Search

CN-121973223-A - Intelligent control system and method for physiotherapy robot

CN121973223ACN 121973223 ACN121973223 ACN 121973223ACN-121973223-A

Abstract

The invention discloses an intelligent control system and method of a physiotherapy robot, which belong to the technical field of robot control and comprise an initial planning module, a real-time sensing module and a correction updating module, wherein the initial planning module is used for acquiring initial data of a target physiotherapy area, constructing a target body surface feature set, acquiring a preparation gesture, combining a sampling probability gradient, carrying out initial planning, generating an initial motion track and carrying out pre-starting verification, the real-time sensing module is used for binding an execution time stamp, constructing a sensing reference library, screening high-weight feature points, acquiring physiotherapy images, calculating a single-frame displacement module length, carrying out displacement risk assessment and adjustment once exceeding a single-frame displacement early warning line, and the correction updating module is used for carrying out adjustment verification, calculating safety compliance rate, displacement correction precision and energy uniformity, generating a target physiotherapy summary, realizing accurate adaptation of the physiotherapy track and parameters under a dynamic scene, and effectively avoiding physiotherapy area offset caused by micro-motion of a user.

Inventors

  • DENG ZHONGQUAN
  • DENG JUN
  • DENG LI

Assignees

  • 中塑联新材料科技湖北有限公司

Dates

Publication Date
20260505
Application Date
20260211

Claims (10)

  1. 1. The intelligent control system of the physiotherapy robot is characterized by comprising an initial planning module, a real-time sensing module and a correction updating module; The initial planning module is used for acquiring initial data of a target physiotherapy area of a user, calculating physiotherapy diameters, configuring initial physiotherapy parameters, constructing a target body surface feature set exclusive to the user, acquiring a preparation posture of a physiotherapy head, carrying out initial planning by utilizing an RRT algorithm and a multi-target ant colony algorithm in combination with sampling probability gradients, generating an initial movement track, driving the physiotherapy head to the preparation posture, and carrying out pre-starting verification in combination with coordinate deviation; The real-time sensing module is used for binding the sampling time sequence and the execution time stamp of the path point, driving the physical therapy head to move to the target coordinate to stabilize the contact force, constructing a sensing reference library, screening high-weight characteristic points, collecting physical therapy images, calculating the single-frame displacement module length, immediately carrying out displacement risk assessment once exceeding a single-frame displacement early warning line, and adjusting; the correction updating module is used for performing adjustment verification, calculating safety compliance rate, displacement correction precision and energy uniformity, and generating target physiotherapy summary.
  2. 2. The intelligent control system of a physiotherapy robot of claim 1, wherein the step of initially planning comprises: Scanning a target physiotherapy area to generate original three-dimensional point cloud data, combining a bilateral filtering algorithm to obtain physiotherapy point clouds, and calculating the physiotherapy diameter of the target physiotherapy area by using a maximum diameter distance method; a standard model of a corresponding part of the target physiotherapy area is called from a body surface feature library, registration is carried out on the standard model and the physiotherapy point cloud, so that a target body surface feature set is constructed, and an initial contact benchmark value and an initial body surface temperature are synchronously acquired; obtaining the physiotherapy type of a user, calling a default parameter set, setting a correction coefficient, and adjusting the default parameter set by combining the physiotherapy diameter to obtain initial physiotherapy parameters; and constructing a three-layer constraint system, and defining a track smooth index, a parameter adaptation index and a safety redundancy index to construct a multi-objective optimization function.
  3. 3. The intelligent control system of a physiotherapy robot of claim 2, wherein the step of initially planning further comprises: Based on the target body surface feature set, corresponding weights of various feature points are called, target coordinates of the target physiotherapy area are calculated through a weighted gravity center method, and the physiotherapy point cloud computing method vector is combined; setting a position safety limit, calculating a terminal position parameter, and generating a preparation posture; setting a secondary distance dividing threshold, dividing the target physiotherapy area into a target neighborhood, a transition area and a far field area, and configuring corresponding sampling probability to divide sampling resources; Combining the three-layer constraint system, and generating a plurality of planning candidate paths by utilizing an RRT algorithm; selecting a planning candidate path corresponding to each ant through probability in each iteration by utilizing an ant colony algorithm, and calculating a fitness value by utilizing a multi-objective optimization function; Updating the pheromone concentration of all planning candidate paths after all ants finish path selection, and repeating iterative operation until reaching a preset iterative coefficient; and taking the planning candidate path with the highest pheromone concentration as an initial motion track, and generating an initial physiotherapy path by combining the inverse kinematics of the robot.
  4. 4. A physiotherapeutic robot intelligent control system according to claim 3, wherein the step of pre-starting the verification comprises: driving a physiotherapy head to reach the preparation posture based on the initial physiotherapy path, acquiring a real-time image of the target physiotherapy area, and extracting a real-time body surface feature set; respectively obtaining real-time values and target values from the real-time body surface feature set and the target body surface feature set, calculating coordinate deviations of the real-time values and the target values of various feature points, and screening deviation check values Setting a check threshold Judging whether positioning deviation exists or not; If it is Judging that the pre-starting check is qualified, if Triggering automatic fine adjustment, converting the constructed deviation vector into joint angle fine adjustment amount, and re-judging qualification.
  5. 5. The intelligent control system of a physiotherapy robot of claim 4, wherein the step of evaluating the displacement risk comprises: extracting an execution time stamp corresponding to each path point in the initial physiotherapy path, binding the execution time stamp with the sampling time sequence of the perception sensor, and synchronously triggering the directional sampling of the perception sensor for the execution operation of each path point; Driving a physiotherapy head to move to the target coordinates, configuring a dynamic reference zero point according to an initial contact reference value, acquiring an image of a target physiotherapy area, calculating the average coordinates of each type of characteristic points, and constructing a perception reference library; dividing high-weight feature points and standby feature points based on the weight association table; activating energy output equipment of the physiotherapy head according to the initial physiotherapy path; And driving the physiotherapy robot to move according to the initial physiotherapy path, triggering a perception synchronizing signal every time when the physiotherapy robot moves by a preset distance, and starting multidimensional data acquisition.
  6. 6. The intelligent control system of a physiotherapy robot of claim 5, wherein the step of evaluating the displacement risk further comprises: collecting a physiotherapy image set for the target physiotherapy area, preferentially tracking the high-weight characteristic points, and extracting real-time coordinates of the high-weight characteristic points; if the high-weight feature points are not detected, automatically calling the standby feature points to carry out supplementary tracking; Acquiring effective contact force, and calculating a real-time displacement vector and a displacement modular length of each high-weight characteristic point in a physiotherapy image set by combining the perception reference library; Calculating the single frame displacement modular length by combining the displacement weights of the high-weight feature points; setting a single-frame displacement early warning line based on the product of a preset displacement limiting coefficient and a position safety limit; If present The single-frame displacement module of the frame image is longer than the single-frame displacement early warning line, continuous displacement is judged, displacement risk assessment is carried out, displacement risk, stage risk and safety redundancy risk are calculated respectively, weighting operation is carried out to obtain comprehensive displacement risk, a secondary risk threshold is set, the risk level of the comprehensive displacement risk is divided, the risk level comprises low risk, medium risk and high risk, and a corresponding adjustment mechanism is triggered; otherwise, judging that no effective displacement exists, and continuously collecting a physiotherapy image set according to the initial physiotherapy path.
  7. 7. The intelligent control system of a physiotherapy robot of claim 6, wherein the risk level adjustment mechanism comprises: If the risk is low, triggering a parameter adaptation mechanism, calling a corresponding compensation mechanism, and calculating parameter fine adjustment quantity by combining real-time displacement data; Checking the fine adjustment of parameters, and monitoring and adjusting the parameters continuously Calculating the displacement drop rate once the displacement drop rate is larger than the parameter fine adjustment lower limit, judging that the adjustment is effective, otherwise, switching to a local correction mechanism; If the risk is intermediate, triggering a local correction mechanism, calculating a global displacement vector, decomposing the global displacement vector into a translation deviation and a rotation deviation, constructing a pose deviation matrix, correcting local path points, and generating a local correction track; And verifying the local correction track, calculating displacement deviation between the high-weight characteristic point coordinates and the path points in the local correction track, judging that the track fine adjustment is effective if the maximum displacement deviation is smaller than the track adjustment upper limit, otherwise repeating the local track fine adjustment, and immediately switching to a path increment planning mechanism if the track fine adjustment is ineffective after the adjustment times upper limit is reached.
  8. 8. The intelligent control system of a physiotherapy robot of claim 7, wherein the risk level adjustment mechanism further comprises: If the path increment planning mechanism is high risk, calculating a new target coordinate by taking the real-time coordinate of the high-weight characteristic point as a reference through a weighted gravity center method, fitting a new normal vector by combining the physiotherapy point cloud, determining a new preparation gesture, generating candidate increment paths by adopting a bidirectional RRT algorithm, multiplexing a multi-target optimization function, calculating a multi-target optimization value of each candidate increment path, and selecting a path corresponding to the minimum value as an increment correction track; Triggering pre-starting verification before executing the incremental correction track, restarting physical therapy after the verification is qualified, automatically calculating pause time, and prolonging the total physical therapy time.
  9. 9. The intelligent control system of a physiotherapy robot of claim 8, wherein the step of adjusting the verification comprises: Driving the tail end physical therapy head to move along the path point sequence to perform three-mode cross check, including visual check, mechanical check and temperature check; If the two modes or more are abnormal, immediately suspending physiotherapy, and carrying out three-mode cross check again to determine whether the abnormality is instantaneous interference, if the abnormality is the single mode check abnormality, determining that the abnormality is instantaneous interference, otherwise, determining that the abnormality is continuous abnormality, and triggering emergency braking; Acquiring the standard reaching time of the safety index, calculating the safety compliance rate by combining with adjusting the total execution time, setting a safety compliance threshold value, and dividing the safety compliance level; obtaining an adjusted actual maximum displacement deviation, calculating displacement correction precision, and setting a displacement compliance threshold value to divide the displacement compliance level; And acquiring whole-course temperature field data, calculating energy uniformity, setting an energy uniformity threshold value to divide energy uniformity levels, and generating target physiotherapy summaries.
  10. 10. A physiotherapy robot intelligent control method based on the physiotherapy robot intelligent control system according to any one of claims 1-9, comprising: Step S1, acquiring initial data of a target physiotherapy area of a user, calculating physiotherapy diameters, configuring initial physiotherapy parameters, constructing a special target body surface feature set of the user, and acquiring a preparation posture of a physiotherapy head; step S2, sampling resources are distributed by utilizing sampling probability gradients, initial planning is carried out by utilizing an RRT algorithm, and an initial motion track is generated; s3, driving the physiotherapy head to the preparation posture, performing pre-starting verification by combining the coordinate deviation, driving the physiotherapy head to move to a target coordinate to stabilize the contact force, constructing a perception reference library, screening high-weight characteristic points, and collecting physiotherapy images; and S4, calculating the single-frame displacement modular length, immediately evaluating and adjusting the displacement risk once exceeding the single-frame displacement early warning line, and performing adjustment verification to generate the target physiotherapy summary.

Description

Intelligent control system and method for physiotherapy robot Technical Field The invention relates to an intelligent control system and method for a physiotherapy robot, and belongs to the technical field of robot control. Background As medical needs continue to grow, physiotherapy service robots are becoming an important tool in rehabilitation therapy. These robots need to have high precision and reliability, and also to be able to provide personalized services to accommodate the needs of different patients. The prior Chinese patent application with the publication number of CN119589705A discloses a control system and a control method of a physiotherapy service robot, wherein the control system comprises a machine vision device, a robot, a central control system, interaction equipment and a physiotherapy instrument, the interaction equipment is connected with the machine vision device and used for sending a starting signal to the machine vision device so that the machine vision device starts to collect human body images and select a physiotherapy area and plan a physiotherapy track, the machine vision device is connected with the central control system and used for sending physiotherapy area and physiotherapy track data, the central control system is connected with the robot and the physiotherapy instrument and used for sending the physiotherapy area and physiotherapy track data to the robot and the physiotherapy instrument, enabling the robot and the physiotherapy instrument to respectively execute physiotherapy service, receiving running track data and state information sent by the robot and the physiotherapy instrument and sending the running track data and state information to the interaction equipment. Although the prior art acquires patient data in real time in a remote environment and adjusts treatment parameters according to the data, thereby providing more flexible and effective treatment service, the real-time adaptation capability of a motion track under a dynamic physiotherapy scene is not considered, especially when a user slightly shifts in the physiotherapy process, such as the user unconsciously turns over and adjusts sitting postures, the robot still performs actions according to initial preset coordinates, and the deviation of a physiotherapy area is easy to cause. Disclosure of Invention Aiming at the defects existing in the prior art, the invention aims to provide an intelligent control system and method for a physiotherapy robot, which are characterized in that a special feature set is established through scanning denoising and model registration, an optimization algorithm is combined with pre-starting verification to generate an accurate initial track, initial errors are reduced, sensor time sequences and path points are bound, the tracking feature points capture user micro-motion in real time, the dynamic adaptation is carried out according to risk levels, and the problems of the physiotherapy offset caused by the user micro-motion are solved by combining three-mode cross verification, so that the robot is prevented from being executed according to preset. In order to achieve the above purpose, the present invention provides the following technical solutions: an intelligent control system of a physiotherapy robot comprises an initial planning module, a real-time sensing module and a correction updating module; The initial planning module is used for acquiring initial data of a target physiotherapy area of a user, calculating physiotherapy diameters, configuring initial physiotherapy parameters, constructing a target body surface feature set exclusive to the user, acquiring a preparation posture of a physiotherapy head, carrying out initial planning by utilizing an RRT algorithm and a multi-target ant colony algorithm in combination with sampling probability gradients, generating an initial movement track, driving the physiotherapy head to the preparation posture, and carrying out pre-starting verification in combination with coordinate deviation; The real-time sensing module is used for binding the sampling time sequence and the execution time stamp of the path point, driving the physical therapy head to move to the target coordinate to stabilize the contact force, constructing a sensing reference library, screening high-weight characteristic points, collecting physical therapy images, calculating the single-frame displacement module length, immediately carrying out displacement risk assessment once exceeding a single-frame displacement early warning line, and adjusting; the correction updating module is used for performing adjustment verification, calculating safety compliance rate, displacement correction precision and energy uniformity, and generating target physiotherapy summary. Specifically, the step of initial planning includes: Scanning a target physiotherapy area to generate original three-dimensional point cloud data, combining a bilateral filtering algorithm to obtain phy