Human body lower limb rehabilitation training method, device, equipment, medium and program product

Abstract

The invention provides a human body lower limb rehabilitation training method, device and equipment, a medium and a program product, and relates to the technical field of rehabilitation medicines.The method comprises the steps that a coordinate point set or a spatial pose set corresponding to the hands of a physician in the process that the physician conducts rehabilitation training on the lower limbs of a target user is obtained through an image collecting device, determining a target rehabilitation training track corresponding to the lower limbs of the target user based on the coordinate point set or the spatial pose set; and controlling a mechanical arm to perform rehabilitation training on the lower limbs of the target user based on the target rehabilitation training track. According to the technical scheme, the mechanical arm can be controlled to conduct rehabilitation training on the lower limbs of the target user according to the target rehabilitation training track corresponding to the lower limbs of the target user, the automation degree is high, the labor cost is reduced, and the special training requirements of the target user can be met.

Description

Technical Field

[0001] The present invention relates to the field of rehabilitation medical technology, and in particular to a method, device, equipment, medium and program product for rehabilitation training of human lower limbs. Background Art

[0002] In recent years, the number of patients suffering from stroke diseases such as stroke and spinal cord injury is increasing. Rehabilitation training can help alleviate the impaired motor skills caused by such diseases. However, the number of physicians in the field of rehabilitation training in China is limited, the doctor-patient ratio is seriously unbalanced, and rehabilitation training is affected by factors such as the physician's experience, ability and professional knowledge. The training methods of rehabilitation physicians are also uneven, and the effect and quality of rehabilitation training are difficult to guarantee.

[0003] In order to solve the problems of shortage of rehabilitation physicians and uneven techniques, there are methods in the prior art for performing rehabilitation training on patients using rehabilitation training robots or robotic arms. However, the existing rehabilitation training robots or robotic arms have a low degree of automation, require a lot of manual participation, have high labor costs, and are difficult to meet the rehabilitation training needs of most patients. Summary of the invention

[0004] The present invention provides a method, device, equipment, medium and program product for human lower limb rehabilitation training, which are used to solve the defects of the prior art that the rehabilitation training robots or mechanical arms have a low degree of automation, require a lot of manual participation, have high labor costs, and are difficult to meet the rehabilitation training needs of most patients. The technical solution of the present invention has a high degree of automation, reduces labor costs, and can meet the special training needs of target users.

[0005] The invention provides a human lower limb rehabilitation training method, comprising the following steps.

[0006] Acquire, by an image acquisition device, a set of coordinate points or a set of spatial postures corresponding to the hands of the physician during the rehabilitation training of the lower limbs of the target user by the physician, and determine a target rehabilitation training trajectory corresponding to the lower limbs of the target user based on the set of coordinate points or the set of spatial postures; Based on the target rehabilitation training trajectory, the robotic arm is controlled to perform rehabilitation training on the lower limbs of the target user.

[0007] According to a human lower limb rehabilitation training method provided by the present invention, the coordinate point set or spatial posture set corresponding to the doctor's hand during the doctor's rehabilitation training of the target user's lower limbs is obtained by an image acquisition device, including: Acquiring, by means of the image acquisition device, a plurality of initial coordinate points or a plurality of initial spatial postures corresponding to the hands of the physician during the rehabilitation training of the lower limbs of the target user by the physician; The coordinate point set or the spatial pose set is determined based on all the initial coordinate points or all the initial spatial poses.

[0008] According to a human lower limb rehabilitation training method provided by the present invention, the initial coordinate point is a coordinate point in a world coordinate system, the initial spatial posture is a spatial posture in the world coordinate system, and the world coordinate system is determined based on the position of the image acquisition device; The determining the coordinate point set or the spatial pose set based on all the initial coordinate points or all the initial spatial poses comprises: All initial coordinate points in the world coordinate system are converted to the robotic arm coordinate system corresponding to the robotic arm to determine the coordinate point set; or all initial spatial poses in the world coordinate system are converted to the robotic arm coordinate system to determine the spatial pose set.

[0009] According to a human lower limb rehabilitation training method provided by the present invention, the target rehabilitation training trajectory corresponding to the lower limb of the target user is determined based on the coordinate point set or the spatial posture set, including: Connecting each coordinate point in the coordinate point set, or connecting each spatial posture in the spatial posture set, to determine a first rehabilitation training trajectory; Optimizing the first rehabilitation training trajectory based on a covariant Hamiltonian optimization algorithm to determine a second rehabilitation training trajectory; The second rehabilitation training trajectory is interpolated with equal time intervals based on a time optimal trajectory generation algorithm to determine the target rehabilitation training trajectory.

[0010] According to a human lower limb rehabilitation training method provided by the present invention, the method of controlling a mechanical arm to perform rehabilitation training on the lower limbs of a target user based on the target rehabilitation training trajectory comprises: Determining a robotic arm motion instruction corresponding to the target rehabilitation training trajectory based on the target rehabilitation training trajectory; The robotic arm is controlled based on the robotic arm movement instruction to perform rehabilitation training on the lower limbs of the target user.

[0011] According to a human lower limb rehabilitation training method provided by the present invention, the robotic arm is a six-degree-of-freedom robotic arm; the six-degree-of-freedom robotic arm is configured with a target robotic arm model; the robotic arm motion instruction is an instruction corresponding to the target robotic arm model; the target robotic arm model is determined by the following steps: Constructing a forward kinematics model and an inverse kinematics model based on the geometric parameters corresponding to each joint in the six-degree-of-freedom robotic arm; The target robot arm model is determined based on the forward kinematics model and the inverse kinematics model.

[0012] The present invention also provides a human lower limb rehabilitation training device, comprising the following modules: A determination module, configured to obtain, through an image acquisition device, a set of coordinate points or a set of spatial postures corresponding to the hands of the physician during the rehabilitation training of the lower limbs of the target user by the physician, and determine a target rehabilitation training trajectory corresponding to the lower limbs of the target user based on the set of coordinate points or the set of spatial postures; A control module is used to control the robotic arm to perform rehabilitation training on the lower limbs of the target user based on the target rehabilitation training trajectory.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any one of the above-mentioned methods for rehabilitation training of human lower limbs is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the human lower limb rehabilitation training method as described above is implemented.

[0015] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above-mentioned methods for rehabilitation training of human lower limbs.

[0016] The human lower limb rehabilitation training method, device, equipment, medium and program product provided by the present invention first obtains the coordinate point set or spatial posture set corresponding to the doctor's hand during the doctor's rehabilitation training of the target user's lower limbs through an image acquisition device, and then determines the target rehabilitation training trajectory corresponding to the target user's lower limbs based on the coordinate point set or the spatial posture set, and then controls the mechanical arm to perform rehabilitation training on the target user's lower limbs based on the target rehabilitation training trajectory. The technical solution of the present invention can control the mechanical arm to perform rehabilitation training on the target user's lower limbs according to the target rehabilitation training trajectory corresponding to the target user's lower limbs, with a high degree of automation, reducing labor costs, and being able to meet the special training needs of the target user. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 This is one of the flow charts of the human lower limb rehabilitation training method provided by the present invention.

[0019] Figure 2 It is a spatial schematic diagram of the world coordinate system calibration provided by the present invention.

[0020] Figure 3 It is a spatial schematic diagram of the initial coordinate points provided by the present invention.

[0021] Figure 4 It is one of the schematic diagrams of the coordinate point set provided by the present invention.

[0022] Figure 5 This is the second schematic diagram of the coordinate point set provided by the present invention.

[0023] Figure 6 This is the third schematic diagram of the coordinate point set provided by the present invention.

[0024] Figure 7 It is a schematic diagram of the displacement curve of the mechanical arm joint provided by the present invention.

[0025] Figure 8 It is a schematic diagram of the speed curve of the mechanical arm joint provided by the present invention.

[0026] Fig. 9 It is a schematic diagram of the rehabilitation training system provided by the present invention.

[0027] Fig.10 One of the schematic diagrams comparing the doctor's hand trajectory and the robot arm's reproduced trajectory provided by the present invention.

[0028] Fig.11 The second schematic diagram of the comparison between the doctor's hand trajectory and the robot arm's reproduction trajectory provided by the present invention.

[0029] Fig.12 The third schematic diagram of the comparison between the doctor's hand trajectory and the robot arm's reproduction trajectory provided by the present invention.

[0030] Fig.13 It is a structural schematic diagram of the human lower limb rehabilitation training device provided by the present invention.

[0031] Fig.14 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are 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.

[0033] In view of the above problems in the prior art, the present invention provides a method for rehabilitation training of human lower limbs. It should be noted that the execution subject of the present invention can be a host computer or other electronic equipment, and the execution subject of the present invention is connected to a mechanical arm. Figure 1 It is one of the flow charts of the human lower limb rehabilitation training method provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 110: Obtain, through an image acquisition device, a set of coordinate points or a set of spatial postures corresponding to the hands of the physician during the rehabilitation training of the target user's lower limbs by the physician, and determine a target rehabilitation training trajectory corresponding to the target user's lower limbs based on the set of coordinate points or the set of spatial postures.

[0034] Specifically, an image acquisition device may be arranged in advance, and the image acquisition device may be, for example, an infrared camera. When the infrared camera is arranged, a tripod may be used to fix the infrared camera, and the position of the infrared camera may be calibrated by a calibration rod. In order to accurately capture the doctor's hand movements, multiple infrared cameras may be arranged.

[0035] In addition, in order to accurately capture the doctor's hand movements and generate corresponding trajectories, the doctor's hands can wear a marking device, which can include multiple marking points, and the marking points are rigid, and the positional relationship between the marking points is fixed. The use of rigid marking points can minimize the errors caused by the slippage of the marking points directly attached to the surface of human skin. Preferably, the marking device can be connected to the back of the experimenter's hand to improve the accuracy of the movement trajectory of the robotic arm when controlling the robotic arm for rehabilitation training. The marking device needs to meet the following conditions: ① The pasting of the marking device does not affect the doctor's hand movement; ② Each marking point in the marking device can be captured by at least two infrared cameras at the same time; ③ There are at least three marking points in the marking device and they are not collinear.

[0036] Preferably, the acquisition environment corresponding to the image acquisition device can also be set as follows: ① The indoor background is set to red, black or a non-reflective wall; ② Infrared interference is reduced as much as possible, for example, measures such as pulling curtains and removing reflective objects can be implemented; ③ The position and angle of the infrared camera should cover the physician's hand area, and the captured mark point should be located at the center of all infrared camera imaging; ④ The frame rate, threshold, focal length and exposure time of the infrared camera are adjusted to make the mark point clearly contrast with the image background.

[0037] Furthermore, an infrared camera can be used to obtain a set of coordinate points or a set of spatial postures corresponding to the doctor's hands during the doctor's rehabilitation training of the target user's lower limbs. It is easy to understand that the coordinate point set and the spatial posture in the spatial posture set both contain timing information, and then the target rehabilitation training trajectory corresponding to the target user's lower limbs can be determined based on the coordinate point set or the spatial posture set. The target user can represent a patient or a type of patient. The target rehabilitation trajectory corresponding to the target user's lower limbs is the trajectory for rehabilitation training for the patient or the type of patient.

[0038] In one embodiment, the acquisition of a set of coordinate points or a set of spatial postures corresponding to the physician's hands during the physician's rehabilitation training of the target user's lower limbs by an image acquisition device includes: Acquiring, by means of the image acquisition device, a plurality of initial coordinate points or a plurality of initial spatial postures corresponding to the hands of the physician during the rehabilitation training of the lower limbs of the target user by the physician; The coordinate point set or the spatial pose set is determined based on all the initial coordinate points or all the initial spatial poses.

[0039] Specifically, optical high-precision motion capture technology can be used to obtain multiple initial coordinate points or multiple initial spatial postures corresponding to the physician's hands during the physician's rehabilitation training of the target user's lower limbs. It is easy to understand that in the process of collecting the initial coordinate points or initial spatial postures, it can be considered that the relative position between the marking point of the marking device and the physician's hand has not changed, that is, the marking point and the physician's hand can be regarded as a rigid body. Figure 3 is a spatial schematic diagram of the initial coordinate points provided by the present invention, such as Figure 3 As shown, the pink sphere is the marking point of the marking device, and the white sphere is the center of the rigid body determined according to the marking point, and then the coordinate point corresponding to the center of the rigid body can be determined as the initial coordinate point. It should be noted that the initial coordinate point corresponds to the position information of the doctor's hand, and the initial spatial posture corresponds to the position information and posture information of the doctor's hand. Then, a coordinate point set or a spatial posture set can be determined based on all initial coordinate points or all initial spatial postures.

[0040] In the above embodiment, the image acquisition device can be used to obtain multiple initial coordinate points or multiple initial spatial postures corresponding to the doctor's hands during the doctor's rehabilitation training of the target user's lower limbs, and then a coordinate point set or a spatial posture set can be determined, so as to facilitate the subsequent determination of the target rehabilitation training trajectory based on the coordinate point set or the spatial posture set, thereby facilitating the subsequent control of the robotic arm to simulate the doctor's rehabilitation training of the target user's lower limbs.

[0041] In one embodiment, the initial coordinate point is a coordinate point in a world coordinate system, the initial spatial pose is a spatial pose in the world coordinate system, and the world coordinate system is determined based on the position of the image acquisition device; The determining the coordinate point set or the spatial pose set based on all the initial coordinate points or all the initial spatial poses comprises: All initial coordinate points in the world coordinate system are converted to the robotic arm coordinate system corresponding to the robotic arm to determine the coordinate point set; or all initial spatial poses in the world coordinate system are converted to the robotic arm coordinate system to determine the spatial pose set.

[0042] Specifically, when the doctor performs lower limb rehabilitation training on the target user's lower limbs, the coordinate points or spatial postures need to be collected in a unified coordinate system, which can be a world coordinate system. The embodiment of the present invention can determine the world coordinate system through calibration between cameras and between cameras and the ground. The positional relationship between cameras can be calibrated by a T-shaped calibration rod, and the positional relationship between a camera and the ground can be calibrated by an L-shaped calibration rod. For example, Figure 2 is a spatial schematic diagram of the world coordinate system calibration provided by the present invention, such as Figure 2 As shown, four cameras are set up in total, and the distances between the four cameras are the same. Figure 2 The calibration rod in is an L-shaped calibration rod, which is used to establish a world coordinate system. The straight line corresponding to one right-angled side of the L-shaped calibration rod is the X-axis of the world coordinate system, the straight line corresponding to the other right-angled side of the L-shaped calibration rod is the Z-axis of the world coordinate system, and the straight line perpendicular to the plane where the L-shaped calibration rod is located is the Y-axis of the world coordinate system. That is, the initial coordinate point is the coordinate point in the world coordinate system, the initial spatial pose is the spatial pose in the world coordinate system, and the world coordinate system is determined based on the position of the image acquisition device.

[0043] Furthermore, the origin offset between the world coordinate system and the robotic arm coordinate system can be determined, and then all initial coordinate points in the world coordinate system can be converted to the robotic arm coordinate system corresponding to the robotic arm based on the origin offset to determine the coordinate point set; or, all initial spatial poses in the world coordinate system can be converted to the robotic arm coordinate system based on the origin offset to determine the spatial pose set.

[0044] For example, assuming that the initial coordinate point in the world coordinate system is for , the origin offset between the world coordinate system and the robot coordinate system is , first we can calculate the initial coordinate point Perform translation transformation to obtain the coordinate point after translation transformation , coordinate point It can be represented by a homogeneous matrix:

[0045] Furthermore, the coordinate points Rotation transformation, assuming that the angle of rotation of the world coordinate system around its own X axis is , and define is the rotation matrix of the world coordinate system around its own X axis, then It can be expressed by the following formula:

[0046] Assume that the angle of rotation of the world coordinate system around its own Y axis is , and define is the rotation matrix of the world coordinate system around its own Y axis, then It can be expressed by the following formula:

[0047] The angle of rotation of the world coordinate system around its own Z axis is , and define is the rotation matrix of the world coordinate system around its own Z axis, then It can be expressed by the following formula:

[0048] Coordinate Point Coordinate points in the robot coordinate system obtained by rotation transformation It can be determined by the following formula:

[0049] Optionally, the X-axis of the world coordinate system may be pre-calibrated to coincide with the base coordinate system of the robot coordinate system. In this case, the coordinate point in the robot coordinate system may be obtained by simply rotating the coordinate point after the translation transformation 90 degrees around the X-axis.

[0050] In the above embodiment, all initial coordinate points in the world coordinate system are converted to the robot arm coordinate system corresponding to the robot arm to determine the coordinate point set; or, all initial spatial poses in the world coordinate system are converted to the robot arm coordinate system to determine the spatial pose set. This embodiment can more accurately determine the coordinate point set after the coordinate system conversion, so that the subsequent robot arm can simulate the doctor's hand to perform rehabilitation training on the target user's lower limbs.

[0051] In one embodiment, determining the target rehabilitation training trajectory corresponding to the lower limb of the target user based on the coordinate point set or the spatial posture set includes: Connecting each coordinate point in the coordinate point set, or connecting each spatial posture in the spatial posture set, to determine a first rehabilitation training trajectory; Optimizing the first rehabilitation training trajectory based on a covariant Hamiltonian optimization algorithm (CHOMP) to determine a second rehabilitation training trajectory; The second rehabilitation training trajectory is interpolated with equal time intervals based on a time-optimal trajectory generation (TOTG) algorithm to determine the target rehabilitation training trajectory.

[0052] Specifically, the coordinate point set includes multiple coordinate points, and the spatial pose set includes multiple spatial poses. The coordinate points in the coordinate point set can be connected to determine the first rehabilitation training trajectory. Alternatively, the spatial poses in the spatial pose set can be connected to determine the first rehabilitation training trajectory. Among them, the algorithm in OMPL (Open MotionPlanning Library) can be used to connect the coordinate points in the coordinate point set, or to connect the spatial poses in the spatial pose set. OMPL is an open source robot motion planning library based on sampling method.

[0053] For example, Figure 4 is one of the schematic diagrams of the coordinate point set provided by the present invention, Figure 5 This is the second schematic diagram of the coordinate point set provided by the present invention. Figure 6 This is the third schematic diagram of the coordinate point set provided by the present invention, such as Figure 4 As shown, Figure 4 The yellow scattered points in are the projections of the coordinate points in the coordinate point set in the YZ plane, such as Figure 5 As shown, Figure 5 The green scattered points in are the projections of the coordinate points in the coordinate point set in the XZ plane, such as Figure 6 As shown, Figure 6 The purple scattered points in are the projections of the coordinate points in the coordinate point set in the XY plane.

[0054] Furthermore, the first rehabilitation training trajectory can be optimized based on the Covariant Hamilton Optimization (CHOMP) algorithm to determine the second rehabilitation training trajectory, and then the second rehabilitation training trajectory can be interpolated with equal time intervals based on the Time-optimal Trajectory Generation (TOTG) algorithm to determine the target rehabilitation training trajectory. Among them, CHOMP is a gradient-based trajectory optimization program, which is designed to be a motion planning algorithm based entirely on trajectory optimization and has a high optimization efficiency.

[0055] In the above embodiment, the first rehabilitation training trajectory is determined based on a set of coordinate points or a set of spatial postures, which can more accurately restore the doctor's hand movement trajectory, and then optimize the first rehabilitation training trajectory based on the covariant Hamiltonian optimization algorithm to obtain the second rehabilitation training trajectory, which has a high optimization efficiency. The second rehabilitation training trajectory is further interpolated with equal time intervals based on the time optimal trajectory generation algorithm. The target rehabilitation training trajectory output by the time optimal trajectory generation algorithm is a trajectory with equal time intervals. The speed and acceleration planned by the algorithm under small spacing are more reasonable and smoother than other optimization algorithms, and the planning of equal time intervals is also more in line with the actual situation of controlling the robotic arm.

[0056] Step 120: Controlling the robotic arm to perform rehabilitation training on the target user's lower limbs based on the target rehabilitation training trajectory.

[0057] Specifically, the host computer can control the mechanical arm to perform rehabilitation training on the lower limbs of the target user based on the target rehabilitation training trajectory. The host computer and the mechanical arm can communicate through the communication port, and the host computer can control the mechanical arm to achieve different functions through different communication ports.

[0058] In one embodiment, controlling the mechanical arm to perform rehabilitation training on the target user's lower limbs based on the target rehabilitation training trajectory includes: Determining a robotic arm motion instruction corresponding to the target rehabilitation training trajectory based on the target rehabilitation training trajectory; The robotic arm is controlled based on the robotic arm movement instruction to perform rehabilitation training on the lower limbs of the target user.

[0059] Specifically, the host computer can determine the manipulator motion instructions corresponding to the target rehabilitation training trajectory based on the target rehabilitation training trajectory, and the manipulator motion instructions can be determined based on the manipulator motion statement. The manipulator motion statement is a robot-related tool set software in the robot operating system unit, which is currently widely used in the development of various robots. The manipulator motion statement provides a convenient and practical platform for robot development, integrating a variety of databases, including motion planning, operation, three-dimensional perception, collision detection and navigation databases, and is a very convenient robot development platform. The manipulator motion instruction can control the manipulator to move to a specific posture. This process can be implemented through a planning request adapter. The planning request adapter is divided into a pre-processing adapter interface and a post-processing adapter interface. The main function of the pre-processing adapter interface is to deal with situations such as the starting state of the joint in the manipulator exceeds the joint limit and the sudden accident causes the force to exceed the set threshold, so as to ensure the safety of the manipulator during movement. The post-processing adapter interface can be used for collision detection.

[0060] Furthermore, the host computer can send robot arm movement instructions to the robot arm, and then control the robot arm to perform rehabilitation training on the target user's lower limbs based on the robot arm movement instructions. The robot arm can also feedback the current state to the host computer after completing the action corresponding to the robot arm movement instruction.

[0061] For example, assuming that the robotic arm is a six-degree-of-freedom robotic arm, Figure 7 is a schematic diagram of the displacement curve of the mechanical arm joint provided by the present invention, Figure 8 Schematic diagram of the speed curve of the mechanical arm joint provided by the present invention. Figure 7 and Figure 8 The six-degree-of-freedom robot includes robot joint 1, robot joint 2, robot joint 3, robot joint 4, robot joint 5 and robot joint 6. The displacement curves of each robot joint are as follows: Figure 7 As shown, the speed curve is Figure 8 As shown, it can be seen that the robotic arm can basically complete smooth and continuous movement.

[0062] In the above embodiment, the robotic arm movement instructions corresponding to the target rehabilitation training trajectory can be determined based on the target rehabilitation training trajectory, and then the robotic arm can be controlled based on the robotic arm movement instructions to perform rehabilitation training on the target user's lower limbs, which can meet the needs of the target user and perform rehabilitation training on the target user's lower limbs through the target rehabilitation training trajectory corresponding to the target user's lower limbs.

[0063] In one embodiment, the robotic arm is a six-degree-of-freedom robotic arm; the six-degree-of-freedom robotic arm is configured with a target robotic arm model; the target robotic arm model is determined by the following steps: Constructing a forward kinematics model and an inverse kinematics model based on the geometric parameters corresponding to each joint in the six-degree-of-freedom robotic arm; The target robot arm model is determined based on the forward kinematics model and the inverse kinematics model.

[0064] Specifically, the robot arm in the present invention may be a six-degree-of-freedom robot arm, which includes six joints. The six-degree-of-freedom robot arm is configured with a target robot arm model. The robot arm motion instructions in the aforementioned embodiment are instructions corresponding to the target robot arm model.

[0065] The target robot model can be determined by the following steps: First, the forward kinematics model and the inverse kinematics model can be constructed based on the geometric parameters corresponding to each joint in the six-degree-of-freedom manipulator, wherein the geometric parameters may include: the length of the connecting rod between the joints, the relative torsion angle between the joint axes, the offset between the joints, and the joint angle.

[0066] For example, the connecting rod length Indicates along Axis direction from joint To joints Distance, relative twist angle Represents the joint axis and The relative torsion angle, offset Indicates from the joint To joints The joints in the six-degree-of-freedom robot also include rotational joints and sliding joints. For rotational joints, the offset is a constant, for sliding joints, the offset is the variable, joint angle Indicates joints The rotation angle at the joint Around joint axis The above parameters can be set as shown in Table 1 below: Table 1 Geometric parameter example table

[0067] The general transformation formula for constructing the forward kinematics model is as follows:

[0068] in, Indicates winding Axis rotation The rotation matrix of Indicates along Axis movement The translation matrix, Indicates winding Axis rotation The rotation matrix of Indicates along Axis movement The translation matrix of .

[0069] Furthermore, the forward kinematics model can be expressed by the following formula:

[0070] .

[0071] Furthermore, for the convenience of description, the following conventions are made:

[0072] .

[0073] Then we can get the following formula (1):

[0074] Formula (1): .

[0075] .

[0076] Furthermore, the left side of formula (1) can be expressed as follows: .

[0077] The right side of formula (1) can be expressed as follows: .

[0078] From the above, we can get the following formulas ①, ② and ③: .

[0079] Simplifying formula ①, we get , and then make ,but , can be obtained , we can get from formula ② , solve formula ③, ,but , can be obtained .

[0080] The final inverse kinematics model is: ; ; ; ; ; .

[0081] Then, after constructing the forward kinematics model and the inverse kinematics model, the target robotic arm model can be determined based on the forward kinematics model and the inverse kinematics model.

[0082] Optionally, the operator can also freely control the robotic arm through a visual interactive device.

[0083] In the above embodiment, the robotic arm can be a six-degree-of-freedom robotic arm with high flexibility. Most existing robotic arms have three degrees of freedom and simple movements, which cannot meet the rehabilitation training needs of most patients. In addition, based on the geometric parameters corresponding to each joint in the six-degree-of-freedom robotic arm, a forward kinematics model and an inverse kinematics model are constructed, and then the target robotic arm model is determined based on the forward kinematics model and the inverse kinematics model, which can ensure the safety of the rehabilitation training process and improve the accuracy of control and the diversity of rehabilitation training.

[0084] The human lower limb rehabilitation training method provided by the present invention first obtains the coordinate point set or spatial posture set corresponding to the doctor's hand during the doctor's rehabilitation training of the target user's lower limbs through an image acquisition device, and then determines the target rehabilitation training trajectory corresponding to the target user's lower limbs based on the coordinate point set or the spatial posture set, and then controls the mechanical arm to perform rehabilitation training on the target user's lower limbs based on the target rehabilitation training trajectory. The technical solution of the present invention can control the mechanical arm to perform rehabilitation training on the target user's lower limbs according to the target rehabilitation training trajectory corresponding to the target user's lower limbs, has a high degree of automation, reduces labor costs, and can meet the special training needs of the target user.

[0085] Optionally, the present invention may also provide a rehabilitation training system, Fig. 9 is a schematic diagram of the rehabilitation training system provided by the present invention, such as Fig. 9 As shown, the rehabilitation training system includes four high-precision capture cameras, aluminum alloy profiles, rehabilitation manipulators, manipulator teaching devices, experimental beds, manipulator control boxes, manipulator stabilization discs and four Forma wheels. The relative positions of the four high-precision capture cameras are fixed. The rehabilitation training system is provided with Forma wheels to ensure the flexibility of the rehabilitation training system when moving and the stability of the rehabilitation training system when working statically. The present invention uses engineering modeling software to design the rehabilitation training system, and uses finite element analysis to perform mechanical simulation verification. It has been verified that the rehabilitation training system has good strength and stability. In addition, the flexible connection between the end of the rehabilitation manipulator and the lower limbs of the human body can be adopted with an ankle joint fixation brace. In the rehabilitation training system, the rehabilitation manipulator is arranged next to the experimental bed, which is convenient for patients to perform sitting and lying rehabilitation training on the bed, avoiding the inconvenience of patients leaving the experimental bed for rehabilitation training, and reducing the psychological burden of patients to a certain extent. The rehabilitation training system is mainly aimed at early passive lower limb rehabilitation training for patients with hemiplegia and stroke. The rehabilitation training system can also perform a variety of rehabilitation training for multiple parts such as knee joints, hip joints and ankle joints, which can meet the rehabilitation needs of different patients. The rehabilitation training system can also adopt multiple safety protection measures, such as electronic limit and torque protection, to ensure the safety of patients during rehabilitation training. In addition, the rehabilitation training system can also record the patient's rehabilitation data, including range of motion, number of exercises and exercise speed, so that doctors can quantitatively evaluate the rehabilitation effect and adjust the personalized rehabilitation plan in time.

[0086] The present invention can also collect the robot arm's reproduced trajectory and compare the doctor's hand trajectory with the robot arm's reproduced trajectory. Fig.10 One of the schematic diagrams of the comparison between the doctor's hand trajectory and the robot arm's reproduction trajectory provided by the present invention, Fig.11 The second schematic diagram of the comparison between the doctor's hand trajectory and the robot arm's reproduction trajectory provided by the present invention, Fig.12 The third schematic diagram of the comparison between the doctor's hand trajectory and the robot arm's reproduction trajectory provided by the present invention. Fig.10 , Fig.11 and Fig.12 As shown, the blue trajectory is the doctor's hand movement trajectory, and the orange-red is the robotic arm reproduction trajectory. It can be seen that although there is an error between the doctor's hand trajectory and the robotic arm reproduction trajectory, the error is small and within the allowable range.

[0087] The human lower limb rehabilitation training device provided by the present invention is described below. The human lower limb rehabilitation training device described below and the human lower limb rehabilitation training method described above can be referenced to each other.

[0088] Fig.13 Schematic diagram of the structure of the human lower limb rehabilitation training device provided by the present invention. Fig.13 As shown, the human lower limb rehabilitation training device 1300 includes the following modules: A determination module 1310 is used to obtain, through an image acquisition device, a set of coordinate points or a set of spatial postures corresponding to the hands of the physician during the rehabilitation training of the lower limbs of the target user by the physician, and determine a target rehabilitation training trajectory corresponding to the lower limbs of the target user based on the set of coordinate points or the set of spatial postures; The control module 1320 is used to control the robot arm to perform rehabilitation training on the lower limbs of the target user based on the target rehabilitation training trajectory.

[0089] In one embodiment, the determination module 1310 is specifically configured to: Acquiring, by means of the image acquisition device, a plurality of initial coordinate points or a plurality of initial spatial postures corresponding to the hands of the physician during the rehabilitation training of the lower limbs of the target user by the physician; The coordinate point set or the spatial pose set is determined based on all the initial coordinate points or all the initial spatial poses.

[0090] In one embodiment, the initial coordinate point is a coordinate point in a world coordinate system, the initial spatial pose is a spatial pose in the world coordinate system, the world coordinate system is determined based on the position of the image acquisition device, and the determination module 1310 is further specifically used for: All initial coordinate points in the world coordinate system are converted to the robotic arm coordinate system corresponding to the robotic arm to determine the coordinate point set; or all initial spatial poses in the world coordinate system are converted to the robotic arm coordinate system to determine the spatial pose set.

[0091] In one embodiment, the determination module 1310 is further configured to: Connecting each coordinate point in the coordinate point set, or connecting each spatial posture in the spatial posture set, to determine a first rehabilitation training trajectory; Optimizing the first rehabilitation training trajectory based on a covariant Hamiltonian optimization algorithm to determine a second rehabilitation training trajectory; The second rehabilitation training trajectory is interpolated with equal time intervals based on a time optimal trajectory generation algorithm to determine the target rehabilitation training trajectory.

[0092] In one embodiment, the control module 1320 is specifically configured to: Determining a robotic arm motion instruction corresponding to the target rehabilitation training trajectory based on the target rehabilitation training trajectory; The robotic arm is controlled based on the robotic arm movement instruction to perform rehabilitation training on the lower limbs of the target user.

[0093] In one embodiment, the robotic arm is a six-degree-of-freedom robotic arm; the six-degree-of-freedom robotic arm is configured with a target robotic arm model; the robotic arm motion instruction is an instruction corresponding to the target robotic arm model; the target robotic arm model is determined by the following steps: Constructing a forward kinematics model and an inverse kinematics model based on the geometric parameters corresponding to each joint in the six-degree-of-freedom robotic arm; The target robot arm model is determined based on the forward kinematics model and the inverse kinematics model.

[0094] The human lower limb rehabilitation training device provided by the present invention first obtains the coordinate point set or spatial posture set corresponding to the doctor's hand during the doctor's rehabilitation training of the target user's lower limbs through an image acquisition device, and then determines the target rehabilitation training trajectory corresponding to the target user's lower limbs based on the coordinate point set or the spatial posture set, and then controls the mechanical arm to perform rehabilitation training on the target user's lower limbs based on the target rehabilitation training trajectory. The technical solution of the present invention can control the mechanical arm to perform rehabilitation training on the target user's lower limbs according to the target rehabilitation training trajectory corresponding to the target user's lower limbs, with a high degree of automation, reducing labor costs, and being able to meet the special training needs of the target user.

[0095] Fig.14 An example of a physical structure diagram of an electronic device is shown in FIG. Fig.14As shown, the electronic device may include: a processor 1410, a communications interface 1420, a memory 1430 and a communication bus 1440, wherein the processor 1410, the communications interface 1420 and the memory 1430 communicate with each other through the communication bus 1440. The processor 1410 may call the logic instructions in the memory 1430 to execute the human lower limb rehabilitation training method, which includes: Acquire, by an image acquisition device, a set of coordinate points or a set of spatial postures corresponding to the hands of the physician during the rehabilitation training of the lower limbs of the target user by the physician, and determine a target rehabilitation training trajectory corresponding to the lower limbs of the target user based on the set of coordinate points or the set of spatial postures; Based on the target rehabilitation training trajectory, the robotic arm is controlled to perform rehabilitation training on the lower limbs of the target user.

[0096] In addition, the logic instructions in the above-mentioned memory 1430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk.

[0097] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored on a non-transitory computer-readable storage medium, when the computer program is executed by a processor, the computer can execute the human lower limb rehabilitation training method provided by the above methods, the method comprising: Acquire, by an image acquisition device, a set of coordinate points or a set of spatial postures corresponding to the hands of the physician during the rehabilitation training of the lower limbs of the target user by the physician, and determine a target rehabilitation training trajectory corresponding to the lower limbs of the target user based on the set of coordinate points or the set of spatial postures; Based on the target rehabilitation training trajectory, the robotic arm is controlled to perform rehabilitation training on the lower limbs of the target user.

[0098] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the computer program is executed by a processor to perform the human lower limb rehabilitation training method provided by the above methods, the method comprising: Acquire, by an image acquisition device, a set of coordinate points or a set of spatial postures corresponding to the hands of the physician during the rehabilitation training of the lower limbs of the target user by the physician, and determine a target rehabilitation training trajectory corresponding to the lower limbs of the target user based on the set of coordinate points or the set of spatial postures; Based on the target rehabilitation training trajectory, the robotic arm is controlled to perform rehabilitation training on the lower limbs of the target user.

[0099] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0100] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for lower limb rehabilitation training, characterized in that: include: Acquire, by an image acquisition device, a set of coordinate points or a set of spatial postures corresponding to the hands of the physician during the rehabilitation training of the lower limbs of the target user by the physician, and determine a target rehabilitation training trajectory corresponding to the lower limbs of the target user based on the set of coordinate points or the set of spatial postures; Based on the target rehabilitation training trajectory, the robotic arm is controlled to perform rehabilitation training on the lower limbs of the target user.

2. The human lower limb rehabilitation training method according to claim 1, characterized in that: The method of obtaining, by means of an image acquisition device, a set of coordinate points or a set of spatial postures corresponding to the hands of the physician during the rehabilitation training of the lower limbs of the target user by the physician includes: Acquiring, by means of the image acquisition device, a plurality of initial coordinate points or a plurality of initial spatial postures corresponding to the hands of the physician during the rehabilitation training of the lower limbs of the target user by the physician; The coordinate point set or the spatial pose set is determined based on all the initial coordinate points or all the initial spatial poses.

3. The human lower limb rehabilitation training method according to claim 2, characterized in that: The initial coordinate point is a coordinate point in a world coordinate system, and the initial spatial posture is a spatial posture in the world coordinate system, and the world coordinate system is determined based on the position of the image acquisition device; The determining the coordinate point set or the spatial pose set based on all the initial coordinate points or all the initial spatial poses comprises: Convert all initial coordinate points in the world coordinate system to the robot coordinate system corresponding to the robot arm to determine the coordinate point set; Alternatively, all initial spatial poses in the world coordinate system are converted to the robot arm coordinate system to determine the spatial pose set.

4. The human lower limb rehabilitation training method according to claim 2, characterized in that: The determining of a target rehabilitation training trajectory corresponding to the lower limbs of a target user based on the coordinate point set or the spatial posture set includes: Connecting each coordinate point in the coordinate point set, or connecting each spatial posture in the spatial posture set, to determine a first rehabilitation training trajectory; Optimizing the first rehabilitation training trajectory based on a covariant Hamiltonian optimization algorithm to determine a second rehabilitation training trajectory; The second rehabilitation training trajectory is interpolated with equal time intervals based on a time optimal trajectory generation algorithm to determine the target rehabilitation training trajectory.

5. The human lower limb rehabilitation training method according to any one of claims 1 to 4, characterized in that: The controlling the mechanical arm to perform rehabilitation training on the lower limbs of the target user based on the target rehabilitation training trajectory includes: Determining a robotic arm motion instruction corresponding to the target rehabilitation training trajectory based on the target rehabilitation training trajectory; The robotic arm is controlled based on the robotic arm movement instruction to perform rehabilitation training on the lower limbs of the target user.

6. The human lower limb rehabilitation training method according to claim 5, characterized in that: The robotic arm is a six-degree-of-freedom robotic arm; the six-degree-of-freedom robotic arm is configured with a target robotic arm model; the robotic arm motion instruction is an instruction corresponding to the target robotic arm model; the target robotic arm model is determined by the following steps: Constructing a forward kinematics model and an inverse kinematics model based on the geometric parameters corresponding to each joint in the six-degree-of-freedom robotic arm; The target robot arm model is determined based on the forward kinematics model and the inverse kinematics model.

7. A human lower limb rehabilitation training device, characterized in that: include: A determination module, configured to obtain, through an image acquisition device, a set of coordinate points or a set of spatial postures corresponding to the hands of the physician during the rehabilitation training of the lower limbs of the target user by the physician, and determine a target rehabilitation training trajectory corresponding to the lower limbs of the target user based on the set of coordinate points or the set of spatial postures; A control module is used to control the robotic arm to perform rehabilitation training on the lower limbs of the target user based on the target rehabilitation training trajectory.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the human lower limb rehabilitation training method as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the human lower limb rehabilitation training method as claimed in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the human lower limb rehabilitation training method as claimed in any one of claims 1 to 6 is implemented.

Images