Exoskeleton robot power auxiliary control method based on artificial intelligence

Abstract

The invention discloses an exoskeleton robot power auxiliary control method based on artificial intelligence, and relates to the technical field of intelligent control. The method comprises the steps that a power device of the exoskeleton robot is determined; acquiring a plurality of indexes for power output of the auxiliary power device; obtaining a first motion scene, and performing parameter learning of an index sequence on the plurality of indexes according to the correlation between the first motion scene and the plurality of indexes to obtain auxiliary learning parameters; the power device controls a power motor to adjust power parameters according to the auxiliary learning parameters. The technical problems that in the prior art, power-assisted control of an exoskeleton robot is not intelligent and accurate enough, power output is difficult to dynamically adjust according to a specific motion scene, energy efficiency is low, and user experience is poor are solved. Accurate adjustment of power parameters of the power device is achieved, and therefore the technical effects of improving energy efficiency and enhancing user experience are achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an artificial intelligence-based exoskeleton robot power-assisted control method. Background Art

[0002] Exoskeleton robots simulate the human skeletal structure to provide users with additional strength support or motion assistance functions, greatly improving the human body's athletic ability and endurance. However, the power-assisted control of exoskeleton robots has always been one of the key factors restricting their performance improvement. Traditional exoskeleton robots have problems such as insufficient intelligence, slow dynamic response, and high energy consumption in power-assisted control. These defects limit their application in complex motion scenarios. Traditional methods can often only provide fixed power output modes, which are difficult to effectively adjust according to the user's real-time motion status, thus affecting the overall energy efficiency and user experience. Summary of the invention

[0003] The present application provides an artificial intelligence-based power-assisted control method for an exoskeleton robot, which solves the technical problems in the prior art that the power-assisted control of an exoskeleton robot is not intelligent and precise enough, and it is difficult to dynamically adjust the power output according to specific motion scenarios, resulting in low energy efficiency and poor user experience.

[0004] The present application provides a power-assisted control method for an exoskeleton robot based on artificial intelligence, the method comprising: Determine a power device of the exoskeleton robot, wherein the power device includes a power input terminal and a power output terminal; obtain multiple indicators for assisting the power output of the power device, wherein the multiple indicators include a power output stability indicator, a power output continuity indicator, a power output step indicator, and a power output energy-saving indicator; receive a sensor data set of a sensor module, perform limb movement scene recognition according to the sensor data set, obtain a first movement scene, perform parameter learning of the multiple indicators in an indicator sequence according to the correlation between the first movement scene and the multiple indicators, and obtain auxiliary learning parameters; the power device controls the power motor to adjust the power parameters according to the auxiliary learning parameters.

[0005] Furthermore, after determining the power device of the exoskeleton robot, determine whether the power device is a single power output; if the power device is a single power output, input the auxiliary learning parameters into the power input end of the power device, identify the initial power parameters according to the auxiliary learning parameters, and output the updated power parameters from the power output end; the power device controls the power motor to adjust the power parameters with the updated power parameters.

[0006] Furthermore, if the power device does not have a single power output, multiple power output circuits of the power device are identified; the auxiliary learning parameters are input into multiple power input terminals of the power device, multiple initial power parameters are identified based on the auxiliary learning parameters, and multiple updated power parameters are output from the power output terminal; the power device controls the power motor to adjust the power parameters with the multiple updated power parameters.

[0007] Furthermore, a collaborative line group of the multiple power output lines is established; the multiple updated power parameters are grouped according to the collaborative line group, the updated power parameter group is output, and the updated power parameters in the updated power parameter group are collaboratively updated to output multiple collaboratively updated power parameters; the power device controls the power motor to adjust the power parameters with the multiple collaboratively updated power parameters.

[0008] Furthermore, the sensing module includes an environmental sensing module, which includes a CMOS sensor, a radar sensor, a GPS and an RTK sensor, and is used to collect sensing data of the environment in which the user wearing the exoskeleton robot is located; obtain the environmental sensing data set collected by the environmental sensing module, and add the environmental sensing data set to the sensing data set.

[0009] Furthermore, the sensing module also includes a limb sensing module, and the limb sensing module includes a first-order inertial sensor and a second-order inertial sensor; the first-order inertial sensor is used to collect upper limb inertial motion sensing data of the user wearing the exoskeleton robot, and the second-order inertial sensor is used to collect lower limb inertial motion sensing data of the user wearing the exoskeleton robot; the limb sensing data set collected by the limb sensing module is obtained, and the limb sensing data set is stored in the sensing data set, and the environmental sensing data set and the limb sensing data set are stored in time series synchronization and alignment using the dynamic time warping DTW algorithm.

[0010] Furthermore, it is determined whether the exoskeleton robot is worn on the legs. If the exoskeleton robot is worn on the legs, a foot pressure sensor is set, and plantar pressure sensing data of the user wearing the exoskeleton robot is collected according to the foot pressure sensor to obtain a foot pressure sensing data set; the foot pressure sensing data set is added to the limb sensing data set for storage and update, and the updated limb sensing data set includes a first-order inertial sensing data set, a second-order inertial sensing data set and a foot pressure sensing data set.

[0011] Furthermore, a motion scene recognition model is constructed, wherein the motion scene recognition model includes a motion scene recognition base layer and a motion scene recognition refinement layer, wherein the motion scene recognition base layer performs basic scene label training on sensor data samples based on a support vector machine to obtain basic scene labels, and the motion scene recognition refinement layer performs refined scene label training on the sensor data samples and the basic scene labels using a convolutional neural network; wherein the basic scene labels at least include walking on flat ground, going up and down stairs, and walking on a ramp, and the refined scene labels include gait phase and slope; the motion scene recognition model is called to perform limb motion scene recognition on the sensor data set to obtain a first motion scene.

[0012] Furthermore, the correlation between the first motion scene and the multiple indicators is identified to obtain multiple correlation coefficients; a parameter learning layer is constructed according to the multiple correlation coefficients to sort the multiple indicators, and multiple queue indicators are output; a parameter learning layer is constructed according to the multiple queue indicators, and the parameter learning layer is connected to the power output end of the power device to perform queue feedback learning, and auxiliary learning parameters are output.

[0013] Furthermore, if the correlation coefficient of the power output step index among the multiple correlation coefficients is the largest, the parameter learning layer weight ratio of the power output step index is set to be greater than 0.5.

[0014] One or more technical solutions provided in this application have at least the following technical effects or advantages: First, determine the power device of the exoskeleton robot, wherein the power device includes a power input end and a power output end. Next, obtain multiple indicators for assisting the power output of the power device, including a power output stability indicator, a power output continuity indicator, a power output step indicator, and a power output energy-saving indicator. Then, receive the sensor data set of the sensor module, perform limb motion scene recognition according to the sensor data set, obtain the first motion scene, and perform parameter learning of the indicator sequence for the multiple indicators according to the correlation between the first motion scene and the multiple indicators to obtain auxiliary learning parameters. Finally, the power device controls the power motor to adjust the power parameters according to the auxiliary learning parameters. The technical problem that the power auxiliary control of the exoskeleton robot in the prior art is not intelligent and accurate enough, and it is difficult to dynamically adjust the power output according to the specific motion scene, resulting in low energy efficiency and poor user experience is solved. By intelligently identifying the limb motion scene and combining multiple power output indicators for parameter learning, the power parameters of the power device are accurately adjusted, thereby achieving the technical effect of improving energy efficiency and enhancing user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A schematic flow chart of a power-assisted control method for an exoskeleton robot based on artificial intelligence provided in an embodiment of the present application; Figure 2 A schematic diagram of a flow chart for obtaining a first motion scene in an artificial intelligence-based exoskeleton robot power-assisted control method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] This application provides an artificial intelligence-based power-assisted control method for an exoskeleton robot, which solves the technical problems in the prior art that the power-assisted control of an exoskeleton robot is not intelligent and precise enough, and it is difficult to dynamically adjust the power output according to specific motion scenarios, resulting in low energy efficiency and poor user experience.

[0018] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0019] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0020] Examples, such as Figure 1 As shown, the embodiment of the present application provides a power-assisted control method for an exoskeleton robot based on artificial intelligence, wherein the method comprises: A power device of the exoskeleton robot is determined, wherein the power device includes a power input end and a power output end.

[0021] The power unit of the exoskeleton robot is a device used to achieve energy transmission and drive control. The power unit mainly includes a power input end and a power output end. The power input end is used to receive energy provided by an external power source, such as a battery, fuel cell or other power source. This part must have stable and reliable energy access capabilities; while the power output end is responsible for converting the input energy into mechanical energy and outputting it to the various actuators of the exoskeleton. Its design must ensure that the output energy meets the accuracy, continuity and stability requirements under different motion modes.

[0022] Furthermore, after determining the power device of the exoskeleton robot, it is determined whether the power device is a single power output; if the power device is a single power output, the auxiliary learning parameters are input into the power input end of the power device, the initial power parameters are identified according to the auxiliary learning parameters, and the updated power parameters are output from the power output end; the power device controls the power motor to adjust the power parameters with the updated power parameters.

[0023] After determining the basic structure of the exoskeleton robot power unit, the output mode of the power unit is judged to determine whether it is a single power output mode. If it is determined that the power unit is a single power output mode, the auxiliary learning parameters obtained through intelligent identification and multi-index parameter learning are further input into the power input end of the power unit. At this time, these auxiliary learning parameters are used to re-identify and analyze the initial power parameters originally set in the power system in order to accurately reflect the energy requirements in the current motion scene. Then, after the parameter identification process, the power output end of the power unit will output the updated power parameters according to the adjustment results, and these updated parameters will serve as the basis for subsequent power adjustment. Finally, the power unit controls the internal power motor and uses the updated power parameters to accurately adjust the output, thereby realizing real-time optimization of the power output of the exoskeleton robot during assisted motion.

[0024] Furthermore, if the power device does not have a single power output, multiple power output circuits of the power device are identified; the auxiliary learning parameters are input into multiple power input terminals of the power device, multiple initial power parameters are identified based on the auxiliary learning parameters, and multiple updated power parameters are output from the power output terminal; the power device controls the power motor to adjust the power parameters with the multiple updated power parameters.

[0025] If the power unit is not a single power output, the system can ensure that it can accurately adjust each line separately by identifying multiple power output lines in the power unit. Specifically, firstly, the independent power output lines in the power unit are determined through detection and identification technology, and the corresponding functions and scope of each line are clarified; then, the auxiliary learning parameters obtained through motion scene recognition and multi-index parameter learning are input into each power input end respectively, so as to identify and correct the initial power parameters of each output line. Next, based on the input auxiliary learning parameters, the system analyzes and processes multiple initial power parameters, generates multiple updated power parameters corresponding to each output line, and outputs these updated parameters from the power output end. Finally, the power unit adjusts the power according to the updated power parameters of each line through precise control of the internal power motor, thereby achieving more detailed and dynamic energy distribution in the multi-output mode, ensuring that the exoskeleton robot can achieve efficient, accurate and energy-saving power assistance in complex motion scenes.

[0026] Furthermore, after the power output terminal outputs a plurality of updated power parameters, the method further includes: Establish a collaborative line group of the multiple power output lines; group the multiple updated power parameters according to the collaborative line group, output the updated power parameter group, and collaboratively update the updated power parameters in the updated power parameter group to output multiple collaboratively updated power parameters; the power device controls the power motor to adjust the power parameters with the multiple collaboratively updated power parameters.

[0027] After multiple updated power parameters are output from the power output end, a collaborative line group between multiple power output lines is further established. Specifically, the system first identifies each independent power output line, and divides them into one or more collaborative line groups according to the function, working state and mutual correlation of each line in the overall power transmission. Subsequently, the system groups the multiple updated power parameters generated by each power output line according to the established collaborative line group to form a corresponding updated power parameter group. In each updated power parameter group, the system uses a preset collaborative update algorithm to integrate and collaboratively update each updated power parameter in the group, thereby outputting multiple collaboratively updated power parameters to ensure the uniformity and coordination of the parameters between each output line. Finally, the power device controls the internal power motor based on these collaboratively updated power parameters to achieve precise adjustment of the power parameters, thereby achieving the purpose of optimizing the power output of the exoskeleton robot in different motion scenarios with high efficiency, precision and energy saving.

[0028] A plurality of indicators for assisting the power output of the power device are obtained, wherein the plurality of indicators include a power output stability indicator, a power output continuity indicator, a power output step indicator, and a power output energy-saving indicator.

[0029] In order to accurately adjust the power output, the system needs to preset multiple indicators related to the power output performance, including the power output stability index, the power output continuity index, the power output step index and the power output energy saving index. Specifically, by analyzing and processing the real-time data collected by the sensor, the system first calculates the power output stability index to evaluate the fluctuation and stability of the power output during long-term operation; then, by measuring the continuity and smoothness of the output signal, the power output continuity index is extracted to reflect the continuity and consistency of the energy transfer process; further, when the system detects a sudden change in the load or control command, the power output step index is obtained by measuring the response rate and amplitude to evaluate the response performance of the system under sudden change conditions; finally, by comparing the actual output power with the input energy, the power output energy saving index is calculated to reflect the overall energy conversion efficiency and energy saving effect.

[0030] By analyzing and processing the real-time data collected by the sensor, the system first pre-processes the raw data, including noise filtering and data smoothing, to ensure the accuracy and reliability of the data. The pre-processed data reflects the actual operation of the exoskeleton robot under different working conditions. Subsequently, the system uses a dynamic analysis algorithm based on these data to calculate indicators reflecting the stability of the power output. Specifically, the power output stability index determines whether there is a significant fluctuation or abnormal change in the output signal by evaluating the fluctuation amplitude, change rate and long-term trend of the power output parameters (such as current, voltage, speed, etc.), thereby quantifying the stability of the system's power output.

[0031] Receive a sensor data set from a sensor module, perform limb movement scene recognition based on the sensor data set, obtain a first movement scene, perform parameter learning of the indicator sequence for the multiple indicators based on the correlation between the first movement scene and the multiple indicators, and obtain auxiliary learning parameters.

[0032] The system collects multi-dimensional data of the user's movement by receiving the sensor module to form a sensor data set (such as joint angle, angular velocity, ground reaction force, etc.). Then, the sensor data set is preprocessed to remove noise and abnormal data; then the preprocessed data is analyzed using a trained motion scene recognition model (such as a classification network based on machine learning or deep learning) to accurately determine the user's current limb movement scene, and then obtain the first motion scene (such as walking, running, or going up and down stairs, etc.); after identifying the first motion scene, the system sorts or weights these indicators according to the correlation between the scene and the aforementioned multiple power output indicators (such as power output stability indicator, power output continuity indicator, power output step indicator, power output energy saving indicator), and performs parameter learning on this basis, that is, dynamically adjusts the contribution of each indicator to the final decision to obtain the optimal configuration, thereby obtaining auxiliary learning parameters; the auxiliary learning parameters include comprehensive considerations of achieving high stability, continuity, step response capability and energy saving effect in the current motion scene, and provide targeted guidance and optimization basis for the subsequent power device in the power output adjustment process.

[0033] Furthermore, the sensing module includes an environmental sensing module, which includes a CMOS sensor, a radar sensor, a GPS and an RTK sensor, and is used to collect sensing data of the environment in which the user wearing the exoskeleton robot is located; obtain the environmental sensing data set collected by the environmental sensing module, and add the environmental sensing data set to the sensing data set.

[0034] In order to obtain more comprehensive information about the user's environment and adjust the auxiliary control strategy of the exoskeleton robot more accurately, the system is equipped with an environmental sensing module, which includes a variety of sensing devices such as CMOS sensors, radar sensors, GPS and RTK sensors, which are used to perceive the visual information of the user's surrounding environment, obstacle distribution and precise location information. Specifically, the CMOS sensor can capture environmental image data in real time, the radar sensor is responsible for detecting the distance and direction of obstacles or target objects, and the GPS and RTK sensors provide more accurate location information and positioning capabilities. By preprocessing the environmental sensing data set obtained by the above-mentioned environmental sensing module and merging it with the user's body sensing data into the same sensing data set, the system can more accurately evaluate the user's current environmental conditions and motion needs in the subsequent motion scene recognition and power parameter learning stages, thereby improving the intelligence and adaptability of the exoskeleton robot's auxiliary output in different scenarios.

[0035] Furthermore, the sensing module also includes a limb sensing module, which includes a first-order inertial sensor and a second-order inertial sensor; the first-order inertial sensor is used to collect upper limb inertial motion sensing data of the user wearing the exoskeleton robot, and the second-order inertial sensor is used to collect lower limb inertial motion sensing data of the user wearing the exoskeleton robot; the limb sensing data set collected by the limb sensing module is obtained, and the limb sensing data set is stored in the sensing data set, and the environmental sensing data set and the limb sensing data set are stored in time series synchronization and alignment using the dynamic time warping DTW algorithm.

[0036] In order to more comprehensively capture the motion characteristics of the user wearing the exoskeleton robot in different limb parts, the system is also equipped with a limb sensing module, which includes a first-order inertial sensor and a second-order inertial sensor. The first-order inertial sensor is used to collect the inertial motion parameters of the user's upper limbs in real time, and the second-order inertial sensor is used to collect the inertial motion parameters of the user's lower limbs in real time. After obtaining the limb sensing data set collected by the above-mentioned limb sensing module, the system will store the data set in a unified sensing data set, and at the same time, the environmental sensing data set previously obtained by the environmental sensing module will be synchronized with the limb sensing data set through the dynamic time warping (DTW) algorithm to synchronize the time series, so that the two remain accurately consistent in the time dimension. This not only ensures that when the user's motion scene is subsequently identified and the power output is adjusted, the environmental information and the limb motion information can be effectively integrated and analyzed on the same time basis, but also lays a data foundation for the exoskeleton robot to achieve more accurate motion assistance in complex environments.

[0037] In order to ensure that the recognition of user motion scenes and subsequent power-assisted decisions can be comprehensively analyzed based on the environmental information and limb motion information on the same time basis, the system uses the dynamic time warping (DTW) algorithm to achieve time-series synchronization alignment of the two parts of data after acquiring the environmental sensor data set and the limb sensor data set. Specifically, the DTW algorithm calculates the similarity between different data sequences and performs nonlinear mapping on the time axis, so that the environmental data and limb data can still be accurately matched and aligned in the time dimension when the sampling rate or sampling duration is different. Through this time-series synchronization alignment processing, it can be ensured that in the subsequent motion scene recognition and auxiliary learning parameter calculation process, various types of sensor information are in a consistent time basis, avoiding analysis deviations caused by misaligned data timestamps, thereby improving the exoskeleton robot's perception accuracy and response efficiency of the user's motion state and surrounding environment.

[0038] Furthermore, it is determined whether the exoskeleton robot is worn on the legs. If the exoskeleton robot is worn on the legs, a foot pressure sensor is set, and plantar pressure sensing data of the user wearing the exoskeleton robot is collected according to the foot pressure sensor to obtain a foot pressure sensing data set; the foot pressure sensing data set is added to the limb sensing data set for storage and update, and the updated limb sensing data set includes a first-order inertial sensing data set, a second-order inertial sensing data set and a foot pressure sensing data set.

[0039] In order to accurately identify and collect the force on the soles of the feet of the user when wearing the exoskeleton robot on the legs, the system first determines whether the exoskeleton robot is in the leg-wearing state; if it is confirmed to be in the leg-wearing state, the foot pressure sensor set at the corresponding foot position of the exoskeleton robot is activated to collect the user's sole pressure sensing data in real time to form a foot pressure sensing data set. Subsequently, the system adds the foot pressure sensing data set to the acquired first-order inertial sensing data set and second-order inertial sensing data set for storage and update, so that the updated limb sensing data set contains upper limb inertial data, lower limb inertial data and sole pressure data at the same time.

[0040] Furthermore, if Figure 2 As shown, the limb movement scene recognition is performed according to the sensor data set to obtain a first movement scene, and the method includes: A motion scene recognition model is constructed, wherein the motion scene recognition model includes a motion scene recognition base layer and a motion scene recognition refinement layer, wherein the motion scene recognition base layer performs basic scene label training on sensor data samples based on a support vector machine to obtain basic scene labels, and the motion scene recognition refinement layer performs refined scene label training on the sensor data samples and the basic scene labels using a convolutional neural network to obtain; wherein the basic scene labels at least include walking on flat ground, going up and down stairs, and walking on a ramp, and the refined scene labels include gait phase and slope; and the motion scene recognition model is called to perform limb motion scene recognition on the sensor data set to obtain a first motion scene.

[0041] Preferably, in order to more accurately identify the limb movement scene and obtain the first movement scene, a movement scene recognition model consisting of a movement scene recognition base layer and a movement scene recognition refinement layer is first constructed: wherein the movement scene recognition base layer trains the sensor data samples based on the support vector machine (SVM) to obtain basic scene labels such as walking on flat ground, going up and down stairs, and walking on a ramp; on this basis, the movement scene recognition refinement layer uses a convolutional neural network (CNN) to further refine the same batch of sensor data samples and basic scene labels to obtain more detailed scene labels such as gait phase and slope. Through this hierarchical recognition method, the category of the overall movement scene can be quickly determined first; next, CNN is used to extract features and perform deep learning on the classified basic scene data to identify specific movement details (such as gait phases or specific walking slopes corresponding to different walking stages). The system calls the motion scene recognition model to process the time-aligned sensor data set, first uses SVM for coarse scene classification, and then uses CNN for refined classification, so as to finally obtain the first motion scene including basic scene information and scene details, providing a more accurate and multi-dimensional reference for the subsequent auxiliary learning parameter calculation and power output adjustment of the power device.

[0042] Furthermore, the method of performing parameter learning of the indicator sequence for the multiple indicators according to the correlation between the first motion scene and the multiple indicators includes: Identify the correlation between the first motion scene and the multiple indicators, and obtain multiple correlation coefficients; construct a parameter learning layer according to the multiple correlation coefficients to sort the multiple indicators, output multiple queue indicators, construct a parameter learning layer according to the multiple queue indicators, connect the parameter learning layer to the power output end of the power device to perform queue feedback learning, and output auxiliary learning parameters.

[0043] After the system identifies the first motion scene, it will first calculate the correlation between the motion scene and multiple indicators such as the power output stability index, the power output continuity index, the power output step index and the power output energy-saving index, and obtain the corresponding multiple correlation coefficients; based on these correlation coefficients, the system prioritizes or weights the above indicators in the parameter learning layer to form multiple queue indicators. Subsequently, the parameter learning layer will connect it to the power output end of the power device according to the obtained multiple queue indicators, conduct queue-style feedback learning for the priority of each indicator, and continuously correct and optimize the required weights and algorithm parameters. Through this mechanism, the system can adaptively adjust the focus on different indicators, and finally output auxiliary learning parameters to provide a targeted configuration plan for the power output of the exoskeleton robot, so that in the first motion scene identified, the power device can adjust the output in a more reasonable and accurate manner.

[0044] In order to quantify the correlation between the first motion scene and the power output stability index, power output continuity index, power output step index and power output energy-saving index, the system first compares the power output characteristics collected in the motion scene with the reference values ​​of each index based on historical sample data or real-time sensor data, and performs statistical analysis in combination with the definition of each index (such as fluctuation measurement to measure stability, output smoothness to measure continuity, step response to measure mutation adaptability, and energy utilization to measure energy-saving effect); in specific implementation, the degree of deviation, fluctuation trend and response rate between different scene data and indicators can be quantitatively calculated through methods such as Pearson correlation and Spearman correlation, so as to obtain one or more correlation coefficients, which respectively reflect the sensitivity and importance of the first motion scene to each index. The above-mentioned correlation measurement can provide a reliable basis for the subsequent sorting and weight allocation of multiple indicators in the parameter learning layer.

[0045] Furthermore, if the correlation coefficient of the power output step indicator among the multiple correlation coefficients is the largest, the parameter learning layer weight ratio of the power output step indicator is set to be greater than 0.5.

[0046] When the calculated multiple correlation coefficients show that the correlation coefficient of the power output step indicator is the maximum value, the system will specially increase the weight of the step indicator in the parameter learning layer. The specific implementation method is: make the parameter learning layer weight of the power output step indicator exceed 0.5, so that the indicator will be given a higher priority in the subsequent queue feedback learning and auxiliary learning parameter generation process. In this way, the system can ensure that the attention to the power output step characteristics is greatly improved in sports scenarios where the scene changes quickly or requires high-sensitivity response, and achieve faster adaptation to sudden load or action switching scenarios.

[0047] The power device controls the power motor to adjust the power parameters according to the auxiliary learning parameters.

[0048] After obtaining the auxiliary learning parameters, the power unit will input the parameters into the internal control module. The control module will adjust the operating mode of the power motor (such as output torque, speed or current, etc.) in real time according to the optimization strategy for different power output indicators (such as stability, continuity, step response and energy saving, etc.) in the auxiliary learning parameters. Specifically, the system will monitor the working status of the power motor in real time, and compare the auxiliary learning parameters with the currently collected sensor data (including exoskeleton joint force, movement amplitude, user physical status, etc.). If a deviation is detected, the motor will be corrected accordingly in speed or torque according to the pre-set threshold and adjustment range of the auxiliary learning parameters, so that the power output tends to the optimal state, ultimately achieving efficient energy utilization and precise power support for the exoskeleton robot.

[0049] In summary, the embodiments of the present application have at least the following technical effects: First, determine the power device of the exoskeleton robot, wherein the power device includes a power input end and a power output end. Next, obtain multiple indicators for assisting the power output of the power device, including a power output stability indicator, a power output continuity indicator, a power output step indicator, and a power output energy-saving indicator. Then, receive the sensor data set of the sensor module, perform limb motion scene recognition according to the sensor data set, obtain the first motion scene, and perform parameter learning of the indicator sequence for the multiple indicators according to the correlation between the first motion scene and the multiple indicators to obtain auxiliary learning parameters. Finally, the power device controls the power motor to adjust the power parameters according to the auxiliary learning parameters. The technical problem that the power auxiliary control of the exoskeleton robot in the prior art is not intelligent and accurate enough, and it is difficult to dynamically adjust the power output according to the specific motion scene, resulting in low energy efficiency and poor user experience is solved. By intelligently identifying the limb motion scene and combining multiple power output indicators for parameter learning, the power parameters of the power device are accurately adjusted, thereby achieving the technical effect of improving energy efficiency and enhancing user experience.

[0050] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0051] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0052] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A power-assisted control method for an exoskeleton robot based on artificial intelligence, characterized in that: The method comprises: Determine a power device of the exoskeleton robot, wherein the power device includes a power input end and a power output end; Acquiring multiple indicators for assisting the power output of the power device, the multiple indicators including a power output stability indicator, a power output continuity indicator, a power output step indicator, and a power output energy-saving indicator; Receiving a sensor data set from a sensor module, performing limb movement scene recognition according to the sensor data set, acquiring a first movement scene, and performing parameter learning of the indicator sequence for the multiple indicators according to the correlation between the first movement scene and the multiple indicators to obtain auxiliary learning parameters; The power device controls the power motor to adjust the power parameters according to the auxiliary learning parameters.

2. The artificial intelligence-based exoskeleton robot power-assisted control method according to claim 1, characterized in that: After determining the power device of the exoskeleton robot, determining whether the power device is a single power output; If the power device has a single power output, the auxiliary learning parameter is input into the power input end of the power device, the initial power parameter is identified according to the auxiliary learning parameter, and the updated power parameter is output from the power output end; The power device controls the power motor to adjust the power parameters according to the updated power parameters.

3. The artificial intelligence-based exoskeleton robot power-assisted control method according to claim 2, characterized in that: If the power device does not have a single power output, identifying multiple power output lines of the power device; Inputting the auxiliary learning parameters into a plurality of power input terminals of the power device, identifying a plurality of initial power parameters according to the auxiliary learning parameters, and outputting a plurality of updated power parameters from the power output terminal; The power device controls the power motor to adjust the power parameters using the multiple updated power parameters.

4. The artificial intelligence-based exoskeleton robot power-assisted control method according to claim 3, characterized in that: After the power output terminal outputs a plurality of updated power parameters, the method further includes: Establishing a coordinated line group of the plurality of power output lines; Grouping the multiple updated power parameters according to the cooperative line group, outputting an updated power parameter group, and cooperatively updating the updated power parameters in the updated power parameter group, outputting multiple cooperatively updated power parameters; The power device controls the power motor to adjust the power parameters using the multiple coordinated updated power parameters.

5. The artificial intelligence-based exoskeleton robot power-assisted control method according to claim 1, characterized in that: The sensor module includes an environmental sensor module, which includes a CMOS sensor, a radar sensor, a GPS and an RTK sensor, and is used to collect sensor data of the environment in which the user wearing the exoskeleton robot is located; Acquire the environmental sensing data set collected by the environmental sensing module, and add the environmental sensing data set to the sensing data set.

6. The artificial intelligence-based exoskeleton robot power-assisted control method according to claim 5, characterized in that: The sensor module also includes a limb sensor module, and the limb sensor module includes a first-order inertial sensor and a second-order inertial sensor; The first-order inertial sensor is used to collect upper limb inertial motion sensing data of the user wearing the exoskeleton robot, and the second-order inertial sensor is used to collect lower limb inertial motion sensing data of the user wearing the exoskeleton robot; The limb sensing data set collected by the limb sensing module is obtained, and the limb sensing data set is stored in the sensing data set. The environment sensing data set and the limb sensing data set are stored by performing time-series synchronization and alignment using a dynamic time warping (DTW) algorithm.

7. The artificial intelligence-based exoskeleton robot power-assisted control method according to claim 6, characterized in that: Determine whether the exoskeleton robot is worn on the legs. If the exoskeleton robot is worn on the legs, set a foot pressure sensor, collect plantar pressure sensing data of the user wearing the exoskeleton robot according to the foot pressure sensor, and obtain a foot pressure sensing data set; The foot pressure sensing data set is added to the limb sensing data set for storage and update, and the updated limb sensing data set includes a first-order inertial sensing data set, a second-order inertial sensing data set and a foot pressure sensing data set.

8. The artificial intelligence-based exoskeleton robot power-assisted control method according to claim 1, characterized in that: Performing limb movement scene recognition according to the sensor data set to obtain a first movement scene, the method comprising: Constructing a motion scene recognition model, the motion scene recognition model comprising a motion scene recognition base layer and a motion scene recognition refinement layer, the motion scene recognition base layer performs basic scene label training on sensor data samples based on a support vector machine to obtain basic scene labels, and the motion scene recognition refinement layer performs refined scene label training on the sensor data samples and the basic scene labels using a convolutional neural network to obtain; The basic scene labels at least include walking on flat ground, going up and down stairs, and walking on a ramp, and the detailed scene labels include gait phase and slope; The motion scene recognition model is called to perform limb motion scene recognition on the sensor data set to obtain a first motion scene.

9. The artificial intelligence-based exoskeleton robot power-assisted control method according to claim 1, characterized in that: According to the correlation between the first motion scene and the multiple indicators, parameter learning of the indicator sequence is performed on the multiple indicators, and the method includes: Identifying the correlation between the first motion scene and the multiple indicators, and obtaining multiple correlation coefficients; A parameter learning layer is constructed according to the multiple correlation coefficients to sort the multiple indicators, and multiple queue indicators are output. A parameter learning layer is constructed according to the multiple queue indicators, and the parameter learning layer is connected to the power output end of the power device to perform queue feedback learning, and output auxiliary learning parameters.

10. The artificial intelligence-based exoskeleton robot power-assisted control method according to claim 9, characterized in that: If the correlation coefficient of the power output step indicator among the multiple correlation coefficients is the largest, the parameter learning layer weight ratio of the power output step indicator is set to be greater than 0.5.

Images