Multi-joint mechanical arm standing assisting track planning method and system for stroke rehabilitation

Abstract

The invention provides a multi-joint mechanical arm standing assisting track planning method and system for stroke rehabilitation. The method comprises the following steps: firstly, acquiring real-time gravity center shift data through a seat and a pressure sensing array at the feet of a patient; secondly, acquiring a real-time pelvic inclination angle of the patient in a sitting posture state and surface electromyogram signals of main muscle groups of lower limbs to generate a standing intention triggering instruction; a pre-established individualized dyskinesia model is called according to the standing intention triggering instruction; then, combining the individualized dyskinesia model and the real-time gravity center shift data to generate a mechanical arm standing assisting track; and finally, the joint motion sequence of the multi-joint mechanical arm is calculated according to the mechanical arm standing assisting track. According to the technical scheme provided by the invention, self-adaptive precise assistance of the mechanical arm on the standing process of the stroke patient is realized through multi-modal physiological signal fusion and personalized parameter dynamic adjustment, and the safety, adaptability and active participation of rehabilitation training are effectively improved.

Description

Technical Field

[0001] This application relates to the field of intelligent rehabilitation technology, and in particular to a method and system for trajectory planning of a multi-joint robotic arm for stroke rehabilitation. Background Technology

[0002] In the rehabilitation training of stroke patients, assisting them to complete the action of standing up from a sitting position is an important part. This process requires rehabilitation equipment to accurately identify the patient's intention and provide personalized assistive force that matches their residual muscle strength in order to complete the training safely and effectively.

[0003] Existing technical solutions employ pre-programmed, fixed-path multi-joint robotic arms to assist patients in standing up by setting a uniform standing path and constant support force.

[0004] However, this existing approach, by adopting a fixed and unchanging assistive mode, cannot adapt in real time to the dynamic changes in muscle strength and body stability of different patients or the same patient at different training stages. This may result in insufficient assistive force to complete the standing up, or excessive assistive force to weaken the patient's sense of active participation, making it difficult to achieve truly personalized and adaptive rehabilitation training. Summary of the Invention

[0005] This application provides a method and system for trajectory planning of a multi-joint robotic arm for stroke rehabilitation, which solves the problem that existing robotic arm assistance schemes using pre-programmed fixed trajectories cannot adapt to the dynamic changes in the patient's muscle strength and body stability in real time, resulting in inaccurate matching of assistive force and difficulty in promoting the patient's active participation in rehabilitation training.

[0006] Firstly, this application provides a method for trajectory planning of a multi-joint robotic arm for stroke rehabilitation, including: Real-time center of gravity shift data of stroke patients during the process of standing up is collected by a pressure sensor array set on the seat and the feet of the stroke patient. Acquire real-time pelvic tilt angle and surface electromyography signals of major lower limb muscle groups in stroke patients in a sitting position; Based on the real-time pelvic tilt angle and surface electromyography signal, a command to trigger the intention to stand up is generated. The pre-established individualized motor dysfunction model of stroke patients is retrieved based on the standing intention trigger command; By combining the individualized motor dysfunction model with the real-time center of gravity offset data, a robotic arm lifting trajectory with a variable support force vector is generated. The joint motion sequence of the multi-joint robotic arm is calculated based on the robotic arm's lifting trajectory.

[0007] Optionally, real-time center of gravity shift data during the stroke patient's standing process is collected via a pressure sensor array positioned between the seat and the stroke patient's feet, including: The pressure sensing array includes multiple pressure sensing units distributed on the seat surface in contact with the soles of the stroke patient's feet. Acquire the pressure measurement values ​​synchronously measured by the multiple pressure sensing units; Calculate the instantaneous pressure center coordinates on the seat plane and the double-foot support plane based on the pressure measurement values; Based on the instantaneous pressure center coordinates on the seat plane and the foot support plane, and the predefined relative spatial relationship between the seat and the foot support plane, the offset vector of the composite center of gravity projection point relative to the standard standing posture of the human body is calculated. The offset vector is used as real-time center of gravity offset data to characterize the stability of the standing movement of stroke patients.

[0008] Optionally, real-time pelvic tilt angle and surface electromyography (EMG) signals of major lower limb muscle groups are acquired in a sitting position in stroke patients, including: A motion measurement sensor installed on the pelvic region of a stroke patient directly measures the change in the tilt angle of the pelvis in three-dimensional space to obtain the real-time pelvic tilt angle. Multiple surface electrodes are attached to the skin surface of target muscle groups in the lower limbs of stroke patients, and electrical signals generated by muscle activity are continuously collected through the surface electrodes. The collected electrical signals are rectified and smoothed to form surface electromyography signals that can reflect the degree of muscle activation. The real-time pelvic tilt angle collected at the same time is time-synchronized with the surface electromyography signal to form synchronous data characterizing the movement intention and posture of stroke patients.

[0009] Optionally, a standing intention trigger command is generated based on the real-time pelvic tilt angle and surface electromyography signal, including: Determine whether the real-time pelvic tilt angle exceeds the preset angle that represents the initial stage of the standing up movement; Simultaneously, it is determined whether the signal intensity of the target muscle group related to hip and knee extension movements in the surface electromyography signal exceeds the resting level; When the real-time pelvic tilt angle exceeds the preset angle and the signal intensity of the target muscle group exceeds the resting level, it is determined that the stroke patient has a clear intention to stand up. Generate a start-up intention trigger command to initiate the robotic arm assisted start-up procedure.

[0010] Optionally, a pre-established individualized motor dysfunction model for stroke patients is retrieved based on the standing intention trigger command, including: In response to the standing intention trigger command, obtain the current stroke patient's identification information; Based on the identity information, the corresponding individualized motor function disorder model is retrieved from the pre-stored model library; The individualized motor dysfunction model includes parameters specific to stroke patients, such as muscle strength asymmetry, joint range of motion limitation, and motor coordination pattern. The retrieved individualized motor dysfunction model is loaded into the robotic arm control system to provide stroke patient-specific parameters for generating the robotic arm's assisted lifting trajectory.

[0011] Optionally, by combining the individualized motor dysfunction model with the real-time center of gravity offset data, a robotic arm assisted lifting trajectory with a variable support force vector is generated, including: Based on the muscle asymmetry parameters included in the individualized motor dysfunction model, the initial support force distribution ratio of the robotic arm on both sides of the stroke patient's trunk is determined. Based on the changes in body stability reflected by the real-time center of gravity offset data, the initial support force distribution ratio is dynamically adjusted to obtain the adjusted support force distribution ratio. Based on the joint range of motion limitation parameters included in the individualized motor dysfunction model, the upper limit of the motion speed of the robotic arm end effector is set; The adjusted support force distribution ratio and the upper limit of movement speed are integrated into the standard standing trajectory template to form the robotic arm assisted standing trajectory with variable support force vector.

[0012] Optionally, the joint motion sequence of the multi-joint robotic arm is calculated based on the robotic arm's lifting trajectory, including: Based on the sequence of spatial path points of the end effector defined in the lifting trajectory of the robotic arm, and the structural parameters of the multi-joint robotic arm, calculate the angle that each joint needs to rotate at each path point; Arrange the calculated joint angles at each path point in chronological order to form a complete joint motion sequence. Based on the motion coordination mode parameters contained in the individualized motor dysfunction model, the rate of change of angle of each joint in the joint motion sequence is coordinated and adjusted to obtain the adjusted joint motion sequence. The adjusted joint motion sequence is converted into control commands for the motors of each joint of the multi-joint robotic arm.

[0013] Secondly, this application provides a multi-joint robotic arm trajectory planning system for stroke rehabilitation, comprising: The data acquisition module is used to collect real-time center of gravity shift data of stroke patients during the process of standing up by using a pressure sensor array set at the seat and the feet of the stroke patient. The acquisition module is used to acquire the real-time pelvic tilt angle and surface electromyography signals of the main muscle groups of the lower limbs of stroke patients in a sitting position. The generation module is used to generate a standing intention trigger command based on the real-time pelvic tilt angle and surface electromyography signal; The retrieval module is used to retrieve a pre-established individualized motor dysfunction model of a stroke patient based on the standing intention trigger command; The module is used to combine the individualized motor dysfunction model with the real-time center of gravity offset data to generate a robotic arm lifting trajectory with a variable support force vector. The calculation module is used to calculate the joint motion sequence of the multi-joint robotic arm based on the robotic arm's lifting trajectory.

[0014] Thirdly, this application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a stroke rehabilitation multi-joint robotic arm assisted lifting trajectory planning method as described in the first aspect above.

[0015] Fourthly, this application provides a computer storage medium storing a computer program, which, when executed by a computer, implements a trajectory planning method for a multi-joint robotic arm used in stroke rehabilitation as described in the first aspect.

[0016] This application achieves accurate identification of stroke patients' intention to stand and personalized assessment of their motor abilities by integrating multimodal information such as center of gravity offset data, pelvic tilt angle, and surface electromyography signals collected by a pressure sensor array. By combining a pre-established individualized motor dysfunction model with real-time center of gravity data, a robotic arm-assisted standing trajectory with dynamically adjusted support force vector is generated, effectively solving the problem that traditional pre-programmed fixed trajectories cannot adapt to changes in the patient's real-time state, and significantly improving the adaptability and safety of rehabilitation training.

[0017] Furthermore, by converting the robotic arm's assisted-lift trajectory into a specific joint motion sequence and coordinating the motion rate of each joint according to individualized motion coordination mode parameters, it is ensured that the assisted-lift action output by the robotic arm conforms to the patient's unique motion pattern and ability limitations. The resulting joint motor control commands can drive the robotic arm to perform assisted movements that are highly matched with the patient's real-time physiological state, thereby ensuring the safety of the exercise while promoting the patient's active participation in training and improving the rehabilitation effect.

[0018] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart of a stroke rehabilitation multi-joint robotic arm trajectory planning method provided in this application is shown; Figure 2 This invention provides a schematic diagram of the structure of a multi-joint robotic arm trajectory planning system for stroke rehabilitation. Figure 3 A schematic diagram of the structure of a computing device provided in this application is shown. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present application, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0022] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. However, it should be clearly understood that these operations may not be executed in the order they appear herein, or may be executed in parallel. The operation numbers, such as 101, 102, etc., are merely used to distinguish different operations and do not themselves represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the descriptions such as "first," "second," etc., in this document are used to distinguish different messages, devices, modules, etc., and do not represent a chronological order, nor do they limit "first" and "second" to different types.

[0023] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] Figure 1 This application provides a flowchart of a method for assisted lifting trajectory planning for a multi-joint robotic arm used in stroke rehabilitation, as shown in the flowchart. Figure 1 As shown, the method includes: Step 101: Collect real-time center of gravity shift data of the stroke patient during the process of standing up by using a pressure sensor array set on the seat and the foot of the stroke patient.

[0025] Optionally, step 101 may specifically include the following steps: Step 1011, the pressure sensing array includes multiple sets of pressure sensing units distributed on the seat surface in contact area with the sole of the stroke patient's foot; Step 1012: Obtain the pressure measurement values ​​synchronously measured by the multiple pressure sensing units; Step 1013: Calculate the instantaneous pressure center coordinates on the seat plane and the double-foot support plane based on the pressure measurement values; Step 1014: Based on the instantaneous pressure center coordinates on the seat plane and the foot support plane, and the predefined relative spatial relationship between the seat and the foot support plane, calculate the offset vector of the composite center of gravity projection point relative to the standard standing posture of the human body. Step 1015: Use the offset vector as real-time center of gravity offset data to characterize the stability of the stroke patient's standing movement.

[0026] In the above scheme, the pressure sensor array refers to a measurement system composed of multiple pressure sensor units arranged on the seat surface and the patient's foot contact area, used to collect pressure distribution data; real-time center of gravity offset data refers to the offset vector obtained by calculation, used to characterize the stability of the patient's center of gravity relative to the standard standing posture during the patient's standing process; the foot contact area refers to the area where the patient's feet contact the support surface; multiple pressure sensor units refer to multiple independent pressure sensors distributed on the seat and foot; pressure measurement value refers to the pressure value collected in real time by each sensor unit; instantaneous pressure center coordinates refer to the coordinates of the pressure concentration point on the seat plane and the foot support plane calculated based on the pressure measurement value; relative spatial relationship refers to the position and posture relationship between the predefined seat plane and the foot support plane; center of gravity projection point refers to the projection position of the body's center of gravity on the support plane obtained by synthetic calculation; offset vector refers to the direction and magnitude of the deviation of the center of gravity projection point from the ideal standing posture; characterizing the stability of the stroke patient's standing action refers to reflecting the patient's body balance during the standing process through the offset vector.

[0027] In this scheme, firstly, step 1011 begins by using multiple sets of pressure sensing units distributed across the seat surface and the patient's foot contact area in a pressure sensing array. These sensors are arranged in an array to ensure coverage of the main pressure sensing area. Secondly, step 1012 synchronously acquires real-time pressure measurements from all pressure sensing units to ensure data consistency. Then, step 1013 uses these pressure measurements to calculate the instantaneous pressure center coordinates on the seat plane and the foot support plane, respectively. These coordinates reflect the location of the center point of pressure distribution on each plane. Next, step 1014 combines the predefined relative spatial relationship between the seat and the foot support plane to synthesize the instantaneous pressure center coordinates of the two planes, obtaining the overall center of gravity projection point, and further calculates the offset vector of this projection point relative to the standard standing posture of the human body. Finally, step 1015 outputs this offset vector as real-time center of gravity offset data for subsequent analysis of the stability of the patient's standing movement.

[0028] For example, in a rehabilitation training scenario, a patient sits on a rehabilitation chair equipped with a pressure sensor array. When the patient begins to try to stand up, multiple pressure sensor units on the seat surface and foot area simultaneously collect pressure data. The system calculates the coordinates of the pressure center points of the seat and feet based on this data, and then, combined with the known height and angle relationship between the seat and the ground, calculates the patient's real-time center of gravity projection position. By comparing this position with the ideal center of gravity position of a standard standing posture, real-time center of gravity offset data reflecting the body's balance is generated.

[0029] This solution uses a multi-region pressure sensor array to synchronously collect pressure data. After coordinate calculation and spatial synthesis processing, it can accurately obtain the real-time changes in the patient's center of gravity during the process of standing up. This provides a reliable data foundation for assessing movement stability and providing personalized assistance, effectively improving the safety and adaptability of rehabilitation training.

[0030] Step 102: Obtain the real-time pelvic tilt angle and surface electromyography signals of the main muscle groups of the lower limbs in the sitting position of the stroke patient.

[0031] Optionally, step 102 may specifically include the following steps: Step 1021: The motion measurement sensor installed on the pelvic part of the stroke patient directly measures the change of the tilt angle of the pelvis in three-dimensional space to obtain the real-time pelvic tilt angle. Step 1022: Attach multiple surface electrodes to the skin surface of the target muscle groups in the lower limbs of the stroke patient, and continuously collect electrical signals generated by muscle activity through the surface electrodes. Step 1023: The collected electrical signals are rectified and smoothed to form surface electromyography signals that can reflect the degree of muscle activation. Step 1024: The real-time pelvic tilt angle collected at the same time is time-synchronized with the surface electromyography signal to form synchronous data characterizing the stroke patient's movement intention and posture.

[0032] In the above scheme, the real-time pelvic tilt angle refers to the change in the tilt angle of the pelvis in three-dimensional space, which is directly measured by a motion measurement sensor; the surface electromyography signal refers to the muscle electrical signal collected by surface electrodes and processed, reflecting the degree of muscle activation; the motion measurement sensor refers to the sensing device installed on the patient's pelvic area to measure changes in posture; three-dimensional space refers to a three-dimensional spatial coordinate system with length, width, and height; multiple surface electrodes refer to multiple signal acquisition points attached to the skin surface; the target muscle group skin surface refers to the skin area corresponding to the main muscle groups of the lower limb; and the electrical signal refers to the original bioelectrical signal generated when the muscle contracts.

[0033] In this scheme, firstly, step 1021 involves fixing a motion measurement sensor to the patient's pelvis. This sensor directly measures the change in the tilt angle of the pelvis in three-dimensional space, obtaining real-time pelvic tilt angle data. Secondly, step 1022 involves attaching multiple surface electrodes to the skin surface of the target muscle groups in the patient's lower limbs, continuously collecting raw electrical signals generated during muscle activity through these electrodes. Then, step 1023 involves rectifying the collected raw electrical signals to convert AC signals to DC signals, followed by smoothing to eliminate noise interference, ultimately forming surface electromyography (EMG) signals that accurately reflect the degree of muscle activation. Finally, step 1024 involves time-synchronizing the real-time pelvic tilt angle collected at the same time point with the processed surface EMG signals, forming synchronized data that comprehensively characterizes the patient's movement intention and body posture.

[0034] Following the specific implementation of the previous solution, during rehabilitation training, the patient wears a motion measurement sensor installed in the pelvis, and surface electrodes are attached to the skin surface of the main muscle groups of the lower limbs. When the patient is about to stand up, the sensor monitors the change in pelvic angle in real time, and the electrodes synchronously collect muscle electrical signals. After rectifying and smoothing the raw electrical signals, the system aligns the processed electromyographic signals with the pelvic tilt angle data at the same time to form synchronized movement intention and posture data.

[0035] This approach uses multi-sensor synchronous acquisition and signal processing to obtain precise pelvic movement posture and muscle activation data, providing a reliable multimodal data foundation for accurately identifying patients' movement intentions and assessing their movement abilities, effectively improving the accuracy and adaptability of rehabilitation training.

[0036] Step 103: Generate a standing intention trigger command based on the real-time pelvic tilt angle and surface electromyography signal.

[0037] Optionally, step 103 may specifically include the following steps: Step 1031: Determine whether the real-time pelvic tilt angle exceeds the preset angle representing the initial stage of the standing up movement; Step 1032: Simultaneously determine whether the signal intensity of the target muscle group related to hip and knee extension movements in the surface electromyography signal exceeds the resting level; Step 1033: When the real-time pelvic tilt angle exceeds the preset angle and the signal intensity of the target muscle group exceeds the resting level, it is determined that the stroke patient has a clear intention to stand up. Step 1034: Generate a start intention trigger command to initiate the robotic arm assisted start procedure.

[0038] In the above scheme, the standing intention trigger command refers to the start signal generated when the system confirms that the patient has a clear intention to stand up; the preset angle characterizing the initial stage of the standing action refers to the pelvic tilt angle threshold set according to ergonomics; the hip and knee extension action refers to the extension movement of the hip and knee joints of the lower limbs; the resting level refers to the reference value of the electrical signal generated by the muscles in a relaxed state; and the robotic arm assisted standing program refers to the software program that controls the robotic arm to perform assisted standing actions.

[0039] In this scheme, firstly, step 1031 compares the real-time acquired pelvic tilt angle with a pre-set angle threshold, which represents the typical range of pelvic tilt angles at the start of the standing motion. Secondly, step 1032 simultaneously analyzes the signals of specific muscle groups related to hip and knee extension movements in the surface electromyography (EMG) signals, comparing the intensity of these signals with pre-established baseline values ​​for muscle resting states. Then, step 1033, when the system detects that the pelvic tilt angle exceeds the preset threshold and the intensity of the related muscle group signals simultaneously exceeds the resting level, comprehensively determines that the patient has indeed generated a clear intention to stand. Finally, step 1034 generates a standing intention trigger command based on this determination result, which triggers the start of the robotic arm-assisted standing program.

[0040] Following the specific implementation of the previous solution, during the rehabilitation training process, the system continuously monitors the patient's pelvic tilt angle and surface electromyography signals; when the system detects that the anterior pelvic tilt angle reaches 15 degrees and the signal intensity of the anterior thigh muscle group is significantly higher than that in the resting state, the system determines that the patient is attempting to stand up; then it generates a standing intention trigger command, which is sent to the robotic arm control system to start the assisted standing program.

[0041] This solution uses a multi-parameter collaborative judgment mechanism to accurately identify the patient's intention to stand up, avoiding false triggering and missed triggering, ensuring the accuracy of the robotic arm's assistance timing, and providing the patient with timely and appropriate support for standing up.

[0042] Step 104: Retrieve the pre-established individualized motor dysfunction model of stroke patients according to the standing intention trigger command.

[0043] Optionally, step 104 may specifically include the following steps: Step 1041: In response to the standing intention trigger command, obtain the current stroke patient's identification information; Step 1042: Retrieve the corresponding individualized motor dysfunction model from the pre-stored model library based on the identity information; Step 1043, the individualized motor dysfunction model includes muscle strength asymmetry parameters, joint range of motion limitation parameters, and motor coordination pattern parameters specific to stroke patients; Step 1044: The retrieved individualized motor dysfunction model is loaded into the robotic arm control system to provide stroke patient-specific parameters for generating the robotic arm assisted lifting trajectory.

[0044] In the above scheme, the individualized motor dysfunction model refers to a digital ability assessment model specifically established for each stroke patient; the identification information refers to the digital code or biometric information used to uniquely identify the patient; the muscle strength asymmetry parameter refers to the numerical parameter that quantifies the difference in strength between the left and right limbs of the patient; the joint range of motion limitation parameter refers to the parameter that describes the degree of limitation of the range of motion of each joint of the patient; the motor coordination pattern parameter refers to the parameter that characterizes the coordination characteristics of each part of the patient during movement; the robotic arm assisted standing trajectory refers to the motion path planning when the robotic arm performs assisted standing action; and the specific parameters refer to the personalized motor ability parameters for a specific patient.

[0045] In this scheme, firstly, step 1041 involves the system immediately acquiring the patient's identification information upon receiving a standing intention trigger command. This information can be a patient ID, RFID tag, or biometric identification result. Secondly, step 1042 involves the system using this identification information as a search criterion to find the corresponding individualized motor dysfunction model from a pre-established patient model database. Then, step 1043 involves the system confirming that the found individualized motor dysfunction model contains the patient's unique motor ability parameters, including muscle asymmetry parameters quantifying the difference in strength between the left and right limbs, joint range of motion limitation parameters describing the degree of limitation in the movement of each joint, and motor coordination pattern parameters reflecting the characteristics of motor coordination. Finally, step 1044 involves the system loading this individualized motor dysfunction model containing patient-specific parameters into the memory of the robotic arm control system, providing data support for the subsequent generation of personalized robotic arm assisted standing trajectories.

[0046] Following the specific implementation of the previous solution, after the system generates a command to trigger the intention to stand up, it immediately reads the current patient's identification code and uses this identification code to find the corresponding personal motor ability profile in the model database. This profile records specific parameters such as the patient's left and right leg strength difference ratio of 30% and the maximum knee joint range of motion of 120 degrees. The system loads these parameters into the robotic arm control system to provide personalized basis for subsequent assistance trajectory planning.

[0047] This solution ensures the accuracy and personalization of rehabilitation assistance by intelligently identifying and quickly accessing the patient's personalized motor ability model. It provides tailor-made robotic arm assistance solutions for patients with different ability levels, significantly improving the effectiveness and safety of rehabilitation training.

[0048] Step 105: Combining the individualized motor dysfunction model with the real-time center of gravity offset data, generate a robotic arm lifting trajectory with a variable support force vector.

[0049] Optionally, step 105 may specifically include the following steps: Step 1051: Determine the initial support force distribution ratio of the robotic arm on both sides of the stroke patient's trunk based on the muscle asymmetry parameters contained in the individualized motor dysfunction model. Step 1052: Based on the changes in body stability reflected by the real-time center of gravity offset data, dynamically adjust the initial support force distribution ratio to obtain the adjusted support force distribution ratio. Step 1053: Based on the joint range of motion limitation parameters included in the individualized motor dysfunction model, set the upper limit of the motion speed of the robotic arm end effector. Step 1054: Integrate the adjusted support force distribution ratio and the upper limit of movement speed into the standard standing trajectory template to form the robotic arm assisted standing trajectory with variable support force vector.

[0050] In the appeal scheme, "variable support force vector" refers to an auxiliary force output mode that can dynamically adjust its magnitude and direction according to real-time conditions; "robotic arm assist trajectory" refers to the motion path and force control scheme of the robotic arm when performing assisted standing tasks; "initial support force distribution ratio" refers to the left-right support force distribution ratio preset according to the patient's muscle strength asymmetry; "body stability change" refers to the dynamic change of the patient's body balance state reflected by center of gravity offset data; "adjusted support force distribution ratio" refers to the left-right support force distribution ratio updated according to real-time stability changes; "robotic arm end effector" refers to the final execution component that comes into contact with the patient's body; and "movement speed limit" refers to the maximum movement speed limit of the robotic arm set to ensure patient safety.

[0051] In this scheme, firstly, step 1051 reads the muscle asymmetry parameters from the individualized motor dysfunction model and calculates the initial support force distribution ratio that the robotic arm needs to provide to both sides of the patient's torso based on the specific numerical values ​​of the difference in strength between the patient's left and right limbs. This ratio ensures that the weaker side receives more auxiliary support. Secondly, step 1052 monitors the changes in body stability reflected by the center of gravity shift data in real time. When the system detects that the patient's body is tilting to one side or showing an unbalanced trend, it dynamically adjusts the initial support force distribution ratio, increasing the support force on the unstable side, thus forming an adjusted support force distribution ratio. Then, step 1053 determines the safe range of motion of each joint of the patient based on the joint range of motion limitation parameters in the individualized motor dysfunction model, and sets the upper limit of the movement speed of the robotic arm's end effector accordingly, ensuring that the movement speed of the robotic arm will not cause joint damage to the patient. Finally, step 1054 integrates the adjusted support force distribution ratio and the upper limit of the movement speed parameters into a standard standing trajectory template. Through force control and speed adjustment of the standard trajectory, a variable support force vector robotic arm assisted standing trajectory that is completely adapted to the current patient state is finally formed.

[0052] Following the specific implementation of the previous solution, during the rehabilitation training process, taking a stroke patient with weaker left-side muscles as an example, the system sets the initial support force distribution ratio to 60% on the left and 40% on the right based on the patient's muscle strength asymmetry parameters. During the standing process, when the real-time center of gravity data shows that the patient's body shifts to the right, the system immediately adjusts the support force ratio to 70% on the left and 30% on the right. At the same time, based on the patient's knee joint range of motion limitation parameters, the upper limit of the robotic arm's movement speed is set to 80% of the normal value. Finally, a variable support force assistance solution is generated that incorporates these personalized parameters on the basis of the standard standing trajectory.

[0053] This solution combines personalized motor ability parameters with real-time stability data to achieve dynamic and precise adjustment of the robotic arm's assistive force. This ensures the safety of the standing process and provides personalized assistance that adapts to changes in the user's real-time condition, significantly improving the effectiveness of rehabilitation training and the user experience.

[0054] Step 106: Calculate the joint motion sequence of the multi-joint robotic arm based on the robotic arm assist trajectory.

[0055] Optionally, step 106 may specifically include the following steps: Step 1061: Calculate the angle that each joint needs to rotate at each path point based on the sequence of spatial path points of the end effector defined in the robotic arm lifting trajectory and the structural parameters of the multi-joint robotic arm. Step 1062: Arrange the calculated joint angles at each path point in chronological order to form a complete joint motion sequence; Step 1063: Based on the motion coordination mode parameters contained in the individualized motor dysfunction model, adjust the rate of angle change of each joint in the joint motion sequence in a coordinated manner to obtain the adjusted joint motion sequence. Step 1064: Convert the adjusted joint motion sequence into control commands for the motors of each joint of the multi-joint robotic arm.

[0056] In the above scheme, a multi-joint robotic arm refers to a robotic arm device with multiple rotary joints; a joint motion sequence refers to a set of angle change instructions for each joint arranged in chronological order; an end effector spatial path point sequence refers to a series of spatial position points that the end effector needs to pass through; the structural parameters of the multi-joint robotic arm refer to physical parameters such as the length, connection method, and range of motion of each joint of the robotic arm; the joint angle at each path point refers to the specific angle value that each joint needs to reach at each path point; and the adjusted joint motion sequence refers to the joint angle instruction sequence after coordination optimization.

[0057] In this scheme, firstly, step 1061 involves the system calculating the specific angle values ​​required for each joint to rotate at each path point based on the spatial path point sequence defined in the robotic arm's assisted lifting trajectory, combined with the specific structural parameters of the multi-joint robotic arm, including the length and connection method of each joint, through inverse kinematics. Secondly, step 1062 arranges and combines the calculated joint angle data at all path points in chronological order to form a complete joint motion sequence describing the entire movement process of the robotic arm. Then, step 1063 adjusts the rate of change of angles of each joint in the joint motion sequence according to the motion coordination mode parameters contained in the individualized motor dysfunction model, making the movement rhythm of the robotic arm more consistent with the patient's natural movement pattern, thus obtaining the adjusted joint motion sequence. Finally, step 1064 converts the angle data in the adjusted joint motion sequence into digital control commands that can be directly executed by the motors of each joint of the multi-joint robotic arm, including specific control parameters such as the motor's rotation angle, speed, and direction.

[0058] Following the specific implementation of the previous solution, during the rehabilitation training process, taking a six-joint rehabilitation robotic arm as an example, the system first calculates the 20 path points that the end effector needs to pass through based on the robotic arm's assisted standing trajectory. Then, it calculates the angle values ​​of the six joints at each path point through inverse kinematics. After arranging these angle values ​​in chronological order, the joint movement speed is smoothly adjusted according to the patient's movement coordination mode parameters. Finally, a joint movement sequence containing the rotation commands of each joint motor is generated to drive the robotic arm to complete the assisted standing action.

[0059] This solution transforms high-level trajectory planning into specific, executable joint movement commands and incorporates personalized motion coordination mode parameters, ensuring that the robotic arm's movement conforms to both trajectory requirements and user characteristics, thus achieving precise, natural, and safe assisted motion control.

[0060] Figure 2 This application provides a structural schematic diagram of a multi-joint robotic arm trajectory planning system for stroke rehabilitation, as shown below. Figure 2 As shown, the system includes: The acquisition module 21 is used to acquire real-time center of gravity shift data of the stroke patient during the process of standing up by using a pressure sensor array set on the seat and the foot of the stroke patient. The acquisition module 22 is used to acquire the real-time pelvic tilt angle and surface electromyography signals of the main muscle groups of the lower limbs of stroke patients in a sitting position. The generation module 23 is used to generate a standing intention trigger command based on the real-time pelvic tilt angle and surface electromyography signal; Retrieval module 24 is used to retrieve a pre-established individualized motor dysfunction model of stroke patients according to the standing intention trigger command; Module 25 is used to combine the individualized motor dysfunction model with the real-time center of gravity offset data to generate a robotic arm lifting trajectory with a variable support force vector. The calculation module 26 is used to calculate the joint motion sequence of the multi-joint robotic arm based on the robotic arm's lifting trajectory.

[0061] Figure 2 The aforementioned multi-joint robotic arm trajectory planning system for stroke rehabilitation can execute... Figure 1 The implementation principle and technical effects of the stroke rehabilitation multi-joint robotic arm assisted lifting trajectory planning method described in the illustrated embodiment will not be repeated here. The specific operation methods of each module and unit in the stroke rehabilitation multi-joint robotic arm assisted lifting trajectory planning system in the above embodiments have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0062] In one possible design, Figure 2 The stroke rehabilitation multi-joint robotic arm assisted lifting trajectory planning system of the embodiment shown can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0063] The processing component 32 is used for the above Figure 1The embodiment describes a method for assisted lifting trajectory planning using a multi-joint robotic arm for stroke rehabilitation.

[0064] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0065] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0066] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0067] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0068] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0069] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0070] This application also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The embodiment shown illustrates a method for assisted lifting trajectory planning of a multi-joint robotic arm for stroke rehabilitation.

[0071] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0072] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0073] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for trajectory planning of a multi-joint robotic arm for stroke rehabilitation, characterized in that, include: Real-time center of gravity shift data of stroke patients during the process of standing up is collected by a pressure sensor array set on the seat and the feet of the stroke patient. Acquire real-time pelvic tilt angle and surface electromyography signals of major lower limb muscle groups in stroke patients in a sitting position; Based on the real-time pelvic tilt angle and surface electromyography signal, a command to trigger the intention to stand up is generated. The pre-established individualized motor dysfunction model of stroke patients is retrieved based on the standing intention trigger command; By combining the individualized motor dysfunction model with the real-time center of gravity offset data, a robotic arm lifting trajectory with a variable support force vector is generated. The joint motion sequence of the multi-joint robotic arm is calculated based on the robotic arm's lifting trajectory.

2. The method according to claim 1, characterized in that, By using a pressure sensor array positioned between the seat and the stroke patient's feet, real-time center of gravity shift data is collected during the stroke patient's standing process, including: The pressure sensing array includes multiple pressure sensing units distributed on the seat surface in contact with the soles of the stroke patient's feet. Acquire the pressure measurement values ​​synchronously measured by the multiple pressure sensing units; Calculate the instantaneous pressure center coordinates on the seat plane and the double-foot support plane based on the pressure measurement values; Based on the instantaneous pressure center coordinates on the seat plane and the foot support plane, and the predefined relative spatial relationship between the seat and the foot support plane, the offset vector of the composite center of gravity projection point relative to the standard standing posture of the human body is calculated. The offset vector is used as real-time center of gravity offset data to characterize the stability of the standing movement of stroke patients.

3. The method according to claim 1, characterized in that, Real-time pelvic tilt angle and surface electromyography (EMG) signals of major lower limb muscle groups were acquired in stroke patients in a sitting position, including: A motion measurement sensor installed on the pelvic region of a stroke patient directly measures the change in the tilt angle of the pelvis in three-dimensional space to obtain the real-time pelvic tilt angle. Multiple surface electrodes are attached to the skin surface of target muscle groups in the lower limbs of stroke patients, and electrical signals generated by muscle activity are continuously collected through the surface electrodes. The collected electrical signals are rectified and smoothed to form surface electromyography signals that can reflect the degree of muscle activation. The real-time pelvic tilt angle collected at the same time is time-synchronized with the surface electromyography signal to form synchronous data characterizing the movement intention and posture of stroke patients.

4. The method according to claim 1, characterized in that, Based on the real-time pelvic tilt angle and surface electromyography signals, a command to trigger the intention to stand is generated, including: Determine whether the real-time pelvic tilt angle exceeds the preset angle that represents the initial stage of the standing up movement; Simultaneously, it is determined whether the signal intensity of the target muscle group related to hip and knee extension movements in the surface electromyography signal exceeds the resting level; When the real-time pelvic tilt angle exceeds the preset angle and the signal intensity of the target muscle group exceeds the resting level, it is determined that the stroke patient has a clear intention to stand up. Generate a start-up intention trigger command to initiate the robotic arm assisted start-up procedure.

5. The method according to claim 1, characterized in that, The pre-established individualized motor dysfunction model for stroke patients is retrieved based on the standing intention trigger command, including: In response to the standing intention trigger command, obtain the current stroke patient's identification information; Based on the identity information, the corresponding individualized motor function disorder model is retrieved from the pre-stored model library; The individualized motor dysfunction model includes parameters specific to stroke patients, such as muscle asymmetry parameters, joint range of motion limitation parameters, and motor coordination pattern parameters. The retrieved individualized motor dysfunction model is loaded into the robotic arm control system to provide stroke patient-specific parameters for generating the robotic arm's assisted lifting trajectory.

6. The method according to claim 1, characterized in that, Combining the individualized motor dysfunction model with the real-time center of gravity offset data, a robotic arm assisted lifting trajectory with a variable support force vector is generated, including: Based on the muscle asymmetry parameters included in the individualized motor dysfunction model, the initial support force distribution ratio of the robotic arm on both sides of the stroke patient's trunk is determined. Based on the changes in body stability reflected by the real-time center of gravity offset data, the initial support force distribution ratio is dynamically adjusted to obtain the adjusted support force distribution ratio. Based on the joint range of motion limitation parameters included in the individualized motor dysfunction model, the upper limit of the motion speed of the robotic arm end effector is set; The adjusted support force distribution ratio and the upper limit of movement speed are integrated into the standard standing trajectory template to form the robotic arm assisted standing trajectory with variable support force vector.

7. The method according to claim 1, characterized in that, The joint motion sequence of the multi-joint robotic arm is calculated based on the robotic arm's lifting trajectory, including: Based on the sequence of spatial path points of the end effector defined in the lifting trajectory of the robotic arm, and the structural parameters of the multi-joint robotic arm, calculate the angle that each joint needs to rotate at each path point; Arrange the calculated joint angles at each path point in chronological order to form a complete joint motion sequence. Based on the motion coordination mode parameters contained in the individualized motor dysfunction model, the rate of change of angle of each joint in the joint motion sequence is coordinated and adjusted to obtain the adjusted joint motion sequence. The adjusted joint motion sequence is converted into control commands for the motors of each joint of the multi-joint robotic arm.

8. A trajectory planning system for a multi-joint robotic arm used in stroke rehabilitation, characterized in that, include: The data acquisition module is used to collect real-time center of gravity shift data of stroke patients during the process of standing up by using a pressure sensor array set on the seat and the feet of the stroke patient. The acquisition module is used to acquire the real-time pelvic tilt angle and surface electromyography signals of the main muscle groups of the lower limbs of stroke patients in a sitting position. The generation module is used to generate a standing intention trigger command based on the real-time pelvic tilt angle and surface electromyography signal; The retrieval module is used to retrieve a pre-established individualized motor dysfunction model of a stroke patient based on the standing intention trigger command; The module is used to combine the individualized motor dysfunction model with the real-time center of gravity offset data to generate a robotic arm lifting trajectory with a variable support force vector. The calculation module is used to calculate the joint motion sequence of the multi-joint robotic arm based on the robotic arm's lifting trajectory.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement the stroke rehabilitation multi-joint robotic arm assisted lifting trajectory planning method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The device contains a computer program that, when executed by a computer, implements a method for assisted lifting trajectory planning of a multi-joint robotic arm for stroke rehabilitation as described in any one of claims 1 to 7.

Images