quantization error can be reduced.

[0037] The identifier resolution module is used to perform time-domain and frequency-domain analysis on digital signals and extract feature parameters; based on preset encoding rules, it assigns a unique identifier code to the combination of feature parameters and uses the CRC algorithm to verify the digital signal.

[0038] In a specific implementation, the identifier parsing module is connected to the signal preprocessing module to perform identifier encoding on the preprocessed neural signal. The identifier encoding process employs a feature extraction-based encoding algorithm. First, the neural signal undergoes time-domain and frequency-domain analysis to extract characteristic parameters such as peak value, frequency components, and pulse width. Then, according to pre-defined encoding rules, a unique identifier code is assigned to each combination of characteristic parameters to accurately identify and distinguish different neural signals during signal transmission and processing. Simultaneously, the identifier parsing module also uses a CRC (Cyclic Redundancy Check) algorithm to parse and verify the identifier-encoded signal. By calculating the checksum and comparing it with the received checksum, the accuracy and integrity of the signal during transmission and processing are ensured.

[0039] For example, the identifier resolution module is specifically used for: The preprocessed digital neural signals are analyzed in both the time and frequency domains to extract various characteristic parameters. In the time domain analysis, features such as peak value, mean, variance, and pulse width are calculated. In the frequency domain analysis, features such as frequency components and spectral energy are obtained using algorithms such as Fast Fourier Transform (FFT).

[0040] For example, the peak value of the signal can be expressed as:

[0041] in, Let t be the expression of the neural signal in the time domain, where t is the time variable.

[0042] The mean of the signal is:

[0043] Where N is the number of sampling points, Let be the signal amplitude at the i-th sampling point.

[0044] The variance is:

[0045] The pulse width can be determined based on the duration of the signal exceeding a certain threshold. In frequency domain analysis, the signal is transformed from the time domain to the frequency domain using FFT to obtain the signal's spectrum. Then, characteristic parameters such as spectral energy are calculated. For example, spectral energy can be expressed as:

[0046] in, Let f be the spectral amplitude of the signal at frequency f.

[0047] Based on pre-defined encoding rules, a unique identifier code is assigned to each combination of feature parameters. These encoding rules can be formulated based on statistical analysis of a large number of neural signal samples, ensuring that neural signal feature combinations corresponding to different human intentions have unique and accurate identifier codes. The identifier code employs an efficient data encoding format, such as binary or hexadecimal encoding, to reduce data transmission volume and storage space. The encoding process can use hash algorithms to convert the binary data of the feature parameter combination into a unique identifier code. For example, the SHA-256 algorithm converts the binary data of the feature parameter combination into a 256-bit hash value as the identifier code.

[0048] The CRC (Cyclic Redundancy Check) algorithm is used to verify the encoded signal. Before signal transmission, a checksum is calculated and appended to the identifier code. At the receiving end, the checksum is recalculated on the received signal and compared with the received checksum. If they match, the signal is considered intact; otherwise, a retransmission mechanism is triggered to ensure the accuracy of signal transmission. The CRC checksum algorithm uses the polynomial division principle, dividing the data using a pre-agreed generator polynomial G(x), and using the remainder as the checksum. For example, using the CRC-16 checksum algorithm, the generator polynomial is: G(x) = X 16 +X 12 +X 15 +1 When validating data, the data is treated as a binary polynomial M(x), and the expression is M(x) × X. 16 Divide by the generator polynomial G(x), and the remainder is the 16-bit check code.

[0049] The signal transmission module is used to encapsulate the identification code and check code of the digital signal, encrypt the digital signal, generate transmission data, and send it to the robotic arm control module using wireless transmission technology.

[0050] In a specific implementation, the signal transmission module employs high-speed, low-latency wireless transmission technology to upload the identified neural signals to a cloud server or edge computing. The wireless transmission technology utilizes advanced communication protocols, enabling stable signal transmission and preventing signal loss and interference. For example, the signal transmission module is specifically used for: High-speed, low-latency wireless transmission technologies, such as Wi-Fi 6, Bluetooth 5.0, or ZigBee, are used to upload the identified neural signals to cloud servers or edge computing devices. The wireless transmission module has an automatic channel-switching function, which can select the optimal channel for signal transmission in real time based on the surrounding wireless signal interference to avoid signal loss and interference. For example, Wi-Fi 6 technology employs Orthogonal Frequency Division Multiple Access (OFDMA) and Multiple User Multiple Input Multiple Output (MU-MIMO) technologies to improve channel utilization and data transmission efficiency while reducing transmission latency.

[0051] Before signal transmission, the identification code and checksum are encapsulated, and necessary transmission protocol header information, such as source address, destination address, and data length, is added to ensure the receiving end can correctly parse the signal. Simultaneously, encryption algorithms such as the Advanced Encryption Standard (AES) are used to encrypt the transmitted data, ensuring signal security during transmission and preventing theft or tampering. The AES encryption algorithm uses symmetric encryption, encrypting data with a 128-bit or 256-bit key. Its encryption process includes multiple rounds of substitution, permutation, and mixing operations to ensure high data security.

[0052] The robotic arm control module is used to acquire transmitted data, parse the human intention represented by the digital signal according to the identification code, and combine it with real-time neural electrical signals to adjust the robotic arm's motion parameters in real time using intelligent control algorithms.

[0053] In a specific implementation, the robotic arm control module is connected to the signal transmission module, receiving uploaded neural signals and interpreting the human intentions represented by the neural signals according to the identification codes, thereby controlling the robotic arm to perform corresponding actions. The robotic arm control module employs an intelligent control algorithm, which can adjust the robotic arm's motion parameters in real time based on changes in neural signals, achieving precise control of the robotic arm.

[0054] For example, the robotic arm control module is specifically used for: Connected to the signal transmission module, it receives uploaded neural signals and parses the human intentions represented by the neural signals based on the identifier codes. The parsing process is based on a pre-established database of mapping relationships between neural signals and robotic arm movements. Pattern recognition algorithms are used to match and classify the identifier codes to determine the type of action the patient wants to perform, such as grasping, extending, or rotating. Pattern recognition algorithms can employ methods such as Support Vector Machines (SVM) or Artificial Neural Networks (ANN). For example, using the SVM algorithm, a classification hyperplane is constructed through learning from training samples, mapping the identifier codes corresponding to different human intentions to different categories, thus achieving accurate parsing of the neural signal intentions.

[0055] Based on the analyzed human intent and real-time changes in neural signals, intelligent control algorithms (such as PID control, fuzzy control, and neural network control) are used to adjust the robotic arm's motion parameters in real time, including joint angles, movement speed, and gripping force, achieving precise control of the robotic arm. These intelligent control algorithms possess self-learning and adaptive capabilities, continuously optimizing control strategies based on patient usage habits and operational feedback, thereby improving the robotic arm's control accuracy and flexibility. For example, using a fuzzy PID control algorithm combines fuzzy control with PID control. Through fuzzy inference of errors and error change rates, the parameters of the PID controller are dynamically adjusted, improving the system's response speed and control accuracy. The control rules of the fuzzy PID control algorithm can be expressed as: K p = K p0 + ΔK p K i = K i0 + ΔK i K d = K d0 + ΔK d Among them, K p K i K d The proportional, integral, and derivative coefficients K of the PID controller are respectively. p0 K i0 K d0 These are the initial proportional coefficient, initial integral coefficient, and initial derivative coefficient of the PID controller; ΔK p ΔK i ΔK d This refers to the adjustment amount of the corresponding parameters obtained through fuzzy inference.

[0056] Adjustments are made based on a fuzzy set of error e and error change rate de (such as negative large, negative small, zero, positive small, positive large) to achieve precise control of the robotic arm's motion parameters.

[0057] In this embodiment, the collaborative work of multiple modules effectively overcomes many shortcomings of existing technologies, demonstrating significant advantages. The neural signal capture module employs a multi-point array of electrodes adapted to the anatomical structure of nerve stumps, combined with automatic calibration and temperature compensation functions, significantly improving the sensitivity, stability, and accuracy of weak neural signal capture, solving the problems of reliance on traditional electromyography signals and insufficient neural signal capture capabilities. The signal preprocessing module significantly improves signal quality through dynamic gain adjustment, precise filtering, and high-resolution analog-to-digital conversion, laying the foundation for subsequent processing. The identifier resolution module achieves accurate signal resolution and transmission integrity assurance through multi-feature parameter extraction, unique identifier encoding, and CRC verification, avoiding signal confusion and loss. The signal transmission module uses encryption and efficient wireless transmission technology to ensure the security and efficiency of signal transmission. The robotic arm control module, combined with intelligent control algorithms, achieves precise response to human intentions and real-time adjustment of movements. The overall system comprehensively improves the control precision, reliability, and safety of the robotic arm, better meeting the needs of people with disabilities for assistive devices and significantly improving their autonomy in daily life.

[0058] like Figure 2 As shown, the following are embodiments of the robotic arm neural signal capture and processing method provided in this disclosure. This method and the robotic arm neural signal capture and processing system of the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the robotic arm neural signal capture and processing method, please refer to the embodiments of the above robotic arm neural signal capture and processing system.

[0059] A method for capturing and processing neural signals in a robotic arm includes the following steps: S1: The neural signal capture module, located at the nerve stump of the amputated arm, uses neural electrodes to capture neural electrical signals in real time.

[0060] S2: The signal preprocessing module amplifies and filters the neural electrical signals to generate analog signals, samples the analog signals, and converts the analog signals into discrete digital signals.

[0061] S3: The identifier resolution module performs time-domain and frequency-domain analysis on the digital signal to extract feature parameters; based on the preset encoding rules, it assigns a unique identifier code to the combination of feature parameters and uses the CRC algorithm to verify the digital signal.

[0062] S4: The digital signal identification code and check code are encapsulated by the signal transmission module, the digital signal is encrypted, and after generating transmission data, it is sent to the robotic arm control module using wireless transmission technology.

[0063] S5: The robotic arm control module acquires transmitted data, parses the human intention represented by the digital signal according to the identification code, and combines it with real-time neural electrical signals to adjust the robotic arm's motion parameters in real time using intelligent control algorithms.

[0064] The robotic arm neural signal capture and processing system provided in this embodiment accurately captures neural signals through high-sensitivity neural electrodes and an automatic calibration unit. After efficient preprocessing and feature extraction, the system uses hash algorithms and CRC checks to ensure signal accuracy and reliability. High-speed wireless transmission and encryption technology are employed to ensure secure and stable signal transmission. The robotic arm control module combines pattern recognition and fuzzy PID control algorithms to accurately interpret intentions and adjust motion parameters in real time. This achieves a complete and efficient process from signal capture to robotic arm control, significantly improving the operational performance, convenience, and comfort of the robotic arm. It represents a major breakthrough in improving the quality of life for people with disabilities and demonstrates broad application prospects.

[0065] Figure 3 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0066] The robotic arm neural signal capture and processing method provided in this application embodiment can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the electronic device includes, but is not limited to, laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0067] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0068] A processor may include one or more processing units, such as: a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0069] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0070] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0071] An external storage interface (ESI) can be used to connect external memory cards, such as microSD cards, to expand the storage capacity of electronic devices. The external memory card communicates with the processor through the ESI to perform data storage functions, such as saving music and video files on the external memory card.

[0072] Internal memory can be used to store computer executable program code, which includes instructions. The processor executes various functional applications and data processing of electronic devices by running the instructions stored in internal memory. Internal memory can include a program storage area and a data storage area. Internal memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0073] Wireless communication functionality in electronic devices can be achieved through antennas, wireless communication modules, modem processors, and baseband processors.

[0074] Wireless communication modules can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0075] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0076] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.

[0077] Electronic devices can achieve display functions through GPUs, displays, and application processors.

[0078] A GPU is a microprocessor for image processing, connected to the display screen and application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0079] A display screen is used to display images, videos, etc. A display screen includes a display panel.

[0080] The aforementioned electronic device realizes the proposed robotic arm neural signal capture and processing method. By employing high-sensitivity neural electrodes to accurately capture neural signals, the signal preprocessing module efficiently amplifies, filters, and performs analog-to-digital conversion, combined with feature extraction, hash encoding, and CRC verification by the identifier resolution module to ensure signal accuracy and reliability, the signal transmission module utilizes data encapsulation encryption and high-speed wireless transmission to ensure secure and stable signal delivery, and the robotic arm control module uses pattern recognition to accurately interpret intent and fuzzy PID control algorithm to adjust motion parameters in real time. This achieves precise and flexible control of the robotic arm over complex movements, thereby effectively improving the convenience and comfort of people with disabilities using the robotic arm and significantly improving their quality of life.

[0081] The storage medium provided in this application stores a program product capable of implementing a method for capturing and processing neural signals from a robotic arm.

[0082] Methods for capturing and processing neural signals in robotic arms include: A neural signal capture module installed at the nerve stump of the severed arm uses neural electrodes to capture neural electrical signals in real time. The neural electrical signal is amplified and filtered by the signal preprocessing module to generate an analog signal. The analog signal is then sampled and converted into a discrete digital signal. The identifier resolution module performs time-domain and frequency-domain analysis on the digital signal to extract feature parameters; based on the preset encoding rules, a unique identifier code is assigned to the combination of feature parameters, and the CRC algorithm is used to verify the digital signal. The digital signal identification code and check code are encapsulated by the signal transmission module, the digital signal is encrypted, and after generating transmission data, it is sent to the robotic arm control module using wireless transmission technology. The robotic arm control module acquires transmitted data, parses the human intention represented by the digital signal according to the identification code, and combines it with real-time neural electrical signals to adjust the robotic arm's motion parameters in real time using intelligent control algorithms.

[0083] In some possible implementations, the robotic arm neural signal capture and processing method of this disclosure can be implemented as a program product including program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure.

[0084] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0085] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A robotic arm neural signal capture and processing system, characterized in that, include: A neural signal capture module is installed at the nerve stump at the amputation site to capture neural electrical signals in real time via neural electrodes. The signal preprocessing module is used to amplify and filter neural electrical signals, generate analog signals, sample the analog signals, and convert the analog signals into discrete digital signals. The identifier resolution module is used to perform time-domain and frequency-domain analysis on digital signals and extract feature parameters; based on preset encoding rules, it assigns a unique identifier code to the combination of feature parameters and uses the CRC algorithm to verify the digital signal; The signal transmission module is used to encapsulate the identification code and check code of the digital signal, encrypt the digital signal, generate transmission data, and send it to the robotic arm control module using wireless transmission technology. The robotic arm control module is used to acquire transmitted data, parse the human intention represented by the digital signal according to the identification code, and combine it with real-time neural electrical signals to adjust the robotic arm's motion parameters in real time using intelligent control algorithms.

2. The robotic arm neural signal capture and processing system according to claim 1, characterized in that, The neural signal capture module is equipped with neural electrodes and a calibration unit. The shape and size of the neural electrodes match the anatomical structure of the nerve stump, and the neural electrodes adopt a multi-point array layout. The calibration unit is used to compare the captured neural electrical signal with a standard electrical signal of known intensity using a reference signal comparison method. The sensitivity parameters of the electrodes are automatically adjusted through a feedback control circuit to ensure the accuracy of signal capture.

3. The robotic arm neural signal capture and processing system according to claim 1, characterized in that, The signal preprocessing module is specifically used for: An operational amplifier is used to amplify the captured neural electrical signals, and the discharge factor is dynamically adjusted during amplification using an automatic gain control algorithm. A second-order active bandpass filter is used to filter the amplified neural electrical signal to generate an analog signal; Based on the Nyquist sampling theorem, the analog signal is sampled at a preset sampling frequency, and a 12-bit analog-to-digital converter is used to quantize the continuous analog signal and convert it into a discrete digital signal. The quantization step size Δ = V full / 2 n V full denoted as , where is the full-scale voltage of the analog-to-digital converter, and n is the number of bits in the analog-to-digital converter.

4. The robotic arm neural signal capture and processing system according to claim 1, characterized in that, The identifier resolution module is specifically used for: Perform time-domain and frequency-domain analysis on digital signals, calculate the peak value, mean, variance, and impulse of the digital signals, obtain the frequency components and spectral energy of the digital signals through fast Fourier transform, and generate characteristic parameter combinations; Based on the preset encoding rules, a hash algorithm is used to convert the binary data of the feature parameter combination into a unique identification code, and generate an identified and encoded signal. The CRC algorithm is used to verify the signal after the identifier is encoded. Before the signal is transmitted, the check code is calculated and appended to the identifier code. At the signal receiving end, the check code of the received signal is recalculated and compared with the received check code. If the two match, the signal is determined to be complete and error-free. If they do not match, the retransmission mechanism is triggered.

5. The robotic arm neural signal capture and processing system according to claim 4, characterized in that, The calculation of the checksum and its appending to the identifier code includes: Using the principle of polynomial division, with a pre-defined generator polynomial G(x) = X 16 +X 12 +X 15 +1 performs a division operation on the encoded signal, and the remainder is used as a check code and appended to the identifier code; where X is a formal variable used to represent different bits in the binary number.

6. The robotic arm neural signal capture and processing system according to claim 1, characterized in that, The signal transmission module is specifically used for: Before signal transmission, the identification code and check code are encapsulated, transmission protocol header information is added, and the digital signal is encrypted using the AES encryption algorithm to generate transmission data. The transmission protocol header information includes the source address, destination address, and data length; Using Wi-Fi 6, Bluetooth 5.0, or ZigBee transmission technologies, the transmitted data is uploaded to a cloud server or edge computing device and sent to the robotic arm control module.

7. The robotic arm neural signal capture and processing system according to claim 1, characterized in that, The robotic arm control module is specifically used for: The system receives uploaded transmission data and, based on a pre-established database of mapping relationships between neural signals and robotic arm movements, matches and classifies the identifier codes using a pattern recognition algorithm to determine the type of movement the patient wants to perform; the movement types include grasping, extending, and rotating. Based on the type of action the patient wants to perform and combined with real-time changes in neural electrical signals, a fuzzy PID control algorithm is used to adjust the motion parameters of the robotic arm in real time; the motion parameters include joint angles, movement speed, and gripping force. The control rules of the fuzzy PID control algorithm include: K p = K p0 + ΔK p K i = K i0 + ΔK i K d = K d0 + ΔK d Among them, K p K i K d K represents the proportional coefficient, integral coefficient, and derivative coefficient of the PID controller. p0 K i0 K d0 These are the initial proportional coefficient, initial integral coefficient, and initial derivative coefficient of the PID controller; ΔK p ΔK i ΔK d This refers to the adjustment amount of the corresponding parameters obtained through fuzzy inference.

8. A method for capturing and processing neural signals in a robotic arm, characterized in that, The method employs the robotic arm neural signal capture and processing system as described in any one of claims 1 to 7; The system includes: A neural signal capture module, installed at the nerve stump of the severed arm, uses neural electrodes to capture neural electrical signals in real time. The neural electrical signal is amplified and filtered by the signal preprocessing module to generate an analog signal. The analog signal is then sampled and converted into a discrete digital signal. The identifier resolution module performs time-domain and frequency-domain analysis on the digital signal to extract feature parameters; based on the preset encoding rules, a unique identifier code is assigned to the combination of feature parameters, and the CRC algorithm is used to verify the digital signal. The digital signal identification code and check code are encapsulated by the signal transmission module, the digital signal is encrypted, and after generating transmission data, it is sent to the robotic arm control module using wireless transmission technology. The robotic arm control module acquires transmitted data, parses the human intention represented by the digital signal according to the identification code, and combines it with real-time neural electrical signals to adjust the robotic arm's motion parameters in real time using intelligent control algorithms.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the robotic arm neural signal capture and processing method as described in claim 8.

10. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the robotic arm neural signal capture and processing method as described in claim 8.

Images