Self-adaptive admittance control method and system for lower limb exoskeleton robot
By analyzing human-computer interaction and physiological state data, the stiffness and damping of the lower limb exoskeleton robot are dynamically adjusted, solving the problem of insufficient user adaptive adjustment in existing technologies and improving the robot's coordination and stability in different motion scenarios.
Patent Information
- Application Number
- CN202511492711.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-20
- Publication Date
- 2026-01-23
AI Technical Summary
Existing lower limb exoskeleton robots are unable to adaptively adjust according to the user's movement and physiological state, resulting in poor assistance effects, energy waste, and movement risks, affecting human-machine coordination and safety.
By acquiring human-computer interaction time-series data and user physiological state time-series data, we analyze user assistance needs and fatigue characteristic values, and combine them with admittance regulation characteristic values to perform adaptive admittance control, dynamically adjusting stiffness and damping to meet the user's motion needs and physiological state.
It enables precise control of the lower limb exoskeleton robot in different movement scenarios, improves the adaptability and stability of human-machine collaborative movement, and ensures user comfort and safety.
Smart Images
Figure CN121374523A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of robot admittance control, in particular to an adaptive admittance control method and system for a lower limb exoskeleton robot. BACKGROUND
[0002] With the growth of rehabilitation medical needs, as an auxiliary device, lower limb exoskeleton robots have gradually become one of the important technologies to solve limb movement disorders and enhance movement ability. Lower limb exoskeleton robots not only help patients with difficulty in movement to restore gait and enhance movement ability, but also provide auxiliary support as an enhancement device to help users more easily complete daily activities. In order to achieve precise auxiliary movement and comfortable use experience.
[0003] At present, exoskeleton robots mainly rely on fixed stiffness and damping strategies in control methods. Although this method can provide certain support, it cannot be dynamically adjusted according to the needs of users, which may lead to user discomfort or low movement efficiency, especially when the movement intensity changes, fatigue increases or gait is unstable, the reaction ability of the exoskeleton robot is weak.
[0004] Based on the above scheme, the limitations of the prior art at least include the following problems: the prior art is difficult to automatically adjust according to the motion state and physiological state of the wearer, so that the lower limb exoskeleton robot is difficult to make accurate response in the face of different motion scenarios such as movement intention conversion, muscle fatigue accumulation, etc., thereby easily leading to poor auxiliary effect and energy waste. For example, when the user's electromyographic signal shows that muscle fatigue is intensified, if the virtual stiffness and damping parameters are still kept low, it is difficult to provide sufficient stability support, which may cause movement risk; and when the interactive force signal detects the user's strong starting intention, if the virtual damping cannot be quickly reduced to improve the system responsiveness, it will cause movement lag, increase the user's energy consumption, and thus affect the synergy and safety of the whole human-machine interaction. SUMMARY
[0005] In view of the deficiencies of the prior art, the present application provides an adaptive admittance control method and system for a lower limb exoskeleton robot, which solves the problem that the prior art is difficult to adaptively adjust according to the physiological state and movement needs of the user, affecting the synergy of man-machine.
[0006] To achieve the above object, the application is implemented by the following technical solutions: An adaptive admittance control method of a lower extremity exoskeleton robot, comprising the following steps: obtaining human-machine interaction time series data of the lower extremity exoskeleton robot and user physiological state time series data; analyzing user assistance demand characteristic values of the lower extremity exoskeleton robot based on the human-machine interaction time series data of the lower extremity exoskeleton robot; analyzing user fatigue characteristic values of the lower extremity exoskeleton robot based on the user physiological state time series data of the lower extremity exoskeleton robot, and combining the user assistance demand characteristic values to analyze admittance regulation characteristic values of the lower extremity exoskeleton robot; and performing adaptive admittance control processing on the lower extremity exoskeleton robot based on the admittance regulation characteristic values.
[0007] Further, the human-machine interaction time series data comprises interaction force signal data and electromyography signal data, the interaction force signal data comprises interaction force values at each time point, and the electromyography signal data comprises EMG values at each time point.
[0008] Further, the specific steps of analyzing the user assistance demand characteristic values of the lower extremity exoskeleton robot are as follows: performing feature extraction processing on the human-machine interaction time series data of the lower extremity exoskeleton robot to obtain interaction mapping characteristic sets of the lower extremity exoskeleton robot, including interaction force intensity characteristics, force change trend characteristics, motion stability characteristics, muscle activation intensity characteristic values, electromyography frequency shift characteristic values, and electromyography activity frequency characteristic values; and analyzing the user assistance demand characteristic values of the lower extremity exoskeleton robot based on the interaction mapping characteristic sets of the lower extremity exoskeleton robot.
[0009] Further, the specific steps of obtaining the interaction mapping characteristic sets of the lower extremity exoskeleton robot are as follows: extracting the interaction force intensity characteristics, the force change trend characteristics, and the motion stability characteristics of the lower extremity exoskeleton robot based on the interaction force signal data of the lower extremity exoskeleton robot; and extracting the muscle activation intensity characteristic values, the electromyography frequency shift characteristic values, and the electromyography activity frequency characteristic values of the lower extremity exoskeleton robot based on the electromyography signal data of the lower extremity exoskeleton robot.
[0010] Further, the specific steps of analyzing the user fatigue characteristic values of the lower extremity exoskeleton robot are as follows: obtaining user reference physiological data of the lower extremity exoskeleton robot, and performing ratio processing on the user physiological state time series data to obtain physiological time series characteristic sets of the lower extremity exoskeleton robot; and analyzing the user fatigue characteristic values of the lower extremity exoskeleton robot based on the physiological deviation time series characteristic sets of the lower extremity exoskeleton robot.
[0011] Further, the specific formula for calculating the admittance regulation characteristic values of the lower extremity exoskeleton robot is as follows: ; wherein, is the admittance regulation characteristic value of the lower extremity exoskeleton robot, is the user assistance demand characteristic value of the lower extremity exoskeleton robot, The power demand adjustment coefficient stored in the database, The user fatigue characteristic value of the lower extremity exoskeleton robot, The fatigue adjustment coefficient stored in the database, The coordination adjustment coefficient stored in the database, .
[0012] Further, the specific steps of the adaptive admittance control processing of the lower extremity exoskeleton robot based on the admittance regulation characteristic value are as follows: comparing and analyzing the admittance regulation characteristic value of the lower extremity exoskeleton robot with the preset admittance regulation characteristic threshold interval; and taking corresponding admittance control measures for the lower extremity exoskeleton robot based on the comparison and analysis result.
[0013] An adaptive admittance control system of a lower extremity exoskeleton robot, comprising: a data acquisition module for acquiring human-machine interaction time series data and user physiological state time series data of the lower extremity exoskeleton robot; a human-machine interaction analysis module for analyzing a user power demand characteristic value of the lower extremity exoskeleton robot based on the human-machine interaction time series data of the lower extremity exoskeleton robot; a comprehensive analysis module for analyzing a user fatigue characteristic value of the lower extremity exoskeleton robot based on the user physiological state time series data of the lower extremity exoskeleton robot, and analyzing an admittance regulation characteristic value of the lower extremity exoskeleton robot in combination with the user power demand characteristic value; and an admittance control feedback module for performing adaptive admittance control processing of the lower extremity exoskeleton robot based on the admittance regulation characteristic value.
[0014] The present application has the following advantages:
[0015] (1) The adaptive admittance control method of the lower extremity exoskeleton robot realizes adaptive and accurate regulation of the admittance of the lower extremity exoskeleton robot by analyzing the human-machine interaction time series data and the user physiological state time series data, extracts features in the interaction force signal data and the electromyographic signal data to construct an interaction mapping feature set that comprehensively reflects the user's motion intention, and generates a user power demand characteristic value accordingly, while accurately evaluating a user fatigue state characteristic value based on the user physiological state time series data, and dynamically generating an admittance regulation characteristic value in combination with the user power demand characteristic value, so as to automatically adjust the admittance according to the user's motion demand and physiological state, thereby significantly improving the adaptability of human-machine collaborative motion.
[0016] (2), the adaptive admittance control system of the lower limb exoskeleton robot, through the data acquisition module obtains human-computer interaction time series data and user physiological state time series data, provides synchronous and accurate input source for human-computer interaction analysis module and comprehensive analysis module;Human-computer interaction analysis module extracts the dynamic characteristics set of interactive force and electromyographic signal, accurately represents the power assistance demand;The comprehensive analysis module fuses the physiological fatigue characteristics and motion demand characteristics, generates the admittance control characteristic value;Finally, through the admittance control feedback module, the adaptive admittance control is realized, so that the stability of the system is significantly improved, and the reliability of the control strategy of the lower limb exoskeleton robot in different motion scenes is ensured.
[0017] Of course, implementing any product of the application does not necessarily require all the advantages described above. BRIEF DESCRIPTION OF DRAWINGS
[0018] Figure 1 The adaptive admittance control method of the lower limb exoskeleton robot of the application is a flow chart.
[0019] Figure 2 The adaptive admittance control system block diagram of the lower limb exoskeleton robot of the application. DETAILED DESCRIPTION
[0020] Please refer to Figure 1 The embodiment of the application provides a technical scheme: an adaptive admittance control method of a lower limb exoskeleton robot, comprising the following steps: in a set sliding time window, obtaining human-computer interaction time series data and user physiological state time series data of the lower limb exoskeleton robot;Based on the human-computer interaction time series data of the lower limb exoskeleton robot, analyze the user power assistance demand characteristic value of the lower limb exoskeleton robot;Based on the user physiological state time series data of the lower limb exoskeleton robot, analyze the user fatigue characteristic value of the lower limb exoskeleton robot, and combine the user power assistance demand characteristic value to analyze the admittance control characteristic value of the lower limb exoskeleton robot;Based on the admittance control characteristic value, the adaptive admittance control processing of the lower limb exoskeleton robot is carried out.
[0021] The human-computer interaction time series data includes interactive force signal data and electromyographic signal data, the interactive force signal data includes the interactive force value at each time point, and the electromyographic signal data includes the EMG value at each time point.
[0022] The specific formula for calculating the admittance control characteristic value of the lower limb exoskeleton robot is as follows: ; wherein, is the admittance control characteristic value of the lower limb exoskeleton robot, is the user power assistance demand characteristic value of the lower limb exoskeleton robot, is the power assistance demand adjustment coefficient stored in the database, The user fatigue characteristic value of the lower extremity exoskeleton robot, The fatigue adjustment coefficient stored in the database, The synergy adjustment coefficient stored in the database, , and in the embodiment, the power assistance demand adjustment coefficient stored in the database , the fatigue adjustment coefficient , the synergy adjustment coefficient are 0.583, 0.417, and 0.624, respectively.
[0023] Specifically, the specific steps of analyzing the user power assistance demand characteristic value of the lower extremity exoskeleton robot are as follows: performing feature extraction processing on the human-machine interaction time series data of the lower extremity exoskeleton robot to obtain an interaction mapping feature set of the lower extremity exoskeleton robot, including an interaction force intensity feature, a force change trend feature, a motion stability feature, a muscle activation intensity feature value, an electromyographic frequency shift feature value, and an electromyographic activity frequency feature value; based on the interaction mapping feature set of the lower extremity exoskeleton robot, analyzing the user power assistance demand characteristic value of the lower extremity exoskeleton robot, which is specifically: performing normalization processing on the interaction force intensity feature, the force change trend feature, the motion stability feature, the muscle activation intensity feature value, the electromyographic frequency shift feature value, and the electromyographic activity frequency feature value of the lower extremity exoskeleton robot, performing weighted processing on the normalized interaction force intensity feature, the force change trend feature, and the motion stability feature, simultaneously performing weighted processing on the normalized muscle activation intensity feature value, the electromyographic frequency shift feature value, and the electromyographic activity frequency feature value, and performing ratio processing on the two weighted processing results to extract the user power assistance demand characteristic value of the lower extremity exoskeleton robot.
[0024] The specific steps of obtaining the interaction mapping feature set of the lower extremity exoskeleton robot are as follows: based on the interaction force signal data of the lower extremity exoskeleton robot, extracting the interaction force intensity feature, the force change trend feature, and the motion stability feature of the lower extremity exoskeleton robot, which is specifically: performing mean value processing on the interaction force value at each time point to extract the interaction force intensity feature (used to represent the average force between the user and the exoskeleton, the larger the value, the more weight the user is supporting or the more force the user is outputting);
[0025] The interaction force values of adjacent time points are subjected to ratio processing, such as the difference between the interaction force values of the first time point and the second time point divided by the interaction force value of the second time point, and weighted processing is performed based on the ratio processing result to extract the force change trend feature (used to represent the intensity of the user's force intention, which quantifies the change rate and trend of the user's force, and the larger the value, the more the user is changing his force state, whether it is suddenly exerting force or suddenly withdrawing force); the interaction force values of each time point are subjected to fast Fourier transform to obtain a plurality of interaction frequency components and corresponding interaction force amplitudes, and the interaction force amplitudes of each interaction frequency component are subjected to square operation to obtain the interaction power values of each interaction frequency component, and weighted processing is performed, and the weighted processing result is subjected to ratio processing with the total interaction power value (i.e. the sum of the interaction power values of all interaction frequency components) to extract the motion stability feature (used to represent the anti-interference ability of the user's motion, which reflects the frequency distribution in the interaction force signal, and the higher the value, the more high-frequency components are contained in the force signal, meaning that the user's motion is shaking, unstable or being disturbed by external high-frequency interference);
[0026] Based on the electromyographic signal data of the lower extremity exoskeleton robot, muscle activation intensity feature values, electromyographic frequency shift feature values, and electromyographic activity frequency feature values of the lower extremity exoskeleton robot are extracted, which are specifically: the electromyographic signal of the set sliding time window is subjected to band-pass filtering processing to remove power frequency noise and motion artifacts, and the EMG value of each time point after band-pass filtering processing is subjected to root mean square processing to extract the muscle activation intensity feature value (used to represent the overall electrical activity intensity of the muscle in the sliding time window, and the larger the value, the more the number of motor units recruited and the higher the discharge frequency, i.e. the stronger the muscle contraction force or the more intense the contraction intention);
[0027] The electromyographic signal in the sliding time window is subjected to fast Fourier transform to convert it from the time domain to the frequency domain, obtaining a plurality of frequency components and corresponding electromyographic amplitudes, and the electromyographic amplitudes of each frequency component are subjected to square operation to obtain the power values of each frequency component, and the cumulative energy method is used to calculate the median frequency, i.e. the total energy of the power values of all frequency components is calculated, and the power values of each frequency component are sequentially added from the lowest frequency component, and when the cumulative energy reaches 50% of the total energy, the frequency component value at this time is recorded as the initial estimate of the median frequency; and the linear interpolation method is used to interpolate between the frequency component and the previous frequency component, and the result is taken as the electromyographic frequency shift feature value (used to represent the concentration trend of the electromyographic signal power spectrum, which represents the change of the frequency spectrum characteristic under the muscle force mode);
[0028] Read the EMG value of each time point, and sequentially difference the EMG values of two adjacent time points, if the difference is less than 0, it is considered that there is a zero-crossing event, the total sum of zero-crossing events is counted, and the ratio processing is performed with the total number of time points, to extract the EMG activity frequency characteristic value (used to represent the degree of change of the EMG signal waveform, the higher the value, the more frequent the signal oscillation, and the muscle may be in a fast adjustment, small amplitude jitter or unstable contraction state).
[0029] In the embodiment, the interaction force and the electromyographic signal are deeply fused to comprehensively perceive the user's motion state, not only accurately capturing the user's force size, but also acutely identifying the rapid and slow changes of the force intention, such as wanting to stand steadily or suddenly start, and secondly, through feature extraction of the interaction force signal, it can be judged whether the motion is stable, whether there is jitter, etc., and the features extracted by the electromyographic signal are analyzed to truly understand the user's motion intention and body state, avoiding energy waste caused by excessive assistance, and providing appropriate support in time when the user really needs it.
[0030] Specifically, the user physiological state time series data includes the user heart rate value, the user skin temperature value, and the user skin electric reaction value of each time point, and the specific steps of analyzing the user fatigue characteristic value of the lower limb exoskeleton robot are as follows: obtaining the user reference physiological data of the lower limb exoskeleton robot (including the user heart rate reference value, the user skin temperature reference value, and the user skin electric reaction reference value, and the heart rate reference value is obtained as follows: obtaining historical user heart rate values of historical time points, and performing mean value processing, taking the result as the user heart rate reference value, and the user skin temperature reference value and the user skin electric reaction reference value have the same acquisition logic as the user heart rate reference value), and performing ratio processing with the user physiological state time series data to obtain the physiological time series feature set of the lower limb exoskeleton robot, that is, performing ratio processing on the user heart rate value, the user skin temperature value, and the user skin electric reaction value of each time point of the lower limb exoskeleton robot with the user heart rate reference value, the user skin temperature reference value, and the user skin electric reaction reference value respectively to obtain the user heart rate ratio value, the user skin temperature ratio value, and the user skin electric reaction ratio value of the corresponding time point, that is, the physiological time series feature set;
[0031] Based on the physiological deviation time series feature set of the lower limb exoskeleton robot, the user fatigue characteristic value of the lower limb exoskeleton robot is analyzed, which is specifically: performing weighted processing on the user heart rate ratio value, the user skin temperature ratio value, and the user skin electric reaction ratio value of each time point of the lower limb exoskeleton robot, and performing sliding average processing based on the weighted processing result to obtain the user fatigue characteristic value of the lower limb exoskeleton robot.
[0032] Among them, the heart rate value can be obtained by an optical volume pulse wave sensor.
[0033] The skin temperature value can be obtained by a skin temperature sensor.
[0034] The skin electrical reaction value can be obtained by a skin conductance sensor.
[0035] In this embodiment, by comparing the user's physiological time series data with the user's reference physiological data, the user's physiological changes can be more accurately captured, and the user's fatigue level can be more finely analyzed. Secondly, by ratio processing of heart rate, skin temperature and skin electrical reaction value, the changes of these physiological signals can be effectively quantified, so as to eliminate the influence of individual differences and environmental changes on the data, make the analysis result more accurate, and the ratio processing makes the lower limb exoskeleton robot reflect the physiological deviation of the user, identify whether the user is in a fatigue state in time, and perform weighted processing and sliding average, which can smooth the instantaneous fluctuation and more accurately predict the fatigue change trend, thereby better supporting the user's movement needs. Finally, it ensures that the robot can tailor the assistance strategy according to the user's physical condition, so that the robot can more accurately perceive and respond to the user's physiological changes, and improve the comfort of use.
[0036] Specifically, the specific steps of performing adaptive admittance control processing on the lower limb exoskeleton robot based on the admittance regulation characteristic value are as follows: comparing and analyzing the admittance regulation characteristic value of the lower limb exoskeleton robot with the preset admittance regulation characteristic threshold interval; based on the comparison and analysis result, taking corresponding admittance control measures on the lower limb exoskeleton robot, which is specifically: if the admittance regulation characteristic value of the lower limb exoskeleton robot is lower than the lower limit of the preset admittance regulation characteristic threshold interval, the stiffness and damping of the lower limb exoskeleton robot are reduced, the support to the user is reduced, and more autonomous movement is allowed, such as the robot reducing the output assistance, maintaining the flexibility of movement and the comfort of the user;
[0037] if the admittance regulation characteristic value of the lower limb exoskeleton robot is in the preset admittance regulation characteristic threshold interval, the stiffness and damping of the lower limb exoskeleton robot are kept in the normal range, and the gait synchronization with the user is ensured, such as maintaining the current control state without the need for large adjustment, ensuring the normal movement of the user; if the admittance regulation characteristic value of the lower limb exoskeleton robot is higher than the lower limit of the preset admittance regulation characteristic threshold interval, the stiffness and damping of the lower limb exoskeleton robot are increased, the support to the user is improved, and the physiological burden of the user is reduced, such as the lower limb exoskeleton robot increasing the output assistance to provide more support.
[0038] In this embodiment, based on the admittance regulation characteristic value, the stiffness and damping of the lower limb exoskeleton robot are dynamically adjusted, so as to more accurately meet the motion requirements and physiological state of the user, and by comparing with the preset admittance regulation characteristic threshold interval, the robot can intelligently identify whether the motion state of the user needs more support or more flexible autonomous motion, for example, when the user is in a low fatigue or high activity level, the control system of the robot will reduce the support intensity and increase the flexibility of motion, so that the user can easily and naturally perform the motion, and when the user is in a fatigue state, the stiffness and damping of the robot will be appropriately increased to provide more support and reduce the physiological burden of the user, helping the user to overcome the difficulties in the motion process, thereby enhancing the comfort of the motion, and avoiding the motion limitation caused by excessive support, and thus the lower limb exoskeleton robot has high adaptability, thereby effectively improving the use experience.
[0039] Please refer to Figure 2 The embodiment of the present application provides a technical scheme: an adaptive admittance control system of a lower limb exoskeleton robot, comprising: a data acquisition module for acquiring human-machine interaction time series data and user physiological state time series data of the lower limb exoskeleton robot; a human-machine interaction analysis module for analyzing user assistance demand characteristic values of the lower limb exoskeleton robot based on the human-machine interaction time series data of the lower limb exoskeleton robot; a comprehensive analysis module for analyzing user fatigue characteristic values of the lower limb exoskeleton robot based on the user physiological state time series data of the lower limb exoskeleton robot, and combining the user assistance demand characteristic values to analyze the admittance regulation characteristic values of the lower limb exoskeleton robot; and an admittance control feedback module for performing adaptive admittance control processing on the lower limb exoskeleton robot based on the admittance regulation characteristic values.
[0040] Although the preferred embodiments of the present application have been described, those skilled in the art can make further changes and modifications to the embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to be interpreted as including all changes and modifications falling within the scope of the present application.
[0041] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these modifications and variations.
Claims
1. An adaptive admittance control method for a lower extremity exoskeleton robot, characterized by, The method comprises the following steps: Obtain human-machine interaction time series data of the lower extremity exoskeleton robot and user physiological state time series data; Based on the human-machine interaction time series data of the lower extremity exoskeleton robot, analyze the user assistance demand characteristic value of the lower extremity exoskeleton robot; Based on the user physiological state time series data of the lower extremity exoskeleton robot, analyze the user fatigue characteristic value of the lower extremity exoskeleton robot, and combine the user assistance demand characteristic value to analyze the admittance control characteristic value of the lower extremity exoskeleton robot; Based on the admittance control characteristic value, perform adaptive admittance control processing on the lower extremity exoskeleton robot.
2. The adaptive admittance control method of the lower extremity exoskeleton robot according to claim 1, wherein, The human-machine interaction time series data includes interaction force signal data and electromyography signal data, the interaction force signal data includes interaction force values at each time point, and the electromyography signal data includes EMG values at each time point.
3. The adaptive admittance control method of the lower extremity exoskeleton robot according to claim 2, wherein, The specific steps for analyzing the user assistance demand characteristic value of the lower extremity exoskeleton robot are as follows: Perform feature extraction processing on the human-machine interaction time series data of the lower extremity exoskeleton robot to obtain interaction mapping feature sets of the lower extremity exoskeleton robot, including interaction force intensity features, force change trend features, motion stability features, muscle activation intensity feature values, electromyography frequency shift feature values, and electromyography activity frequency feature values; Based on the interaction mapping feature sets of the lower extremity exoskeleton robot, analyze the user assistance demand characteristic value of the lower extremity exoskeleton robot.
4. The adaptive admittance control method of the lower extremity exoskeleton robot according to claim 3, wherein, The specific steps for obtaining the interaction mapping feature sets of the lower extremity exoskeleton robot are as follows: Based on the interaction force signal data of the lower extremity exoskeleton robot, extract the interaction force intensity features, force change trend features, and motion stability features of the lower extremity exoskeleton robot; Based on the electromyography signal data of the lower extremity exoskeleton robot, extract the muscle activation intensity feature values, electromyography frequency shift feature values, and electromyography activity frequency feature values of the lower extremity exoskeleton robot.
5. The adaptive admittance control method of the lower extremity exoskeleton robot according to claim 1, wherein, The specific steps for analyzing the user fatigue characteristic value of the lower extremity exoskeleton robot are as follows: Obtain user reference physiological data of the lower extremity exoskeleton robot, and perform ratio processing on the user physiological state time series data to obtain physiological time series features of the lower extremity exoskeleton robot; Based on the physiological deviation time series features of the lower extremity exoskeleton robot, analyze the user fatigue characteristic value of the lower extremity exoskeleton robot. 6.The adaptive admittance control method of the lower extremity exoskeleton robot according to claim 1, wherein, The specific formula for calculating the admittance control characteristic value of the lower extremity exoskeleton robot is as follows: ； wherein, is a user fatigue characteristic value of the lower extremity exoskeleton robot, is a user assistance demand characteristic value of the lower extremity exoskeleton robot, is an assistance demand adjustment coefficient stored in the database, is a user fatigue characteristic value of the lower extremity exoskeleton robot, is a fatigue adjustment coefficient stored in the database, is a coordination adjustment coefficient stored in the database, .
7. The adaptive admittance control method of the lower extremity exoskeleton robot according to claim 1, wherein, The specific steps for performing adaptive admittance control processing on the lower extremity exoskeleton robot based on the admittance control characteristic value are as follows: Compare and analyze the admittance control characteristic value of the lower extremity exoskeleton robot with a preset admittance control characteristic threshold interval; Based on the comparison and analysis result, take corresponding admittance control measures on the lower extremity exoskeleton robot.
8. An adaptive admittance control system of a lower extremity exoskeleton robot, applying the adaptive admittance control method of the lower extremity exoskeleton robot according to any one of claims 1 to 7, characterized by, The method comprises the following steps: A data acquisition module is configured to obtain human-machine interaction time series data of the lower extremity exoskeleton robot and user physiological state time series data; A human-machine interaction analysis module is configured to analyze the user assistance demand characteristic value of the lower extremity exoskeleton robot based on the human-machine interaction time series data of the lower extremity exoskeleton robot; A comprehensive analysis module is configured to analyze the user fatigue characteristic value of the lower extremity exoskeleton robot based on the user physiological state time series data of the lower extremity exoskeleton robot, and analyze the admittance control characteristic value of the lower extremity exoskeleton robot in combination with the user assistance demand characteristic value. An admittance control feedback module is configured to perform adaptive admittance control processing on the lower extremity exoskeleton robot based on the admittance regulation characteristic value.