Intelligent wearable exoskeleton self-adaptive auxiliary regulation and control method and exoskeleton system

Abstract

The invention discloses an intelligent wearable exoskeleton self-adaptive auxiliary regulation and control method and an intelligent wearable exoskeleton system.The intelligent wearable exoskeleton self-adaptive auxiliary regulation and control method comprises the steps that a motion data sample of human walking is obtained, and a human motion model is constructed based on a man-machine closed-chain motion model according to the motion data sample; collecting multi-modal data of the target user when the target user wears the exoskeleton in real time; calling a human body motion model and a man-machine closed-chain motion model, and generating an exoskeleton control instruction of man-machine motion cooperation according to the multi-modal data; and dynamically adjusting motion control parameters of the exoskeleton according to the control instruction. According to the method, the precise human body motion model is constructed based on the man-machine closed-chain motion model, the man-machine motion cooperative exoskeleton control instruction is generated in combination with the model, the exoskeleton motion control parameters are dynamically adjusted according to the instruction, the body type difference, the muscle strength level and the motion habit of different users can be precisely matched, and the wearing comfort and safety are effectively improved.

Description

Technical Field

[0001] The embodiments of this specification relate to the technical field of intelligent wearable devices, and particularly to an intelligent wearable exoskeleton adaptive assistance regulation method and an intelligent wearable exoskeleton system. Background Art

[0002] As an advanced human-machine interaction system integrating mechanical engineering, biomedical and intelligent control technologies, exoskeletons are accelerating the intelligent transformation of traditional rehabilitation treatment models. With the deepening of the global population aging and the continuous growth of the rehabilitation needs of patients with motor function disorders, traditional rehabilitation methods mainly based on artificial training gradually expose structural defects such as insufficient personalized adaptation ability and slow improvement of long-term efficacy. For example, standardized rehabilitation training programs are difficult to match the muscle strength attenuation degree, joint range of motion limitation differences and movement compensation patterns of different patients, resulting in problems such as aggravated muscle atrophy or secondary joint injuries for some patients due to mismatched training intensity. Exoskeleton technology can significantly improve the pertinence and efficiency of rehabilitation training by accurately sensing human motion intentions and providing quantitative assistance forces, showing advantages that are difficult to replace by traditional means in clinical scenarios such as gait reconstruction for stroke patients and standing function recovery for spinal cord injury patients.

[0003] The large-scale application of current exoskeleton technology is still limited by four core bottlenecks: First, the lack of personalized adaptability. Existing systems mostly adopt a "one-size-fits-all" control parameter setting, and cannot dynamically respond to individual differences in body size (such as leg length deviation > 5 cm), muscle strength level (such as the maximum torque of the quadriceps femoris < 40% of the normal population average), and movement habits (such as the abnormal gait cycle of hemiplegic patients); Second, the defect in wearing comfort. The fixed joint limit and single assist mode of traditional mechanical structures are likely to cause muscle fatigue or skin compressive injuries to users.

[0004] In view of this, how to improve the comfort of intelligent wearable exoskeletons during use and enhance the adaptability in different application objects and application environments is a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0005] In view of this, the embodiments of this specification provide an intelligent wearable exoskeleton adaptive assistance regulation method. One or more embodiments of this specification also relate to an intelligent wearable exoskeleton system to solve the technical defects existing in the prior art.

[0006] According to the first aspect of the embodiments of this specification, an intelligent wearable exoskeleton adaptive assistance regulation method is provided, including: Obtain a motion data sample of human walking, and construct a human motion model based on the motion data sample and a human-machine closed-chain motion model; wherein, the human-machine closed-chain motion model is a motion coupling relationship model of a wearable exoskeleton and a human joint constructed based on the human motion mechanism. Real-time collect multi-modal data of a target user when wearing the exoskeleton. Call the human motion model and the human-machine closed-chain motion model, and generate an exoskeleton control instruction for human-machine motion coordination according to the multi-modal data. Dynamically adjust the motion control parameters of the exoskeleton according to the control instruction.

[0007] In one embodiment, the constructing a human motion model based on the motion data sample and a human-machine closed-chain motion model includes: Construct a general model and a difference model of human motion based on the motion data sample and the human-machine closed-chain motion model. Wherein, the general model is used to analyze the common characteristics of crowd motion, and the difference model is used to analyze the motion characteristic differences between individuals.

[0008] In one embodiment, the real-time collecting multi-modal data of a target user when wearing the exoskeleton includes: Real-time collect the physiological parameters, motion states and environmental information of the target user when wearing the exoskeleton as the multi-modal data.

[0009] In one embodiment, the dynamically adjusting the motion control parameters of the exoskeleton according to the control instruction includes: Dynamically adjust the power output parameters, kinematic parameters, energy management parameters and human-machine interaction parameters of the exoskeleton according to the control instruction.

[0010] In one embodiment, before the real-time collecting multi-modal data of a target user when wearing the exoskeleton, it further includes: Perform personalized parameter configuration of initial motion control on the exoskeleton according to the individual characteristics of the target user.

[0011] In one embodiment, after the dynamically adjusting the motion control parameters of the exoskeleton according to the control instruction, it further includes: After the state of the exoskeleton is adjusted, obtain the real-time collected multi-modal data. Evaluate the adjustment effect according to the multi-modal data to generate an evaluation result. Optimize and adjust the human-machine closed-chain motion model, the human motion model and the motion control parameters according to the evaluation result.

[0012] According to the second aspect of the embodiments of this specification, an intelligent wearable exoskeleton system is provided, including: A multi-dimensional sensing module, configured to collect motion data samples of human walking and real-time collect multi-modal data of a target user when wearing the exoskeleton; A main controller module, configured to construct a human motion model based on the human-machine closed-chain motion model according to the motion data samples; call the human motion model and the human-machine closed-chain motion model, generate an exoskeleton control instruction for human-machine motion coordination according to the multi-modal data; dynamically adjust the motion control parameters of the exoskeleton according to the control instruction; wherein, the human-machine closed-chain motion model is a motion coupling relationship model of the wearable exoskeleton and human joints constructed based on the human motion mechanism.

[0013] In one embodiment, the multi-dimensional sensing module includes: A joint position sensor, configured to collect joint motion curves; A force sensor, configured to monitor the force condition of bone movement; An electromyography sensor, configured to obtain muscle output torque and activity signals; An accelerometer, configured to detect motion acceleration parameters; An environment sensor, configured to sense environmental dynamic change data.

[0014] In one embodiment, the main controller module includes: A DSP unit, configured to receive the motion data samples and the multi-modal data transmitted by the multi-dimensional sensing module, and perform signal filtering processing; perform feature processing on the filtered signals to obtain sample features and multi-modal features; construct a human motion model based on the human-machine closed-chain motion model according to the sample features; call the human motion model and the human-machine closed-chain motion model, and generate an exoskeleton control instruction for human-machine motion coordination according to the multi-modal features; An FPGA unit, configured to execute a control algorithm and an adaptive strategy according to the exoskeleton control instruction analyzed and generated by the DSP unit, and dynamically adjust the motion control parameters of the exoskeleton.

[0015] In one embodiment, the intelligent wearable exoskeleton system further includes: a feedback and adjustment module, configured to evaluate the adjustment effect according to the collected data and generate an evaluation result; optimize and adjust the human-machine closed-chain motion model, the human motion model, and the motion control parameters according to the evaluation result.

[0016] The intelligent wearable exoskeleton adaptive assistance regulation method provided by this application obtains human walking motion data samples, constructs an accurate human motion model based on the human-machine closed-chain motion model, then collects multi-modal data in real time when the target user wears the exoskeleton, generates exoskeleton control instructions for human-machine motion coordination in combination with the model, and dynamically adjusts the exoskeleton motion control parameters according to the instructions. It can break through the limitations of the traditional "one-size-fits-all" exoskeleton mode, accurately match the body type differences, muscle strength levels, and motion habits of different users, effectively improve wearing comfort and safety, avoid problems such as muscle fatigue and skin damage caused by improper assistance, and at the same time achieve real-time and adaptive dynamic regulation through closed-loop feedback, enhance the adaptability of the exoskeleton in different application objects and scenarios, significantly improve the pertinence and efficiency of rehabilitation training, and provide strong technical support for the intelligent transformation of the traditional rehabilitation treatment mode. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flowchart of an intelligent wearable exoskeleton adaptive assistance regulation method provided by an embodiment of this specification; Figure 2 is a schematic diagram of the overall implementation of exoskeleton control provided by an embodiment of this specification; Figure 3 is a schematic diagram of the structure of an intelligent wearable exoskeleton system provided by an embodiment of this specification. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] Many specific details are set forth in the following description in order to provide a thorough understanding of this specification. However, this specification can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the connotation of this specification. Therefore, this specification is not limited by the specific implementations disclosed below.

[0019] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any and all possible combinations of one or more of the associated listed items.

[0020] It should be understood that although terms such as first and second may be used in one or more embodiments of this specification to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to a determination".

[0021] In this specification, an intelligent wearable exoskeleton adaptive assistance control method is provided. This specification also relates to an intelligent wearable exoskeleton system, which will be described in detail one by one in the following embodiments.

[0022] Embodiment 1: See Figure 1 , Figure 1 which shows a flowchart of an intelligent wearable exoskeleton adaptive assistance control method provided according to an embodiment of this specification, specifically including the following steps.

[0023] Step S101: Obtain a motion data sample of human walking, and construct a human motion model based on the motion data sample based on the human-machine closed-chain motion model; Collect the walking data of normal people or specific patients in the main application scenarios with a preset sample size. The data may include: joint motion angle curves (knee joint, hip joint, etc.), bone motion trajectory parameters, output torque data of muscles at joints, muscle electrical signal activity characteristics, etc.

[0024] According to the obtained motion data sample, relying on the human-machine closed-chain motion model, construct a human motion model to depict the motion coupling relationship between the exoskeleton and human joints, such as the linkage trajectory and force transmission path of mechanical joints and biological joints, and construct the human motion model. The human motion model is based on the human motion mechanism and is verified and corrected through data samples to ensure the consistency between physical meaning and actual scenarios.

[0025] Among them, the human-machine closed-chain motion model is a motion coupling relationship model between the wearable exoskeleton and human joints constructed based on the human motion mechanism. The human-machine closed-chain motion model is used to describe the spatial position constraints, motion transmission relationships, and force coupling characteristics between the exoskeleton mechanical joints and human joints. The human-machine closed-chain motion model takes into account the natural motion trajectory and mechanical characteristics of human joints. When analyzing and controlling the exoskeleton based on the human-machine closed-chain motion model, muscle fatigue or skin compression caused by the "fixed joint limit" of traditional exoskeletons can be avoided. For example, in the flexion and extension motion of the knee joint, the model can drive the exoskeleton joint to rotate along the real joint center of the user, reduce the friction of the mechanical structure on soft tissues, and improve the comfort of long-term wearing.

[0026] Step S102: Collect multi-modal data of the target user in real time while wearing the exoskeleton; Collect the multi-modal data of the target user in real time. The collected data covers multiple modalities, such as biomechanical signals (such as electromyogram EMG, joint torque), motion posture data (such as acceleration and angular velocity of inertial navigation sensors), physiological indicators (such as heart rate, body surface pressure), etc., so as to accurately capture the individual state. For example, the user's motion intention (such as whether to prepare to lift the leg) can be identified through electromyogram signals, and the motion phase (such as the stance phase / swing phase) can be judged by combining joint angle data, providing a real-time basis for dynamic regulation. The fusion of multi-modal data can improve the accuracy of model calculation, thus ensuring that the control instructions fit the user's current state. Optionally, a configuration of multi-modal data includes: physiological parameters, motion state, and environmental information. Physiological parameters such as heart rate, energy consumption, and muscle fatigue; motion state such as joint motion curves, bone motion trajectories, joint output torque, and muscle electrical activity signals; environmental information such as terrain (ground flatness, slope, obstacles), spatial environmental data (environmental temperature, humidity, light intensity). Existing exoskeletons are difficult to better adapt to complex or dynamic environmental changes. In the method of the present invention, more comprehensive environmental correction data can be provided according to complex or dynamic environmental changes, enabling the exoskeleton to work better under various conditions. This configuration of multi-modal data comprehensively considers physiological parameters, motion state, and environmental information, and can comprehensively describe the user's current situation from multiple dimensions. It can not only understand the user's body movement, but also know their physiological fatigue level and the environmental conditions they are in, so as to more accurately grasp the user's overall state. Of course, different data collection items can also be configured according to different needs, which will not be limited here.

[0027] Compared with the traditional fixed-parameter system, this method can achieve "one solution for one person" through real-time collection and analysis of multi-modal data, thereby improving training safety and efficiency.

[0028] Step S103: Invoke the human motion model and the human-machine closed-chain motion model, and generate exoskeleton control instructions for human-machine motion coordination according to the multi-modal data; By analyzing the laws of human motion mechanics and the human-machine closed-chain motion model representing the mechanical linkage relationship between the exoskeleton and the human body, real-time collection of multi-modal data such as human electromyogram signals, joint angles, and gait cycles, inputting the data into the two models to calculate the dynamic coupling relationship between the human motion intention and the exoskeleton mechanical system, and then generating control instructions that accurately match the current human motion state and individual characteristics, such as joint assistance magnitude, motion trajectory parameters, etc., enabling the exoskeleton to dynamically adjust its actions according to human needs, realizing the coordinated synchronization of human-machine motion, and improving the pertinence, safety, and efficiency of exoskeleton assistance.

[0029] Among them, the motion coupling relationship between the exoskeleton and the human joints is characterized by the human-machine closed-chain motion model, and the control commands that conform to the individual motion laws are calculated through algorithms in combination with the human motion model, which can accurately match the body type differences (such as leg length deviation), muscle strength levels (such as quadriceps torque), and motion habits (such as abnormal gait cycles) of different users. For example, for the abnormal gait cycle of hemiplegic patients, the two models can dynamically adjust the motion trajectories and assistance timing of the exoskeleton joints to avoid the problem of mismatched training intensity caused by standardized parameters.

[0030] It should be noted that the exoskeleton control commands are not in a fixed mode, but are dynamically adjusted according to real-time data. By perceiving the human motion intention (such as electromyogram signals, joint angle changes) and providing a quantified auxiliary force, the exoskeleton assistance / resistance is accurately matched with the human motion phase (such as the swing phase and the support phase in the gait cycle), realizing "assistance on demand", avoiding the low efficiency of training or the strengthening of the compensation mode caused by a single assistance mode, and solving the core pain point of "fixed assistance mode and lack of dynamic adaptability" in traditional technologies. Especially in the clinical rehabilitation scenario, it significantly improves the safety, pertinence, and efficiency of training.

[0031] Step S104: Dynamically adjust the motion control parameters of the exoskeleton according to the control commands.

[0032] By receiving and parsing the control commands in real time, the mechanical motion parameters of the exoskeleton system are adjusted in real time and adaptively, so that the motion characteristics of the exoskeleton (such as assistance magnitude, motion trajectory, response speed, etc.) can accurately match the individual needs and current motion states of the user. The adjustable parameters of motion control mainly include mechanical parameters (such as joint range of motion, damping coefficient), control parameters (such as assistance gain, torque threshold), interaction parameters (such as voice feedback sensitivity), etc.

[0033] Based on the above introduction, this embodiment provides a complete closed-loop adaptive auxiliary control method for intelligent wearable exoskeletons from "data acquisition → model calculation → intelligent decision-making → parameter adjustment". This method obtains human walking motion data samples, constructs an accurate human motion model based on the human-machine closed-chain motion model, then real-time collects multi-modal data when the target user wears the exoskeleton, generates exoskeleton control commands for human-machine motion coordination in combination with the model, and dynamically adjusts the exoskeleton motion control parameters according to the commands. It can break through the limitations of the traditional "one-size-fits-all" mode of exoskeletons, accurately match the body type differences, muscle strength levels, and motion habits of different users, effectively improve the wearing comfort and safety, avoid problems such as muscle fatigue and skin damage caused by improper assistance, and at the same time achieve real-time and adaptive dynamic control through closed-loop feedback, enhance the adaptability of exoskeletons in different application objects and scenarios, significantly improve the pertinence and efficiency of rehabilitation training, and provide strong technical support for the intelligent transformation of traditional rehabilitation treatment modes.

[0034] Example Two: To improve the accuracy of the human motion model in analyzing the characteristics of target users, in this example, it is proposed that when constructing the human motion model, based on the obtained motion data samples and the human-machine closed-chain motion model, a general model and a difference model are constructed respectively.

[0035] Among them, the general model focuses on the common characteristics that generally exist during crowd movement, such as the approximate laws of stride length and stride frequency within a certain range when most people walk, and common situations such as the amplitude and rhythm of arm swing; the difference model focuses on exploring the differences in motion characteristics between individuals, such as the stride differences caused by different leg lengths of different people, the differences in motion speed and endurance caused by different muscle strengths, and special motion habits (such as walking with an out-toe gait), etc.

[0036] The construction of the difference model enables the exoskeleton to make personalized adjustments according to the unique motion characteristics of each user. In rehabilitation therapy, the degrees and characteristics of motor function impairments of different patients are different. Through the difference model, the exoskeleton can provide customized assistance strategies for each patient to improve the effect of rehabilitation training.

[0037] The general model can provide the basic framework of crowd movement for the exoskeleton, enabling the exoskeleton to quickly respond and cooperate with the user's movement in most cases. At the same time, the accurate analysis of individual differences by the difference model further optimizes the collaborative movement between humans and machines. In this way, the exoskeleton can better adapt to the motion habits and abilities of different users, reduce the conflicts and interferences between humans and machines, and improve the fluency and efficiency of movement.

[0038] By constructing the general model and the difference model, the control of the exoskeleton is more based on data and scientific analysis. This enables the exoskeleton to make real-time adjustments and optimizations according to actual motion data, avoiding the errors and inadaptabilities that may be brought about by the control methods based on experience or fixed parameters in traditional methods.

[0039] Example Three: In the above examples, there are no restrictions on the parameter types and adjustment methods for controlling the exoskeleton with control instructions. Different types and models of exoskeletons may have different configurations. In this example, a general adjustment method is proposed. Specifically, the dynamic output parameters, kinematic parameters, energy management parameters, and human-machine interaction parameters of the exoskeleton can be adjusted according to the control instructions.

[0040] Among them, the dynamic output parameters such as joint assist / resistance torque, assist mode (continuous / pulse type); the kinematic parameters such as joint range of motion limit, preset motion trajectory curve; the energy management parameters such as motor power distribution ratio, kinetic energy recovery threshold; the human-machine interaction parameters such as tactile feedback intensity, training mode (passive assistance / active resistance).

[0041] (1) Objectives of adjusting power output parameters: By adjusting the output power or torque of the exoskeleton drive device, match the user's movement intention with the physiological state. One regulation logic includes: Dynamically increase or decrease the joint assistance torque based on the EMG signal intensity. For example, when the EMG amplitude is lower than the threshold, automatically increase the assistance to a certain extent (such as 20%); Switch the assistance mode according to the gait phase. For example, provide joint extension assistance during the stance phase and switch to damping control during the swing phase.

[0042] (2) Objectives of adjusting kinematic parameters: Optimize the exoskeleton joint movement trajectory and range of motion to match the human biomechanical characteristics. The adjustment of kinematic parameters is based on the spatial constraints of the human-machine closed-chain motion model. One adjustment strategy for kinematic parameters can specifically include: Limit the joint range of motion to match the individual physiological limit (such as the knee joint flexion angle ≤ 100°); Correct the joint movement trajectory parameters to compensate for individual gait deviations (such as shortening the hip joint swing amplitude when the affected side step length is shortened).

[0043] (3) The existing exoskeletons are not efficient enough in energy management for a long time, resulting in a short device battery life. This method can optimize the assistance strategy and improve the energy consumption efficiency by controlling commands to regulate the energy management parameters of the exoskeleton. Objectives of adjusting energy management parameters: Optimize the exoskeleton energy distribution and recovery, and improve the battery life and energy efficiency ratio. One adjustment strategy for energy management parameters includes: Prioritize allocating 60% of the motor power to high-energy-consuming joints (such as the hip joint), and the remaining joints are dynamically allocated according to the motion contribution degree; Trigger kinetic energy recovery when the motion acceleration exceeds 1.5 m / s², and convert mechanical energy into electrical energy for storage.

[0044] (4) Objectives of adjusting human-computer interaction parameters: Improve the user operation experience and intention recognition accuracy through multi-modal feedback and mode switching. One adjustment strategy for human-computer interaction parameters includes: Output environmental risk prompts through the tactile feedback module (such as a vibration motor), and the intensity increases as the distance to the obstacle shortens; Automatically switch the training mode according to the proportion of the active force component in the EMG signal (such as switching from the passive assistance mode to the active resistance mode).

[0045] In this embodiment, only the above regulation logic is taken as an example for introduction. The different regulation logic configurations in different scenarios during the specific implementation can all refer to the introduction of this embodiment, and will not be elaborated here.

[0046] Embodiment Four: To improve the comfort of the target user when wearing the exoskeleton, before long-term wearing of the exoskeleton, the personalized parameter configuration of the initial motion control of the exoskeleton can be further adjusted according to the individual characteristics of the target user, and the exoskeleton motion control can be adjusted according to individual differences first.

[0047] As Figure 2 shown in a schematic diagram of the overall implementation of exoskeleton control. In the initial stage of the user wearing the exoskeleton for training, individual characteristic data of the target user (height, weight, joint range of motion, etc.) are obtained, and differential adjustment is performed according to the general model and difference model of human motion to generate the initial control parameters of the exoskeleton for the target user, including but not limited to: adjusting the extension length or angle range of the exoskeleton joints according to the user's leg length; adjusting the magnitude of the assistance provided by the exoskeleton during movement according to the magnitude of the user's muscle strength; considering the user's movement habits and adjusting the movement mode of the exoskeleton (rehabilitation training mode / assistance mode) to better match the user's movement rhythm, etc.

[0048] The purpose of this is to make the exoskeleton device better fit the user's body characteristics and movement characteristics, so that in the subsequent use process, the device can accurately respond to the user's movement intention, intelligently adjust the training difficulty and mode, and ensure the optimization and comfort of the training effect.

[0049] Example Five: To further improve the regulation effect and enhance the user experience, in this example, it is proposed that after dynamically adjusting the motion control parameters of the exoskeleton according to the control instruction each time, the following steps can be further executed: Step S105: After the state of the exoskeleton is adjusted, obtain the multi-modal data collected in real time; Step S106: Evaluate the adjustment effect according to the multi-modal data and generate an evaluation result; Step S107: Optimize and adjust the human-machine closed-chain motion model, human motion model, and motion control parameters according to the evaluation result.

[0050] After dynamically adjusting the motion control parameters of the exoskeleton according to the control instruction each time, continuously collecting multi-modal data and evaluating the adjustment effect can continuously obtain the actual feedback information after the exoskeleton state is adjusted. Then, according to the evaluation result, the human-machine closed-chain motion model, human motion model, and motion control parameters are optimized and adjusted to form a closed-loop optimization system, enabling the exoskeleton to continuously adapt to different users and the state changes of users at different times, and continuously improving the performance and effect. This cyclic optimization mechanism helps to timely detect problems or mismatches that occur during the operation of the exoskeleton and make timely adjustments to avoid system performance degradation or instability caused by factors such as long-term use or environmental changes, ensuring that the exoskeleton can operate stably and reliably in various situations and improving the user's experience and safety.

[0051] Embodiment Six: Corresponding to the above method embodiments, this specification also provides an embodiment of an intelligent wearable exoskeleton system, Figure 3 which shows a schematic structural diagram of an intelligent wearable exoskeleton system provided by an embodiment of this specification. As Figure 3 shown, the system mainly includes: A multi-dimensional sensing module, configured to collect motion data samples of human walking and real-time collect multi-modal data of a target user when wearing the exoskeleton; A main controller module, configured to construct a human motion model based on the human-machine closed-chain motion model according to the motion data samples; call the human motion model and the human-machine closed-chain motion model, generate an exoskeleton control instruction for human-machine motion coordination according to the multi-modal data; dynamically adjust the motion control parameters of the exoskeleton according to the control instruction; wherein, the human-machine closed-chain motion model is a motion coupling relationship model of the wearable exoskeleton and human joints constructed based on the human motion mechanism.

[0052] It should be noted that the technical solution of this wearable exoskeleton system and the technical solution of the above intelligent wearable exoskeleton adaptive auxiliary regulation method belong to the same concept. For the details not described in the technical solution of the wearable exoskeleton system device, reference can be made to the description of the technical solution of the above intelligent wearable exoskeleton adaptive auxiliary regulation method.

[0053] In one embodiment, the multi-dimensional sensing module specifically includes: a joint position sensor, a force sensor, an electromyography sensor, an accelerometer, and an environment sensor.

[0054] Among them, the joint position sensor is configured to collect joint motion curves; the force sensor is configured to monitor the force on bone movement; the electromyography sensor is configured to obtain muscle output torque and activity signals; the accelerometer is configured to detect motion acceleration parameters; the environment sensor is configured to sense environmental dynamic change data.

[0055] In one embodiment, the main controller module includes: a DSP unit and an FPGA unit.

[0056] Among them, the DSP unit is used for data analysis and processing and pattern recognition. Specifically, it is configured to receive the motion data samples and multi-modal data transmitted by the multi-dimensional sensing module, and perform signal filtering processing; perform feature processing on the filtered signals to obtain sample features and multi-modal features; construct a human motion model based on the sample features based on the human-machine closed-chain motion model; call the human motion model and the human-machine closed-chain motion model, and generate an exoskeleton control instruction for human-machine motion coordination according to the multi-modal features; The FPGA unit executes complex control algorithms to dynamically adjust the assistive force and energy management strategy of the exoskeleton, providing efficient and personalized motion assistance. Specifically, it is used to execute control algorithms and adaptive strategies according to the exoskeleton control instructions generated by the DSP unit's analysis, and dynamically adjust the motion control parameters of the exoskeleton.

[0057] In one embodiment, the intelligent wearable exoskeleton system further includes: a feedback and adjustment module.

[0058] The feedback and adjustment module cooperates with the main controller module to evaluate the adjustment effect based on the collected data and generate an evaluation result; according to the evaluation result, optimize and adjust the human-machine closed-chain motion model, human motion model, and motion control parameters.

[0059] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0060] It should be noted that for the foregoing method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of this specification are not limited by the described order of actions, because according to the embodiments of this specification, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential for the embodiments of this specification.

[0061] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0062] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not elaborate on all the details, nor do they limit the invention to only the specific implementation manners. Obviously, according to the content of the embodiments of this specification, many modifications and changes can be made. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can understand and utilize this specification well. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. An intelligent wearable exoskeleton adaptive assistance regulation method, characterized in that Including the following steps: Obtain motion data samples of human walking, and construct a human motion model based on the motion data samples and a human-machine closed-chain motion model; wherein, the human-machine closed-chain motion model is a motion coupling relationship model between a wearable exoskeleton and human joints constructed based on human motion mechanism; Real-time collect multimodal data of a target user when wearing the exoskeleton; Call the human motion model and the human-machine closed-chain motion model, and generate an exoskeleton control instruction for human-machine motion coordination according to the multimodal data; Dynamically adjust the motion control parameters of the exoskeleton according to the control instruction.

2. The method according to claim 1, wherein The constructing a human motion model based on the motion data samples and a human-machine closed-chain motion model includes: Construct a general model and a difference model of human motion based on the motion data samples and the human-machine closed-chain motion model; Wherein, the general model is used to analyze the common characteristics of population motion, and the difference model is used to analyze the motion characteristic differences between individuals.

3. The method according to claim 1, wherein The real-time collecting multimodal data of a target user when wearing the exoskeleton includes: Real-time collect the physiological parameters, motion states and environmental information of the target user when wearing the exoskeleton as the multimodal data.

4. The method according to claim 1, characterized in that The dynamically adjusting the motion control parameters of the exoskeleton according to the control instruction includes: Dynamically adjust the power output parameters, kinematic parameters, energy management parameters and human-machine interaction parameters of the exoskeleton according to the control instruction.

5. The method according to claim 1, characterized in that, Before the real-time collecting multimodal data of a target user when wearing the exoskeleton, it further includes: Perform personalized parameter configuration of initial motion control on the exoskeleton according to the individual characteristics of the target user.

6. The method according to claim 1, wherein After the dynamically adjusting the motion control parameters of the exoskeleton according to the control instruction, it further includes: After the state of the exoskeleton is adjusted, obtain the real-time collected multimodal data; Evaluate the adjustment effect according to the multimodal data and generate an evaluation result; According to the evaluation result, perform optimization adjustment on the human-machine closed-chain motion model, the human motion model and the motion control parameters.

7. An intelligent wearable exoskeleton system, characterized in that, Including: A multi-dimensional sensing module, which is used to collect motion data samples of human walking and real-time collect multimodal data of a target user when wearing the exoskeleton; A main controller module, which is used to construct a human motion model based on the motion data samples and a human-machine closed-chain motion model; call the human motion model and the human-machine closed-chain motion model, generate an exoskeleton control instruction for human-machine motion coordination according to the multimodal data; dynamically adjust the motion control parameters of the exoskeleton according to the control instruction; wherein, the human-machine closed-chain motion model is a motion coupling relationship model between a wearable exoskeleton and human joints constructed based on human motion mechanism.

8. The system according to claim 7, characterized in that, The multi-dimensional sensing module includes: A joint position sensor, which is used to collect joint motion curves; A force sensor, which is used to monitor the force condition of bone motion; An electromyography sensor, which is used to obtain muscle output torque and activity signals; An accelerometer, which is used to detect motion acceleration parameters; An environment sensor, which is used to sense environmental dynamic change data.

9. The system according to claim 7, wherein The main controller module includes: A DSP unit, configured to receive the motion data samples and the multi-modal data transmitted by the multi-dimensional sensing module, and perform signal filtering processing; perform feature processing on the filtered signal to obtain sample features and multi-modal features; construct a human body motion model based on the sample features and the human-machine closed-chain motion model; call the human body motion model and the human-machine closed-chain motion model, and generate an exoskeleton control instruction for human-machine motion coordination according to the multi-modal features. An FPGA unit, configured to execute a control algorithm and an adaptive strategy according to the exoskeleton control instruction analyzed and generated by the DSP unit, and dynamically adjust the motion control parameters of the exoskeleton.

10. The system according to claim 7, wherein It further includes: A feedback and adjustment module, configured to evaluate the adjustment effect according to the collected data and generate an evaluation result; optimize and adjust the human-machine closed-chain motion model, the human body motion model, and the motion control parameters according to the evaluation result.

Images