Robotic-based rehabilitation method and system

Abstract

The embodiment of the present application relates to the technical field of robots, and discloses a rehabilitation method and system based on a robot. The rehabilitation method comprises the following steps: receiving a mode selection result of a user, wherein the mode comprises a passive training mode and an active training mode; when the passive training mode is adopted, a dragging torque, a joint position and a joint speed are acquired in real time in response to a dragging force applied on the robot by an operator; a gravity compensation torque is determined based on the joint position, a friction compensation torque is determined based on the joint speed, and a command torque is obtained according to the gravity compensation torque, the friction compensation torque and the dragging torque; and the robot is controlled to perform a passive training rehabilitation operation through the command torque. According to the scheme of the embodiment of the present application, mechanical resistance is eliminated based on the gravity / friction compensation of dynamics in the passive training mode, the dragging torque is superimposed to realize smooth dragging, and the physical consumption of the operator is significantly reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of robot technology, in particular to a robot-based rehabilitation method and system. BACKGROUND

[0002] With the rapid development of robot technology, its application in the field of medical rehabilitation is increasingly widespread. Rehabilitation robots can assist patients in standardized and repetitive exercise training, effectively alleviate the workload of therapists, and improve the efficiency and consistency of rehabilitation training. In particular, in the field of neurological rehabilitation and motor function reconstruction, robot-assisted training shows significant advantages.

[0003] Currently, existing rehabilitation robot systems mostly use pre-programmed trajectory control methods to guide patients to move along fixed paths. However, such systems lack real-time sensing and response capabilities for human-robot interaction forces, making it difficult to adapt to individual differences and real-time state changes of different patients. In passive training mode, most systems fail to fully compensate for the effects of robot gravity and friction, resulting in significant drag and unnatural movement, and poor patient experience. SUMMARY

[0004] To address the above-mentioned defects, the embodiments of the present application disclose a robot-based rehabilitation method and system. In passive training mode, gravity / friction compensation based on dynamics eliminates mechanical resistance, and superimposes drag torque to achieve smooth dragging, significantly reducing the physical exertion of the operator.

[0005] The first aspect of the embodiments of the present application discloses a robot-based rehabilitation method, comprising:

[0006] receiving a mode selection result of a user, the mode including a passive training mode and an active training mode;

[0007] When the passive training mode is adopted, in response to the drag force applied by the operator on the robot, the drag torque, joint position and joint velocity are obtained in real time;

[0008] determining a gravity compensation torque based on the joint position, determining a friction compensation torque based on the joint velocity, and obtaining a command torque according to the gravity compensation torque, the friction compensation torque and the drag torque;

[0009] controlling the robot to perform passive training rehabilitation operations through the command torque.

[0010] Through the selection of passive and active training modes, the needs of patients at different rehabilitation stages can be met. Generally, early users can perform joint range of motion training through the passive mode, and later users can perform muscle strength and coordination training through the active mode, greatly expanding the applicable population and rehabilitation period of the device.

[0011] In the passive mode, by calculating and compensating the gravity and friction in real time, the resistance caused by the robot body to the movement is greatly eliminated, so that the operator feels light and smooth when dragging the robot arm, as if moving a weightless object, which improves the naturalness and comfort of human-machine interaction.

[0012] It should be noted that the user is generally a patient, or a patient family member, a therapist or a physiotherapist who performs the mode selection under the guidance of the therapist or physiotherapist; the operator can also be any of the above personnel.

[0013] As an optional implementation, in the first aspect of the embodiment of the present application, the gravity compensation torque of each joint is determined based on the joint position, comprising:

[0014] The gravity compensation torque of each joint is calculated through a dynamic model:

[0015]

[0016] Alternatively, the gravity compensation torque of each joint is obtained through a recursive Newton-Euler algorithm;

[0017] wherein, is the gravity compensation torque of the i th joint, n is the total number of joints, G is a gravity function, is a joint position vector, is the position Jacobian matrix of the k th link mass center, T is the transpose of the matrix, is the mass of the k th link, and g is the acceleration of gravity.

[0018] Using the dynamic model, the actual structure parameters of the robot can be accurately modeled, different models can be adapted, and the gravity compensation torque required by each joint can be accurately calculated, especially for complex configuration robots. The calculation complexity of the recursive Newton-Euler algorithm is greatly reduced, the calculation speed is fast, and it is particularly suitable for real-time systems and meets the real-time control requirements.

[0019] As an optional implementation, in the first aspect of the embodiment of the present application, the friction compensation torque is determined based on the joint speed, comprising:

[0020] The friction compensation torque of each joint is determined according to the joint speed:

[0021]

[0022] wherein, is the friction compensation torque of the i th joint, is a friction function, is a joint speed vector, is the joint speed of the i th joint, is a viscous friction coefficient, is the Coulomb friction coefficient, is a symbol function.

[0023] The viscous and Coulomb friction model is a classical and effective friction modeling method, has small calculation amount, is suitable for real-time control, and the viscous friction coefficient and the Coulomb friction coefficient can be calibrated according to an actual robot or calibrated through a genetic algorithm and the like to adapt to different temperature conditions.

[0024] As an optional implementation, in the first aspect of the embodiment of the present application, the drag torque is acquired in real time, comprising:

[0025] The drag torque is calculated according to the drag force collected by the sensor in real time:

[0026]

[0027] wherein, is the drag torque of the i th joint, is the transpose of the Jacobian matrix corresponding to the i th joint, is the drag force;

[0028] The command torque is obtained according to the gravity compensation torque, the friction compensation torque and the drag torque:

[0029]

[0030] wherein, is the command torque of the i th joint, is the gravity compensation torque of the i th joint, is the friction compensation torque of the i th joint, and α is an amplification coefficient.

[0031] The amplification coefficient α is an adjustable coefficient, and its range is generally set to 1-3. In the muscle strength reconstruction period, α can be set to 1, and pure zero force drag is relied on to complete passive training. When α>1, the robot provides assistance according to a certain proportion, realizing the effect of small force drag and large force assistance. The operator applies a very small force, and the system will amplify this effect to output a larger auxiliary torque, so as to easily complete the training action, and it is particularly suitable for the auxiliary training of patients with weak muscle strength. For example, when α=1.8, the operator's output is only 1 / 1.8=56% of the actual demand.

[0032] As an optional implementation, in the first aspect of the embodiment of the present application, the passive training rehabilitation operation is realized by controlling the robot through the command torque, comprising:

[0033] The command torque is converted into a command current:

[0034]

[0035] wherein, is the command current of the i th joint, is the conversion torque coefficient;

[0036] outputting the command current to the actuator corresponding to each joint, so that the robot performs the passive training rehabilitation operation.

[0037] conversion torque coefficient The conversion torque coefficient can be obtained by trial, and the conversion torque coefficient corresponding to different motors is not necessarily the same. The command torque is converted into the command current input to the actuator, so that the motor can smoothly output torque and avoid shaking or impact.

[0038] As an optional implementation, in the first aspect of the embodiment of the application, the method further comprises: when the active training mode is adopted, determining the command torque according to the joint position deviation value:

[0039]

[0040] wherein, is the command torque of the i th joint, is the virtual impedance coefficient, is the joint position deviation value of the i th joint;

[0041] converting the command torque into a command current:

[0042]

[0043] wherein, is the command current of the i th joint, is the conversion torque coefficient;

[0044] outputting the command current to the actuator corresponding to each joint, so that the robot performs the passive training rehabilitation operation.

[0045] by setting the virtual impedance coefficient The virtual environment of various different strengths can be simulated flexibly by simulating the spring resistance, so as to provide the patient with various active training modes such as resistance training and stiffness training, guide trajectory correction, and enrich the content and means of rehabilitation training.

[0046] For example, when the virtual impedance coefficient is small, the soft virtual environment allows the patient to move under small resistance. The robot does not resist the movement of the patient, but provides a soft spatial guide to help the patient complete the full range of joint movement without effort and learn the correct movement trajectory, so it can be suitable for patients with weak muscle strength, in the early stage of rehabilitation, or needing to focus on training movement accuracy and coordination.

[0047] When the virtual impedance coefficient is large, the hard virtual environment generates strong resistance to the movement of the patient. The patient must exert more force to produce displacement, so that the target muscle group bears high load, stimulates muscle fiber thickening, and increases strength, and therefore, can be suitable for patients who need to increase muscle volume, absolute strength and endurance, and is in the middle and late stages of rehabilitation.

[0048] As an optional implementation, in the first aspect of the embodiment of the application, the method further comprises:

[0049] real-time acquisition of heart rate data and electromyographic signal data of the user;

[0050] When the heart rate data is greater than a preset heart rate value, or / and, the electromyographic signal data is less than a preset EMG value, or / and, the joint position is not in a corresponding preset range, the robot is controlled to stop urgently.

[0051] Through physiological signal and joint position safety monitoring, a safety protection system is constructed, which can intervene and stop urgently in time at the beginning of fatigue, excessive load or possible muscle strain, and effectively avoids secondary injury.

[0052] It can be understood that the preset heart rate value and the preset EMG value can be adjusted according to the individual condition of the patient, realizing personalized customization of safety protection, so that the system has good applicability to patients with different physical conditions.

[0053] The second aspect of the embodiment of the application discloses a rehabilitation system based on a robot, comprising:

[0054] a receiving unit configured to receive a mode selection result of an operator, the mode including a passive training mode and an active training mode;

[0055] an acquisition unit configured to, when the passive training mode is adopted, acquire a drag torque, a joint position and a joint speed in real time in response to a drag force applied by the operator on the robot;

[0056] a calculation unit configured to determine a gravity compensation torque based on the joint position, determine a friction compensation torque based on the joint speed, and obtain a command torque according to the gravity compensation torque, the friction compensation torque and the drag torque;

[0057] an execution unit configured to control the robot to perform a passive training rehabilitation operation through the command torque.

[0058] The third aspect of the embodiment of the present application discloses an electronic device, comprising: a memory storing executable program codes; and a processor coupled with the memory; the processor invokes the executable program codes stored in the memory, and is configured to execute the robot-based rehabilitation method disclosed in the first aspect of the embodiment of the present application.

[0059] The fourth aspect of the embodiment of the present application discloses a computer readable storage medium storing a computer program, wherein the computer program enables a computer to execute the robot-based rehabilitation method disclosed in the first aspect of the embodiment of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative effort based on these drawings.

[0061] Figure 1 is a flowchart of the robot-based rehabilitation method disclosed in the embodiment of the present application;

[0062] Figure 2 is a structural diagram of a robot-based rehabilitation system provided by the embodiment of the present application;

[0063] Figure 3 is a structural diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0064] The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present application.

[0065] It should be noted that the terms first, second, third, fourth and the like in the specification and claims of the present application are used to distinguish different objects, and are not used to describe a specific order. The terms of the embodiments of the present application include and have as well as any variations thereof, which are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0066] Embodiment one

[0067] Please refer to Figure 1 , Figure 1 is a flowchart of a robot-based rehabilitation method according to an embodiment of the present application. In the method described in the embodiment of the present application, the execution subject is composed of software or hardware, which can receive relevant information through wired or wireless means and send certain instructions. Of course, it can also have certain processing and storage functions. The execution subject can control multiple devices, such as remote physical servers or cloud servers and related software, or local hosts or servers and related software that perform relevant operations on devices placed somewhere. In some scenarios, it can also control multiple storage devices, which can be placed in the same place or different places. As shown in Figure 1 , the robot-based rehabilitation method includes the following steps:

[0068] S110, receiving a mode selection result of a user, the mode including a passive training mode and an active training mode.

[0069] The rehabilitation training can include a passive training mode and an active training mode. Through the selection of the passive and active training modes, the needs of patients at different rehabilitation stages can be met. The passive training mode is to completely control the limb movement of the patient by the rehabilitation robot, and the patient does not need to actively participate, which is suitable for patients at the early stage of rehabilitation or with muscle weakness, helping to maintain joint range of motion and prevent muscle atrophy. The active training mode is to independently complete a predetermined action sequence by the patient without external help, and the rehabilitation robot only provides guidance as a supervisor.

[0070] There are various ways to receive the mode selection of the user. For example, the mode selection can be made through mechanical or touch buttons, or through voice and the like, which is not limited here. The user mainly refers to the patient. Of course, in some other embodiments, the rehabilitation trainer or therapist can select the appropriate training mode according to the actual situation of the user, and then the rehabilitation trainer, therapist or patient's family member can perform the mode selection.

[0071] S120, when the passive training mode is adopted, the drag torque, joint position and joint speed are acquired in real time in response to the drag force applied by the operator on the robot.

[0072] The operator refers to the operating personnel for dragging the rehabilitation robot in the passive training mode, who can be the patient himself, a rehabilitation trainer or physiotherapist, or a patient's family member, etc. That is, the user and the operator can be different personnel.

[0073] Generally, the drag force in passive mode is small, which can be balanced by the contribution of the user and the rehabilitation robot through the amplification coefficient. The drag force applied to the robot can be collected by the force sensor arranged at the end of the robot, including the drag force itself, joint position and joint speed. For example, when the operator is detected to apply external force to the robot, the collection mechanism is triggered to obtain the drag force itself, joint position and joint speed. The joint position and joint speed can be collected by a Hall element, or can be realized by a position sensor and a speed sensor respectively, which is not limited here.

[0074] Since only very small force is needed to drag the robot in the present application, in order to avoid the misoperation of the humanoid robot caused by environmental factors or other factors, in the preferred embodiment of the present application, the collection mechanism can be triggered in two ways. One is to preliminarily wake up the robot by physical means such as button or wireless means such as voice, and then trigger the collection mechanism under the condition of external force. The other way is to apply external force to the robot which is not less than the preset pressure threshold, and preliminarily wake up the robot when the duration of the external force reaches the preset time threshold, and then trigger the collection mechanism under the condition of external force.

[0075] S130, determining a gravity compensation torque based on the joint position, determining a friction compensation torque based on the joint speed, and obtaining a command torque according to the gravity compensation torque, the friction compensation torque and the drag torque.

[0076] The gravity compensation torque is determined by the joint position, which can be realized by a dynamic model. Using the dynamic model, the actual structure parameters of the robot (including mass, center of mass, Jacobian matrix, etc.) can be accurately modeled, which is suitable for different models and can accurately calculate the gravity compensation torque required by each joint, especially for complex configuration robots.

[0077] Specifically, the dynamic model is constructed according to the joint position, the link mass and the Jacobian matrix, and the gravity compensation torque of each joint is calculated:

[0078]

[0079] wherein, is the gravity compensation torque of the i th joint, n is the total number of joints, G is the gravity function, is the joint position vector, is the position Jacobian matrix of the k th link center of mass, T is the transpose of the matrix, is the mass of the k th link, g is the acceleration of gravity.

[0080] It should be noted that the summation formula is used because the gravity compensation torque of a joint needs to compensate for the gravity of the corresponding link of the joint and the equivalent torque transmitted downstream through the mechanical structure, that is, the gravity of all links downstream. Taking a six-axis robot as an example, because all links are located downstream of joint 1, the gravity compensation torque of joint 1 needs to compensate for the gravity of the entire robot, and the gravity compensation torque of joint 6 only compensates for the gravity of the end link.

[0081] To greatly reduce the computational complexity to meet the real-time control requirements of real-time systems, in other embodiments, the gravity compensation torque of each joint can also be obtained by a recursive Newton-Euler algorithm:

[0082]

[0083] wherein, is the gravity torque of the i-th joint.

[0084] Using the recursive Newton-Euler algorithm, the computational complexity can be reduced from O(n 2 ) to O(n).

[0085] The friction compensation torque can be realized by a viscous and Coulomb friction model:

[0086]

[0087] wherein, is the friction compensation torque of the i-th joint, is a friction function, is a joint velocity vector, is the joint velocity of the i-th joint, is a viscous friction coefficient, is a Coulomb friction coefficient, is a sign function.

[0088] The viscous and Coulomb friction model is a classical and effective friction modeling method, with small computational load and suitable for real-time control. The viscous friction coefficient and the Coulomb friction coefficient can be calibrated according to the actual robot, or can be calibrated by a genetic algorithm, etc. to adapt to different temperature conditions.

[0089] The drag torque can be converted by the drag force collected by the sensor in real time:

[0090]

[0091] wherein, is the drag torque of the i-th joint, is the transpose of the Jacobian matrix corresponding to the i-th joint, For the drag force, since the Jacobian matrices corresponding to the joints are different, the drag force can be mapped to each joint based on the Jacobian matrix corresponding to each joint, forming a drag torque corresponding to each joint.

[0092] After superimposing the gravity compensation torque, the friction compensation torque and the drag torque, the command torque is obtained:

[0093]

[0094] wherein, is the command torque of the i th joint, is the gravity compensation torque of the i th joint, is the friction compensation torque of the i th joint, and a is an amplification factor.

[0095] The amplification factor a is an adjustable coefficient, which is generally set in the range of 1-3. During the muscle strength reconstruction period, a can be set as a=1 to rely on pure zero force drag to complete passive training. When a>1, the robot provides assistance according to a certain proportion, achieving the effect of small force drag and large force assistance. The operator applies a very small force, and the system will amplify this effect to output a larger auxiliary torque, thereby easily completing the training action. This is particularly suitable for the assisted training of patients with weak muscle strength. For example, when a=1.8, the operator's output is only 1 / 1.8=56% of the actual demand.

[0096] S140, when the active training mode is adopted, the command torque is determined according to the joint position deviation value.

[0097] The command torque can be determined by setting a virtual impedance coefficient in combination with the joint position deviation value:

[0098]

[0099] wherein, is the command torque of the i th joint, is the virtual impedance coefficient, is the joint position deviation value of the i th joint;

[0100] The virtual impedance coefficient simulates the spring resistance, which can flexibly simulate virtual environments of various different strengths, provides resistance training, stiffness training and other active training modes for patients, and guides the trajectory correction, thereby enriching the content and means of rehabilitation training.

[0101] Exemplarily, when the virtual impedance coefficient is small, the soft virtual environment allows the patient to perform movement under small resistance. The robot does not resist the movement of the patient, but provides a soft spatial guidance to help the patient complete the full range of joint movement without effort and learn the correct movement trajectory, and thus can be suitable for patients with weak muscle strength, in the early stage of rehabilitation, or needing to emphasize training of movement accuracy and coordination.

[0102] When the virtual impedance coefficient is large, the hard virtual environment strongly resists the movement of the patient. The patient must exert more force to produce displacement, so that the target muscle group bears high load, stimulates muscle fiber thickening, and increases strength, and thus can be suitable for patients who need to increase muscle volume, absolute strength, and endurance, and are in the middle and late stages of rehabilitation.

[0103] S150, controlling the robot to perform passive or active training rehabilitation operation through the command torque.

[0104] The command torque is an output parameter of the actuator, which needs to be converted into a current value that can control the actuator to output the corresponding command torque in use, which is called command current:

[0105]

[0106] wherein, is the command current of the i-th joint, is the rotation torque coefficient, which can be obtained by experiment, and different motors may not have the same rotation torque coefficient.

[0107] The command torque is converted into the command current input to the actuator, and the command current is output to the actuator corresponding to each joint to control the robot to perform passive or active training rehabilitation operation.

[0108] In a preferred embodiment of the present application, a safety protection system is also constructed through physiological signals and joint position safety monitoring, which can intervene and emergency stop in time at the beginning of fatigue (EMG signal weakening), excessive load (rapid heart rate) or conditions that may cause sprain (exceeding the range of joint movement), effectively avoiding secondary injury. Specifically, it can include:

[0109] Real-time acquisition of heart rate data HR and electromyogram data EMG of the user; when the heart rate data HR is greater than a heart rate preset value HR max , or / and, the electromyogram data EMG is less than an EMG preset value EMG threshold , or / and, , the robot is controlled to emergency stop.

[0110] It can be understood that the heart rate preset value and the EMG preset value can be adjusted according to the individual condition of the patient, the personalized customization of the safety protection is realized, and the system has good applicability to patients with different physical conditions.

[0111] In the passive mode, the embodiment of the application greatly eliminates the resistance to movement caused by the robot body by calculating and compensating the gravity and friction in real time, so that the operator feels light and smooth when dragging the mechanical arm, as if moving a weightless object, and the naturalness and comfort of human-computer interaction are improved.

[0112] Embodiment two

[0113] Please refer to Figure 2 , Figure 2 is a structural schematic diagram of a rehabilitation system based on a robot disclosed by the embodiment of the application. As shown in Figure 2 , the rehabilitation system based on a robot can include:

[0114] The receiving unit 210 is configured to receive a mode selection result of an operator, and the mode includes a passive training mode and an active training mode.

[0115] The acquisition unit 210 is configured to, when the passive training mode is adopted, acquire a dragging torque, a joint position and a joint speed in real time in response to a dragging force applied to the robot by the operator.

[0116] The calculation unit 230 is configured to determine a gravity compensation torque based on the joint position, determine a friction compensation torque based on the joint speed, and obtain a command torque according to the gravity compensation torque, the friction compensation torque and the dragging torque.

[0117] The execution unit 240 is configured to control the robot to perform a passive training rehabilitation operation through the command torque.

[0118] The calculation unit 230 can include:

[0119] The gravity compensation torque of each joint is calculated through a dynamic model:

[0120]

[0121] Alternatively, the gravity compensation torque of each joint is acquired through a recursive Newton-Euler algorithm.

[0122] wherein, is the gravity compensation torque of the i th joint, n is the total number of joints, G is a gravity function, is a joint position vector, is a position Jacobian matrix of the k th connecting rod mass center, T is a transpose of a matrix, is the mass of the k th connecting rod, and g is the acceleration of gravity.

[0123] determine a friction compensation torque based on the joint velocity, comprising:

[0124] determine a friction compensation torque of each joint according to a respective joint velocity:

[0125]

[0126] wherein, is a friction compensation torque of the i-th joint, is a friction force function, is a joint velocity vector, is a joint velocity of the i-th joint, is a viscous friction coefficient, is a coulomb friction coefficient, is a sign function.

[0127] The acquisition unit 220 can include:

[0128] acquire a dragging force in real time through a sensor, and calculate the dragging torque according to the dragging force:

[0129]

[0130] wherein, is a dragging torque of the i-th joint, is a transpose of a Jacobian matrix corresponding to the i-th joint, is a dragging force;

[0131] obtain a command torque according to the gravity compensation torque, the friction compensation torque, and the dragging torque:

[0132]

[0133] wherein, is a command torque of the i-th joint, is a gravity compensation torque of the i-th joint, is a friction compensation torque of the i-th joint, and a is a magnification coefficient.

[0134] The execution unit 240 can include:

[0135] convert the command torque into a command current:

[0136]

[0137] wherein, is a command current of the i-th joint, is a torque conversion coefficient;

[0138] The command current is output to the actuator corresponding to each joint to make the robot perform passive training rehabilitation operation.

[0139] The system can further comprise an active mode unit for determining a command torque according to the joint position deviation value when an active training mode is adopted:

[0140]

[0141] wherein, is the command torque of the i th joint, is a virtual impedance coefficient, is the joint position deviation value of the i th joint;

[0142] The command torque is converted into a command current:

[0143]

[0144] wherein, is the command current of the i th joint, is a rotation torque coefficient;

[0145] The command current is output to the actuator corresponding to each joint to make the robot perform active training rehabilitation operation.

[0146] The system can further comprise a safety enhancement unit for acquiring heart rate data and electromyographic signal data of the user in real time; when the heart rate data is greater than a preset heart rate value, or / and, the electromyographic signal data is less than a preset EMG value, or / and, the joint position is not within a corresponding preset range, the robot is controlled to stop urgently.

[0147] Embodiment three

[0148] Please refer to Figure 3 , Figure 3 is a structural schematic diagram of an electronic device disclosed by an embodiment of the present application. The electronic device can be a computer, a server, and the like, and of course, under certain circumstances, can also be a mobile phone, a tablet computer, a monitoring terminal, and the like intelligent device, and an image acquisition device with processing function. As shown in the figure, the electronic device can include: Figure 3

[0149] a memory 310 storing executable program codes;

[0150] a processor 320 coupled with the memory 310;

[0151] The processor 320 calls the executable program codes stored in the memory 310 to execute part or all of the steps in the rehabilitation method based on the robot in embodiment one.

[0152] ​The embodiment of the present application discloses a computer readable storage medium which stores a computer program, wherein the computer program causes a computer to execute part or all steps in the robot-based rehabilitation method in the embodiment one.

[0153] The embodiment of the present application also discloses a computer program product, wherein when the computer program product is run on a computer, the computer program product causes the computer to execute part or all steps in the robot-based rehabilitation method in the embodiment one.

[0154] The embodiment of the present application also discloses an application publishing platform, wherein the application publishing platform is used for publishing a computer program product, wherein when the computer program product is run on a computer, the computer program product causes the computer to execute part or all steps in the robot-based rehabilitation method in the embodiment one.

[0155] In various embodiments of the present application, it should be understood that the magnitude of the serial number of the processes does not mean the inevitable sequence of execution, and the execution sequence of the processes should be determined according to their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0156] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e. can be located in one place, or can be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment of the present application.

[0157] In addition, each functional unit in the embodiments of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0158] When the integrated unit is realized in the form of software functional unit and sold or used as an independent product, it can be stored in a computer accessible memory. Based on such understanding, the technical solutions of the present application essentially or the part that makes contributions to the prior art or the whole or part of the technical solutions can be embodied in the form of software product, and the computer software product is stored in a memory, including a plurality of steps for causing a computer device (which can be a personal computer, a server or a network device, and specifically can be a processor in the computer device) to execute part or all steps of the method described in each embodiment of the present application.

[0159] In the embodiments provided in the present application, it should be understood that B corresponding to A means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean that B is determined only according to A, but B can also be determined according to A and / or other information.

[0160] A person of ordinary skill in the art can understand that part or all of the steps in the various methods of the embodiments can be completed by instructing the relevant hardware by a program, and the program can be stored in a computer readable storage medium, including Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM) or other optical disk memories, magnetic disk memories, magnetic tape memories, or any other computer readable medium capable of carrying or storing data.

[0161] The above describes in detail the rehabilitation method and system based on the robot according to the embodiments of the present application. The principles and implementation manners of the present application are described by applying specific examples. The above description of the embodiments is only used to help understand the method of the present application and its core idea. Meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manners and application ranges can be changed. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A robot-based rehabilitation method, characterized by, The method comprises: receiving a mode selection result of a user, the mode including a passive training mode and an active training mode; when the passive training mode is adopted, acquiring in real time a drag torque, a joint position and a joint velocity in response to a drag force applied by the operator on the robot, wherein the drag torque is acquired in real time, including: acquiring in real time the drag force through a sensor, and calculating the drag torque according to the drag force; wherein, is the drag torque of the ith joint, is the transpose of the Jacobian matrix corresponding to the ith joint, is the drag force; determining a gravity compensation torque based on the joint position, determining a friction compensation torque based on the joint velocity, and obtaining a command torque according to the gravity compensation torque, the friction compensation torque and the drag torque; wherein, is the command torque for the i-th joint, is the gravity compensation torque for the i-th joint, is the friction compensation torque for the i-th joint, and α is an amplification factor. controlling the robot to perform a passive training rehabilitation operation through the command torque.

2. The robot-based rehabilitation method according to claim 1, characterized in that, determining the gravity compensation torque based on the joint position, including: calculating the gravity compensation torque of each joint through a dynamic model; or, acquiring the gravity compensation torque of each joint through a recursive Newton-Euler algorithm; wherein, is the gravity compensation moment for the ith joint, n is the total number of joints, G is the gravity function, is the joint position vector, is the position Jacobian matrix of the kth link mass center, T is the transpose of the matrix, is the kth link mass, g is the gravity acceleration.

3. The robot-based rehabilitation method according to claim 1, characterized in that, determining the friction compensation torque based on the joint velocity, including: determining the friction compensation torque of each joint according to the joint velocity; wherein is the friction compensated torque of the i-th joint, is the friction function, is the joint velocity vector, is the joint velocity of the i-th joint, is the viscous friction coefficient, is the coulomb friction coefficient, is the sign function.

4. The robot-based rehabilitation method according to claim 1, characterized in that, controlling the robot to perform the passive training rehabilitation operation through the command torque, including: converting the command torque into a command current; wherein, is the command current for the i-th joint, is the torque coefficient; outputting the command current to an actuator corresponding to each joint, so that the robot performs the passive training rehabilitation operation.

5. The robot-based rehabilitation method according to claim 1, characterized in that, The method further comprises: when the active training mode is adopted, determining a command torque according to a joint position deviation value: wherein, is a command torque for the i-th joint, is a virtual impedance coefficient, is a joint position error value for the i-th joint; converting the command torque into a command current; wherein, command current for the i-th joint, is the torque coefficient; outputting the command current to an actuator corresponding to each joint, so that the robot performs the active training rehabilitation operation.

6. The robot-based rehabilitation method according to any one of claims 1-5, characterized in that, The method further comprises: acquiring in real time heart rate data and electromyographic signal data of the user; when the heart rate data is greater than a preset heart rate value, or / and, the electromyographic signal data is less than a preset EMG value, or / and, the joint position is not within a corresponding preset range, controlling the robot to stop urgently.

7. A robot-based rehabilitation system, characterized in that The method comprises: a receiving unit configured to receive a mode selection result of an operator, the mode including a passive training mode and an active training mode; an acquiring unit configured to acquire in real time a drag torque, a joint position and a joint velocity in response to a drag force applied by the operator on the robot when the passive training mode is adopted, wherein the drag torque is acquired in real time, including: acquiring in real time the drag force through a sensor, and calculating the drag torque according to the drag force; wherein, is the drag torque of the ith joint, is the transpose of the Jacobian matrix corresponding to the ith joint, is the drag force; a calculating unit configured to determine a gravity compensation torque based on the joint position, determine a friction compensation torque based on the joint velocity, and obtain a command torque according to the gravity compensation torque, the friction compensation torque and the drag torque; wherein, is the command torque for the i-th joint, is the gravity compensation torque for the i-th joint, is the friction compensation torque for the i-th joint, and α is an amplification factor. an executing unit configured to control the robot to perform a passive training rehabilitation operation through the command torque.

8. An electronic device, comprising: The method comprises: a memory storing executable program codes; a processor coupled with the memory; the processor invokes the executable program codes stored in the memory, for executing the robot-based rehabilitation method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, wherein the computer program causes a computer to execute the robot-based rehabilitation method according to any one of claims 1 to 6.

Images