Lower limb exoskeleton control method and system for assisting tower climbing

By identifying tower climbing motion data and finite state machine, dynamically controlling exoskeleton power is solved, and the problem in the existing technology that the exoskeleton is difficult to provide tower climbing assistance for power maintenance operations is reduced, and labor intensity and height are reduced. Fall risk.

CN119036413AInactive Publication Date: 2024-11-29STATE GRID HUBEI EXTRA HIGH VOLTAGE CO

Patent Information

Application Number
CN202411351142.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-26
Publication Date
2024-11-29
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing power-assisted exoskeleton system is difficult to adapt to the tower climbing action needs during power maintenance operations, and the power-assisted mode is a fixed mode, which cannot intelligently identify different working conditions, and cannot effectively reduce the labor intensity and fall from high places of tower climbers. risk.

Method used

By obtaining the movement data of the wearer's tower climbing, using a preset classification algorithm to identify the current assist status, and determining the next moment assist status based on the tower climbing motion recognition finite state machine, thereby controlling the assist mode of the lower limb exoskeleton to achieve Dynamic assist control.

Benefits of technology

It reduces the labor intensity of tower climbers, improves work efficiency, reduces the risk of falling from high places caused by physical strength, and provides an intelligent assist mode that is more adaptable to climbing movements.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119036413A_ABST
    Figure CN119036413A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of exoskeletons, and discloses a lower limb exoskeleton control method and system for assisting tower climbing. The method comprises the following steps: acquiring motion data of tower climbing of a wearer; identifying a current assistance state corresponding to the motion data according to a preset classification algorithm; according to the tower climbing motion recognition finite-state machine and the current assistance state, the assistance state of the next moment is determined; and controlling the lower limb exoskeleton according to the power assisting mode corresponding to the power assisting state at the next moment. Aiming at the tower climbing work of the electric power system, different working stages are autonomously identified based on the preset classification algorithm and the tower climbing motion identification finite-state machine, and auxiliary torque generation and assistance control are performed according to the assistance state at the next moment, so that assistance is provided for tower climbing during electric power overhaul operation, and the working efficiency is improved. Therefore, the labor intensity of tower climbing personnel is reduced, the working efficiency is improved, and the high-altitude falling risk caused by physical power failure is reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of exoskeletons, and in particular to a lower limb exoskeleton control method and system for tower climbing assistance. Background Art

[0002] With the rapid development of the power industry, the requirements of industry and information industry for power supply stability and reliability are getting higher and higher, and power maintenance work is becoming more and more important. However, at present, power maintenance work mainly relies on manual tower climbing for maintenance. Operators usually need to climb the tower for maintenance and troubleshooting, which is labor-intensive and easily increases the risk of falling from heights due to physical exhaustion.

[0003] It is an appropriate strategy to reduce the burden on maintenance workers by using exoskeleton robots. As an auxiliary device, the power-assisted exoskeleton can reduce the weight of personnel and reduce labor intensity. It can provide lifting torque for power maintenance personnel and effectively reduce the probability of risks such as misoperation that may be caused by physical exertion. However, most of the existing power-assisted exoskeletons are used in the field of medical rehabilitation. It is difficult to meet the power-assisted needs of climbing towers during power maintenance operations, and it is impossible to set a power-assisted mode that adapts to tower climbing movements. In addition, the power-assisted mode of the existing power-assisted exoskeleton system is a fixed mode, which cannot intelligently identify different working conditions. Most of the modes are switched through button switches, which is not suitable for the work process of tower climbing. Summary of the invention

[0004] The main purpose of the present invention is to provide a lower limb exoskeleton control method and system for tower climbing assistance, aiming to solve at least one of the above-summarized problems.

[0005] To achieve the above object, the present invention provides a lower limb exoskeleton control method for tower climbing assistance, comprising:

[0006] Obtain the wearer's motion data of tower climbing;

[0007] Identify the current power assist state corresponding to the motion data according to a preset classification algorithm;

[0008] Determine the power-assisting state at the next moment according to the tower climbing motion identification finite state machine and the current power-assisting state;

[0009] The lower limb exoskeleton is controlled according to the power assist mode corresponding to the power assist state at the next moment.

[0010] In some embodiments, obtaining the wearer's tower climbing motion data includes:

[0011] Collect the angle, angular velocity and angular acceleration of the wearer's walking joints;

[0012] Using the angle, the angular velocity and the angular acceleration as joint motion information;

[0013] Collecting interaction force information between the lower limb exoskeleton and the wearer;

[0014] Motion data is generated according to the joint motion information and the interaction force information.

[0015] In some embodiments, the identifying the current power assist state corresponding to the motion data according to a preset classification algorithm includes:

[0016] Constructing a motion data set according to the collected motion data;

[0017] Establishing a data vector based on the motion data set;

[0018] Inputting the data vector into a preset classification algorithm to output a classification result;

[0019] The current power assist state is determined according to the classification result.

[0020] In some embodiments, the determining the power-assisting state at the next moment according to the tower climbing motion identification finite state machine and the current power-assisting state includes:

[0021] Establish a tower climbing motion recognition finite state machine;

[0022] An activation function for determining whether a state is switched according to the collected motion data;

[0023] Based on the tower climbing motion recognition finite state machine, the power assisting state at the next moment is obtained according to the current power assisting state and the activation function.

[0024] In some embodiments, the method further comprises:

[0025] The tower climbing action and the power-assisting state of the lower limb exoskeleton are classified to obtain multiple types of power-assisting states; wherein the power-assisting states include a flat ground state, an ascending state, a holding state, and a descending state;

[0026] Formulate finite motion state conversion relations according to the plurality of types of power-assist states;

[0027] Accordingly, the tower climbing motion identification finite state machine obtains the power assist state at the next moment according to the current power assist state and the activation function, including:

[0028] Based on the tower climbing motion identification finite state machine, the power assisting state at the next moment is obtained according to the finite motion state conversion relationship, the current power assisting state and the activation function.

[0029] In some embodiments, obtaining the power assist state at the next moment according to the finite motion state conversion relationship, the current power assist state and the activation function includes:

[0030] When the activation function is state switching and the current power-assisting state is a holding state, switching the current power-assisting state to one of an ascending state, a descending state and a flat ground state;

[0031] When the activation function is state switching and the current power-assisting state is an ascending state, switching the current power-assisting state to a maintaining state;

[0032] When the activation function is state switching and the current power-assisting state is a descending state, switching the current power-assisting state to a flat ground state;

[0033] When the activation function is state switching and the current power-assisting state is a flat ground state, the current power-assisting state is switched to an ascending state.

[0034] In some embodiments, the ascending state includes a support phase, a flexion phase, a pedaling phase, and a power assist phase; wherein the switching conditions between the ascending state and the holding state include:

[0035] When the activation function is state switching and the current power-assisting state is in the support phase or the lever-stepping phase of the ascending state, switching the current power-assisting state to the holding state;

[0036] When the activation function is state switching and the current power-assisting state is a holding state, the current power-assisting state is switched to a flexion phase or a power-assisting phase of an ascending state.

[0037] In some embodiments, controlling the lower limb exoskeleton according to the power assist mode corresponding to the power assist state at the next moment includes:

[0038] Determining a power assist strategy according to the power assist state at the next moment;

[0039] determining a torque curve according to the power assist strategy;

[0040] Transmitting motion data corresponding to the torque curve to an output function of the tower climbing motion recognition finite state machine to obtain an output torque;

[0041] The output torque is transmitted to a controller to control the motor operation of the lower limb exoskeleton.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes a lower limb exoskeleton control system for tower climbing assistance, comprising:

[0043] A collection module, used to obtain the wearer's motion data of tower climbing;

[0044] A classification module, used for identifying a current power-assisting state corresponding to the motion data according to a preset classification algorithm;

[0045] An identification module, used for determining the power-assisting state at the next moment according to the tower climbing motion identification finite state machine and the current power-assisting state;

[0046] The control module is used to control the lower limb exoskeleton according to the power-assistance mode corresponding to the power-assistance state at the next moment.

[0047] In some embodiments, the system further comprises: a power assist classification module, for classifying the tower climbing action and the power assist state of the lower limb exoskeleton to obtain multiple types of power assist states; wherein the power assist states include a flat ground state, an ascending state, a holding state, and a descending state;

[0048] Formulate finite motion state conversion relations according to the plurality of types of power-assist states;

[0049] Correspondingly, the identification module is specifically configured to obtain the power assisting state at the next moment based on the tower climbing motion identification finite state machine according to the finite motion state conversion relationship, the current power assisting state and the activation function.

[0050] The present invention provides a lower limb exoskeleton control method for tower climbing assistance, including: obtaining motion data of the wearer's tower climbing; identifying the current power-assisting state corresponding to the motion data according to a preset classification algorithm; determining the power-assisting state at the next moment according to a tower climbing motion identification finite state machine and the current power-assisting state; and controlling the lower limb exoskeleton according to the power-assisting mode corresponding to the power-assisting state at the next moment. In the present invention, for the tower climbing work of the power system, based on the preset classification algorithm and the tower climbing motion identification finite state machine, different working stages (power-assisting states) can be autonomously identified, and auxiliary torque is generated and power-assisting control is performed according to the power-assisting state at the next moment, thereby providing power assistance for climbing the tower during power maintenance operations, thereby reducing the labor intensity of tower climbers, improving work efficiency, and reducing the risk of falling from heights due to lack of physical strength, solving the problems that the existing power-assisting exoskeletons are difficult to provide power assistance for climbing towers during power maintenance operations, and the power-assisting mode is not suitable for climbing movements. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a flow chart of an embodiment of a lower limb exoskeleton control method for tower climbing assistance of the present invention;

[0052] Figure 2 A schematic diagram of the lower limb exoskeleton structure involved in an embodiment of the present invention;

[0053] Figure 3It is a schematic diagram of the lower limb exoskeleton tower climbing auxiliary control algorithm involved in the embodiment of the present invention;

[0054] Figure 4 A state transition diagram of a tower climbing motion identification finite state machine involved in an embodiment of the present invention;

[0055] Figure 5 A schematic diagram of switching conditions between a rising state and a holding state involved in an embodiment of the present invention;

[0056] Figure 6 A schematic diagram of a multi-class SVM support vector machine classification model involved in an embodiment of the present invention;

[0057] Figure 7 It is a structural block diagram of an embodiment of a lower limb exoskeleton control system for tower climbing assistance of the present invention;

[0058] Figure 8 The present invention is a schematic diagram of the structure of an electronic device in a hardware operating environment according to an embodiment of the present invention.

[0059] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] It should be noted that all directional indications in the embodiments of the present invention (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0062] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in the field to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0063] The present invention provides a lower limb exoskeleton control method and system for tower climbing assistance.

[0064] The embodiment of the present invention provides a lower limb exoskeleton control method for tower climbing assistance, referring to Figure 1 , Figure 1 The figure is a flow chart of an embodiment of a lower limb exoskeleton control method for tower climbing assistance according to the present invention.

[0065] like Figure 1 As shown, the lower limb exoskeleton control method for tower climbing assistance includes:

[0066] Step S100: Acquiring the wearer's tower climbing motion data;

[0067] Step S200: identifying the current power-assisting state corresponding to the motion data according to a preset classification algorithm;

[0068] Step S300: determining the power assist state at the next moment according to the tower climbing motion recognition finite state machine and the current power assist state;

[0069] Step S400: controlling the lower limb exoskeleton according to the power assist mode corresponding to the power assist state at the next moment.

[0070] It should be noted that the execution subject in this embodiment may be an electronic device, which may be a computer device with data processing functions, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment, a computer device (such as a processor of a lower limb exoskeleton) is used as an example for explanation.

[0071] It can be understood that this embodiment uses a lower limb exoskeleton (lower limb exoskeleton robot) for tower climbing as an example to illustrate the process of the control method. The lower limb exoskeleton is used to execute the lower limb exoskeleton control method for tower climbing assistance as described in the embodiment of the present invention.

[0072] For example, Figure 2 As shown, the lower limb exoskeleton for tower climbing includes a backboard control module (I), a waist structure (II), a hip joint mechanism (III), and a thigh part (IV); the backboard control module (I) integrates a processor (such as Raspberry Pi 4b), a battery, a voltage divider, and a TTL to USB serial port module; the waist structure (II) is provided with an adjustable structure connected to the backboard; the hip joint mechanism (III) outputs auxiliary torque through a motor direct drive; the thigh part (IV) is provided with an elastic strap connected to the wearer's thigh.

[0073] The following combination Figures 1 to 4 The specific process of the lower limb exoskeleton control method for tower climbing assistance is described.

[0074] like Figure 3 As shown, in actual application, the tower climbing actions of the workers and the exoskeleton power-assisting states during the power maintenance work are classified according to the finite state machine (FSM), and multiple types of power-assisting states are obtained; among them, the power-assisting states include flat ground state, ascending state, holding state and descending state; and finite motion state conversion relationships are formulated according to the multiple types of power-assisting states.

[0075] For example, Figure 4 As shown, the power-assisting states of the lower limb exoskeleton can be divided into four categories: flat ground state, ascending state, holding state, and descending state. Specifically, flat ground state: the wearer has not yet started climbing the tower, and the power-assisting mode of the lower limb exoskeleton is to maintain a zero torque output state; ascending state: the wearer climbs up the tower, and the power-assisting mode of the lower limb exoskeleton is to assist the lower limbs in exerting force; holding state: the wearer temporarily stops during the upward climbing process, and the power-assisting mode of the lower limb exoskeleton is to assist the fixed action in maintaining force; descending state: the wearer descends along the tower, and the power-assisting mode of the lower limb exoskeleton is to maintain a zero damping output state to offset the friction of the movement.

[0076] It is understandable that the lower limb exoskeleton is in only one power-assisting state at any one time, e.g. Figure 4 As shown in the figure, the finite motion state transition relationship includes: the ascending state and the holding state are mutually reachable, the holding state and the descending state are mutually reachable; the ascending state and the descending state are not mutually reachable; the flat ground state can be transferred to the ascending state; the descending state can be transferred to the flat ground state; and the holding state can be transferred to the flat ground state. Among them, mutual access means two mutually reachable states.

[0077] In one embodiment, obtaining motion data of a wearer climbing a tower includes: collecting the angle, angular velocity, and angular acceleration of the wearer's walking joints; using the angle, the angular velocity, and the angular acceleration as joint motion information; collecting interaction force information between a lower limb exoskeleton and the wearer; and generating motion data based on the joint motion information and the interaction force information.

[0078] Specifically, the lower limb exoskeleton includes data acquisition sensors such as an inertial measurement unit and a force sensor. The inertial measurement unit is used to continuously collect joint motion information of the wearer during several groups of climbing processes, and the force sensor is used to collect interaction force information between the lower limb exoskeleton and the wearer.

[0079] Exemplarily, two inertial measurement units (IMUs) are installed on the lower limb exoskeleton, and the IMUs are fixed to the thighs with elastic bandages to collect the angles, angular velocities, and angular accelerations of the wearer's walking joints. Eight force sensors, such as force-sensitive resistors (FSRs), are provided at the part where the lower limb exoskeleton and the wearer's thighs are in contact, with four force-sensitive resistors provided on each of the left and right legs to detect the interaction force between the exoskeleton and the wearer. A motion data set M is established based on the above-collected angle, angular velocity, angular acceleration, and interaction force data for subsequent identification of the power-assistance state of the lower limb exoskeleton.

[0080] It should be noted that the number and specific types of collection devices for collecting motion data can be set according to actual conditions, and this embodiment does not limit this.

[0081] In one embodiment, the current power assistance state corresponding to the motion data is identified according to a preset classification algorithm, including: constructing a motion data set based on the collected motion data; establishing a data vector based on the motion data set; inputting the data vector into a preset classification algorithm to output a classification result; and determining the current power assistance state according to the classification result.

[0082] Specifically, the motion data set M is:

[0083] M={θ l ,θ r ,ω l ,ω r ,a l ,a r ,τ 1~c}

[0084] Among them, θ is the hip joint angle, ω is the hip joint angular velocity, α is the hip joint angular acceleration, τ 1~c It represents the interaction force signal detected by c sensors, the subscript l represents the left leg, and the subscript r represents the right leg.

[0085] Exemplarily, two inertial measurement units and c sensors (e.g., 8 force-sensitive resistors) are installed on the lower limb exoskeleton to collect data such as angle, angular velocity, angular acceleration, and interaction force and establish a motion data set M. At this time, the motion data set M is:

[0086] M={θ l ,θ r ,ω l ,ω r ,al ,a r ,τ 1~8}

[0087] Among them, τ 1~8 Represents the interaction force detected by 8 force-sensitive resistors.

[0088] Exemplarily, a data vector is established based on the joint motion data (angle, angular velocity, angular acceleration) and the interaction force data as the input of the preset classification algorithm, and the output is the classification label of different power-assisting states, for example, label 0 represents the flat ground state, label 1 represents the ascending state, label 2 represents the holding state, and label 3 represents the descending state. The preset classification algorithm includes but is not limited to the SVM (support vector machine classification) algorithm, the NBC (naive Bayes classification) algorithm, the LR (logistic regression) algorithm, the decision tree algorithm, the KNN (K nearest neighbor) algorithm, and the ANN (artificial neural network) algorithm.

[0089] In one example, the SVM classification algorithm is used as an example for explanation: a data vector is input into the SVM classification algorithm, and hyperplane partitioning is performed to output classification labels of different states.

[0090] Specifically, the steps of classification using the SVM classification algorithm include:

[0091] First, build a multi-class SVM support vector machine classification model. Since the embodiment of the present invention divides the power-assisting state of the lower limb exoskeleton into four categories (flat state, ascending state, holding state, descending state), it is necessary to use a multi-class ovo SVM classifier for classification to convert the multi-classification problem into multiple binary classification problems. Figure 6 The multi-class SVM support vector machine classification model shown uses 6 SVM binary classification models to divide the data set into 4 different power states.

[0092] Second, collect and classify motion data and calibrate feature values. The motion data includes the angle, angular velocity, angular acceleration and force sensing information of the left and right leg hip joints. Calibrate the feature values ​​of the motion data at each moment. For example, when the lower limb exoskeleton is in the rising state S1, the feature value is 1, and so on. The motion data and feature values ​​are divided into a training data set and a validation data set.

[0093] Third, the multi-class SVM support vector machine classification model obtains the motion data set and performs hyperplane division. The basic division formula is:

[0094] 1-y i (w T x i +b)≤0,i=1,2,···,n

[0095]

[0096] Where w=(w1,w2,...w n ) represents the normal vector of the plane; (x i ,y i ) is the sample space coordinate, which is the data space after the motion data is kernelized; b is the constant coefficient. The multi-class SVM support vector machine classification model divides the data into two categories through a hyperplane. In order to obtain a more appropriate and accurate division plane, the multi-class SVM support vector machine classification model needs to be trained to obtain better classification results. The training data set is input into the multi-class SVM support vector machine classification model. The input is the kernelized motion data, and the output is the classification feature. The training result is the continuous optimization of the model parameters to obtain the minimum objective function. After the training is completed, the verification data set is input into the model. If the verification data can be correctly classified, the training of the multi-class SVM support vector machine classification model is completed.

[0097] Fourth, the trained multi-class SVM support vector machine classification model is installed on the processor of the lower limb exoskeleton, and the joint motion data (angle, angular velocity, angular acceleration) and interaction force data collected at each moment are classified by multi-class SVM support vector machine to obtain the current motion state, that is, the current assistance state.

[0098] In one embodiment, the power assist state at the next moment is determined based on the tower climbing motion recognition finite state machine and the current power assist state, including: establishing a tower climbing motion recognition finite state machine; determining an activation function for determining whether the state is switched based on the collected motion data; and obtaining the power assist state at the next moment based on the tower climbing motion recognition finite state machine according to the current power assist state and the activation function.

[0099] In one embodiment, the method further includes: classifying the tower climbing action and the power-assisting state of the lower limb exoskeleton to obtain multiple types of power-assisting states; wherein the power-assisting states include a flat ground state, an ascending state, a holding state, and a descending state; formulating a finite motion state conversion relationship according to the multiple types of the power-assisting states; accordingly, based on the tower climbing motion identification finite state machine, obtaining the power-assisting state at the next moment according to the current power-assisting state and the activation function, including: based on the tower climbing motion identification finite state machine, obtaining the power-assisting state at the next moment according to the finite motion state conversion relationship, the current power-assisting state, and the activation function.

[0100] Specifically, a tower climbing motion recognition finite state machine is established to perform lower limb exoskeleton motion recognition for tower climbing. Exemplarily, the tower climbing motion recognition finite state machine is:

[0101] F i ={M i ,Ωi ,S i ,δ i ,σ i}

[0102] Where Ω is the output function; S represents the state set, which includes the flat state (S0), the rising state (S1), the holding state (S2) and the descending state (S3); δ represents the activation function of whether the state is switched, σ represents the controller command, and the subscript i represents the state time.

[0103] For example, the activation function δ (e.g., 0 or 1) of whether the state is switched can be calculated by using the angular acceleration and other data in the motion data set M. i The next moment power state can be obtained by adding the activation function δ. When the activation function δ is expressed as a state switch (for example, 1), the current power state S i Switch to the next power state; when the activation function δ indicates no state switching (e.g. 0), keep the current power state S i .

[0104] In one embodiment, the assist state at the next moment is obtained according to the finite motion state conversion relationship, the current assist state and the activation function, including: when the activation function is a state switching and the current assist state is a holding state, the current assist state is switched to one of an ascending state, a descending state and a flat ground state; when the activation function is a state switching and the current assist state is an ascending state, the current assist state is switched to a holding state; when the activation function is a state switching and the current assist state is a descending state, the current assist state is switched to a flat ground state; when the activation function is a state switching and the current assist state is a flat ground state, the current assist state is switched to an ascending state.

[0105] For example, Figure 4 As shown in the figure, the finite motion state transition relationship includes: the ascending state and the holding state are mutually reachable, the holding state and the descending state are mutually reachable; the ascending state and the descending state are not mutually reachable; the flat ground state can be transferred to the ascending state; the descending state can be transferred to the flat ground state; and the holding state can be transferred to the flat ground state. Among them, mutual access means two mutually reachable states.

[0106] In one embodiment, the ascending state includes a support stage, a flexion stage, a lever-operating stage and an assisting stage; wherein the switching conditions between the ascending state and the maintaining state include: when the activation function is a state switching and the current assisting state is the support stage or the lever-operating stage of the ascending state, the current assisting state is switched to the maintaining state; when the activation function is a state switching and the current assisting state is the maintaining state, the current assisting state is switched to the flexion stage or the assisting stage of the ascending state.

[0107] Specifically, the ascending state of the lower limb exoskeleton can be divided into four stages, including the support stage, the flexion stage, the stepping on the pole stage and the power-assisting stage. For example, in the support stage: the legs stand upright and step on the foot spikes to support the human body to stand. At this time, the lower limb exoskeleton robot does not need power assistance; the flexion stage: the thigh flexes to find the next foot spike position. At this time, the lower limb exoskeleton robot is in zero damping mode; the stepping on the pole stage: at this time, the human body has just stepped on the foot spike, which is a short time stage used to divide the ascending and power-assisting stages; the power-assisting stage: the thigh stretches to drive the human body to climb. At this time, the lower limb exoskeleton robot needs to provide downward power assistance to assist the human body in climbing. When the human body is stretched to a certain degree, the thigh has basically achieved verticality, the exoskeleton power-assisting effect disappears, and the zero-force mode is performed until it returns to the support stage.

[0108] Specifically, the switching conditions between the rising state and the holding state of the lower limb exoskeleton robot are as follows: Figure 5 Reference Figure 5 In the support phase and the pole-stepping phase, you can connect to the holding state to change the position of the safety buckle and adjust the human body posture; the holding state can be connected to the flexion phase or the assist phase to perform the human body climbing movement.

[0109] In one embodiment, the lower limb exoskeleton is controlled according to the assisting mode corresponding to the assisting state at the next moment, including: determining an assisting strategy according to the assisting state at the next moment; determining a torque curve according to the assisting strategy; transmitting motion data corresponding to the torque curve to the output function of the tower climbing motion recognition finite state machine to obtain an output torque; transmitting the output torque to a controller to control the motor operation of the lower limb exoskeleton.

[0110] It can be understood that the lower limb exoskeleton is controlled to apply different assisting torques in different assisting modes according to the motion state of the tower climbing motion recognition finite state machine (ie, the assisting state at the next moment).

[0111] Specifically, the assist strategy and its torque curve corresponding to the assist state at the next moment are determined, and the motion data determined according to the torque curve is transmitted to the output function Ω of the tower climbing motion recognition finite state machine to obtain the output torque of the lower limb exoskeleton, and transmitted to the controller command σ, and the motor operation of the lower limb exoskeleton is controlled according to the controller command σ.

[0112] Specifically, flat ground state: the wearer has not yet started tower climbing, and the lower limb exoskeleton maintains a zero torque output state, at which time the motor does not apply torque; ascending state: the wearer climbs up the tower, and the lower limb exoskeleton adopts a closed-loop torque control method, and divides the ascending state into four stages (support stage, flexion stage, pole-stepping stage, and assisting stage) according to the angle and speed information of the human body. In the assisting stage, the motor outputs a downward torque, and feedback control is used to assist the lower limbs in exerting force; holding state: the wearer temporarily stops during the ascending process, and the lower limb exoskeleton adopts a position control method to maintain the current angle of the lower limb exoskeleton and assist in maintaining force in fixed movements; descending state: the wearer descends along the tower, and the lower limb exoskeleton maintains a zero damping output state. At this time, the output torque of the motor is less than that of the ascending state, and is only used to offset movement friction and damping.

[0113] It should be noted that the lower limb exoskeleton control method for tower climbing assistance described in this embodiment can be used for lower limb exoskeleton robots for tower climbing to perform power assistance state identification and power assistance control. This method collects the wearer's tower climbing motion data with the help of a sensor system (such as an inertial measurement unit, a force-sensitive resistor), divides and identifies the wearer's different working states through a preset classification algorithm such as a support vector machine SVM, and controls the exoskeleton's power assistance state at the next moment through a finite state machine FSM, i.e., a tower climbing motion identification finite state machine, to provide assistance for climbing towers during power maintenance operations, thereby reducing the labor intensity of tower climbing workers and improving work efficiency.

[0114] The present embodiment provides a lower limb exoskeleton control method for tower climbing assistance, including: obtaining the wearer's tower climbing motion data; identifying the current power assist state corresponding to the motion data according to a preset classification algorithm; determining the power assist state at the next moment according to the tower climbing motion identification finite state machine and the current power assist state; and controlling the lower limb exoskeleton according to the power assist mode corresponding to the power assist state at the next moment. In the present embodiment, for the tower climbing work of the power system, based on the preset classification algorithm and the tower climbing motion identification finite state machine, different working stages (power assist states) can be autonomously identified, and auxiliary torque is generated and power assist control is performed according to the power assist state at the next moment, thereby providing power assist for climbing the tower during power maintenance operations, thereby reducing the labor intensity of tower climbers, improving work efficiency, and reducing the risk of falling from heights due to lack of physical strength, solving the problems that the existing power assist exoskeleton is difficult to provide power assist for climbing the tower during power maintenance operations, and the power assist mode is not suitable for climbing movements.

[0115] In addition, an embodiment of the present invention further proposes a storage medium, on which is stored a lower limb exoskeleton control program for tower climbing assistance. When the lower limb exoskeleton control program for tower climbing assistance is executed by a processor, the steps of the lower limb exoskeleton control method for tower climbing assistance as described above are implemented.

[0116] Reference Figure 7 , Figure 7 The structure block diagram of an embodiment of a lower limb exoskeleton control system for tower climbing assistance of the present invention.

[0117] like Figure 7 As shown, the lower limb exoskeleton control system for tower climbing assistance includes:

[0118] The acquisition module 10 is used to obtain the motion data of the wearer climbing the tower;

[0119] A classification module 20, for identifying a current power-assisting state corresponding to the motion data according to a preset classification algorithm;

[0120] An identification module 30, for determining a power-assisting state at a next moment according to a tower climbing motion identification finite state machine and the current power-assisting state;

[0121] The control module 40 is used to control the lower limb exoskeleton according to the power assist mode corresponding to the power assist state at the next moment.

[0122] In one embodiment, the identification module 30 is specifically used to establish a tower climbing motion identification finite state machine; determine an activation function for determining whether a state is switched based on the collected motion data; and obtain the power assist state at the next moment based on the tower climbing motion identification finite state machine according to the current power assist state and the activation function.

[0123] In one embodiment, the system also includes: the system also includes: an assist classification module, which is used to classify the tower climbing action and the assist state of the lower limb exoskeleton to obtain multiple types of assist states; wherein the assist states include flat ground state, rising state, holding state and descending state; a finite motion state conversion relationship is formulated according to the multiple types of assist states; accordingly, the identification module 30 is specifically used to obtain the assist state at the next moment based on the finite motion state conversion relationship, the current assist state and the activation function based on the tower climbing action identification finite state machine.

[0124] It should be noted that the present embodiment is explained by taking a lower limb exoskeleton (lower limb exoskeleton robot) for tower climbing as an example. The lower limb exoskeleton is equipped with a lower limb exoskeleton control system for tower climbing assistance as described in the present embodiment. The system collects the motion data of the wearer's tower climbing with the help of a sensing system (such as an inertial measurement unit, a force-sensitive resistor), divides and identifies the different working states of the wearer through a preset classification algorithm such as a support vector machine SVM, and controls the next moment's assistance state of the exoskeleton through a finite state machine FSM, i.e., a tower climbing motion identification finite state machine, to provide assistance for climbing the tower during power maintenance operations, thereby reducing the labor intensity of tower climbing workers and improving work efficiency.

[0125] In this embodiment, a lower limb exoskeleton control system for tower climbing assistance is proposed. Through this system, for tower climbing work, based on a preset classification algorithm and a tower climbing motion recognition finite state machine, different working stages (power-assisting states) can be autonomously identified, and auxiliary torque is generated and power-assisting control is performed according to the power-assisting state at the next moment, thereby providing assistance for climbing the tower during power maintenance operations, thereby reducing the labor intensity of tower climbers, improving work efficiency, and reducing the risk of falling from heights due to physical exhaustion. The problems of existing power-assisting exoskeletons being difficult to provide assistance for climbing towers during power maintenance operations and the power-assisting mode being unsuitable for climbing movements are solved.

[0126] It should be noted that the technical details that are not described in detail in the embodiment of the lower limb exoskeleton control system for tower climbing assistance can be referred to the lower limb exoskeleton control method for tower climbing assistance as described above provided in any embodiment of the present invention, and will not be repeated here.

[0127] Reference Figure 8 , Figure 8 The figure is a schematic diagram of the structure of an electronic device of the hardware operating environment involved in the embodiment of the present invention.

[0128] like Figure 8As shown, the electronic device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM memory) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0129] Those skilled in the art will understand that Figure 8 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0130] like Figure 8 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a lower limb exoskeleton control program for tower climbing assistance.

[0131] exist Figure 8 In the electronic device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the electronic device of the present invention can be set in the electronic device, and the electronic device calls the lower limb exoskeleton control program for tower climbing assistance stored in the memory 1005 through the processor 1001, and executes the lower limb exoskeleton control method for tower climbing assistance provided in the embodiment of the present invention.

[0132] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0133] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0134] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0135] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0136] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0137] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A lower limb exoskeleton control method for tower climbing assistance, characterized in that: include: Obtain the wearer's motion data of tower climbing; Identify the current power assist state corresponding to the motion data according to a preset classification algorithm; Determine the power-assisting state at the next moment according to the tower climbing motion identification finite state machine and the current power-assisting state; The lower limb exoskeleton is controlled according to the power assist mode corresponding to the power assist state at the next moment.

2. The method according to claim 1, characterized in that The step of obtaining the wearer's tower climbing motion data includes: Collect the angle, angular velocity and angular acceleration of the wearer's walking joints; Using the angle, the angular velocity and the angular acceleration as joint motion information; Collecting interaction force information between the lower limb exoskeleton and the wearer; Motion data is generated according to the joint motion information and the interaction force information.

3. The method according to claim 1, characterized in that The identifying the current power-assisting state corresponding to the motion data according to a preset classification algorithm includes: Constructing a motion data set according to the collected motion data; Establishing a data vector based on the motion data set; Inputting the data vector into a preset classification algorithm to output a classification result; The current power assist state is determined according to the classification result.

4. The method according to claim 1, characterized in that The determining the power-assisting state at the next moment according to the tower climbing motion identification finite state machine and the current power-assisting state includes: Establish a tower climbing motion recognition finite state machine; An activation function for determining whether a state is switched according to the collected motion data; Based on the tower climbing motion recognition finite state machine, the power assisting state at the next moment is obtained according to the current power assisting state and the activation function.

5. The method according to claim 4, characterized in that The method further comprises: The tower climbing action and the power-assisting state of the lower limb exoskeleton are classified to obtain multiple types of power-assisting states; wherein the power-assisting states include a flat ground state, an ascending state, a holding state, and a descending state; Formulate finite motion state conversion relations according to the plurality of types of power-assist states; Accordingly, the tower climbing motion identification finite state machine obtains the power assist state at the next moment according to the current power assist state and the activation function, including: Based on the tower climbing motion identification finite state machine, the power assisting state at the next moment is obtained according to the finite motion state conversion relationship, the current power assisting state and the activation function.

6. The method according to claim 5, characterized in that The obtaining the power-assisting state at the next moment according to the finite motion state conversion relationship, the current power-assisting state and the activation function includes: When the activation function is state switching and the current power-assisting state is a holding state, switching the current power-assisting state to one of an ascending state, a descending state and a flat ground state; When the activation function is state switching and the current power-assisting state is an ascending state, switching the current power-assisting state to a maintaining state; When the activation function is state switching and the current power-assisting state is a descending state, switching the current power-assisting state to a flat ground state; When the activation function is state switching and the current power-assisting state is a flat ground state, the current power-assisting state is switched to an ascending state.

7. The method according to claim 5, characterized in that The ascending state includes a support phase, a flexion phase, a pedaling phase, and a power assist phase; wherein the switching conditions between the ascending state and the holding state include: When the activation function is state switching and the current power-assisting state is in the support phase or the lever-stepping phase of the ascending state, switching the current power-assisting state to the holding state; When the activation function is state switching and the current power-assisting state is a holding state, the current power-assisting state is switched to a flexion phase or a power-assisting phase of an ascending state.

8. The method according to any one of claims 1 to 7, characterized in that The controlling of the lower limb exoskeleton according to the power assist mode corresponding to the power assist state at the next moment includes: Determining a power assist strategy according to the power assist state at the next moment; determining a torque curve according to the power assist strategy; Transmitting motion data corresponding to the torque curve to an output function of the tower climbing motion recognition finite state machine to obtain an output torque; The output torque is transmitted to a controller to control the motor operation of the lower limb exoskeleton.

9. A lower limb exoskeleton control system for tower climbing assistance, characterized in that: include: A collection module, used to obtain the wearer's motion data of tower climbing; A classification module, used for identifying a current power-assisting state corresponding to the motion data according to a preset classification algorithm; An identification module, used for determining the power-assisting state at the next moment according to the tower climbing motion identification finite state machine and the current power-assisting state; The control module is used to control the lower limb exoskeleton according to the power-assistance mode corresponding to the power-assistance state at the next moment.

10. The system according to claim 9, characterized in that The system further comprises: a power-assistance classification module, which is used to classify the tower climbing action and the power-assistance state of the lower limb exoskeleton to obtain multiple types of power-assistance states; wherein the power-assistance states include a flat ground state, an ascending state, a holding state, and a descending state; Formulate finite motion state conversion relations according to the plurality of types of power-assist states; Correspondingly, the identification module is specifically configured to obtain the power assisting state at the next moment based on the tower climbing motion identification finite state machine according to the finite motion state conversion relationship, the current power assisting state and the activation function.

Citation Information

Patent Citations

  • Motion state recognition method of upper limb assistance exoskeleton robot

    CN113400309A

  • Unpowered exoskeleton for assisting tower climbing

    CN115556073A

  • Non-contact-based lower limb knee joint exoskeleton assisting method and system and computer readable medium

    CN116276918A

  • Power-assisted exoskeleton robot motion recognition method based on state machine

    CN118269058A

  • Active exoskeleton convenient to climb

    CN217992510U

Cited By

  • Power assisting method and device for assisting iron tower climbing

    CN120595575A