WO2023284241A1

WO2023284241A1 - Rehabilitation mechanism control method, rehabilitation mechanism control system, and rehabilitation device

Info

Publication number: WO2023284241A1
Application number: PCT/CN2021/137762
Authority: WO
Inventors: 魏文昊; 葛伟; 黄博俊; 李光林; 于文龙; 黄品高; 王辉; 黄剑平
Original assignee: 中国科学院深圳先进技术研究院
Priority date: 2021-07-16
Filing date: 2021-12-14
Publication date: 2023-01-19
Also published as: CN113499229B; CN113499229A

Abstract

A rehabilitation mechanism control method, a rehabilitation mechanism control system (100), and a rehabilitation device (200). The rehabilitation mechanism control method comprises: a sensing module (7) detects environmental features, user's use posture information, and user's position information relative to a rehabilitation mechanism (S101); and a control module (6) receives the environmental features, use posture information, and position information, and controls a locomotion module (2) of the rehabilitation mechanism to move autonomously in all directions according to the environmental features, use posture information, and position information (S102). According to the provided technical solution of the rehabilitation mechanism, the user's rehabilitation status can be monitored in real time, so as to facilitate the planning of rehabilitation training, enabling movement path planning of the entire rehabilitation mechanism according to the user's position relative to the rehabilitation mechanism and the environmental features, thereby realizing automatic omnidirectional autonomous follow-up, reducing interference to patients, reducing the workload of nursing staff, and improving patient rehabilitation training effect.

Description

Control method of rehabilitation institution, control system of rehabilitation institution and rehabilitation equipment

technical field

Embodiments of the present invention relate to the technical field of rehabilitation equipment, and in particular, to a control method of a rehabilitation mechanism, a control system of a rehabilitation mechanism, and rehabilitation equipment.

Background technique

Due to reasons such as stroke, cerebrovascular disease and accidental injury, a large number of patients suffer from hand and foot inconvenience, paralysis and even amputation. For patients with inconvenient hands and feet and paralysis, they need nursing and rehabilitation training; for patients with lower limb amputations, they need to learn and practice using artificial limbs. And these inevitably need support and weight loss to ensure that nursing or rehabilitation can be carried out safely and effectively.

The walking mode of the walking hanger of the existing rehabilitation equipment is driven by the patient, pushed by the nursing staff and driven by two driving wheels. None of these three ways can make the walking hanger realize fully automatic omnidirectional self-following, which will cause The workload of nursing staff is heavy, the types of rehabilitation training movements are limited, or the training of patients is interfered.

The problem that existing rehabilitation equipment cannot meet the needs of patients has become an urgent problem to be solved in the industry.

technical problem

technical solution

The embodiment of the invention provides a control method of a rehabilitation mechanism, a control system of a rehabilitation mechanism, and rehabilitation equipment. The control method of the rehabilitation mechanism enables the rehabilitation equipment to realize full-automatic omnidirectional self-following, reduces interference to patients, and reduces the need for nursing staff. The workload of the patient has been improved, and the effect of rehabilitation training for patients has been improved.

In order to achieve the above technical problems, the present invention adopts the following technical solutions:

In a first aspect, an embodiment of the present invention provides a method for controlling a rehabilitation institution, including:

The sensing module detects environmental features, user posture information, and user position information relative to the rehabilitation mechanism;

The control module receives the environmental characteristics, the use posture information and the position information, and controls the walking module of the rehabilitation mechanism to walk autonomously in all directions according to the environment characteristics, the use posture information and the position information.

In some embodiments, the sensing module detects environmental features, user posture information, and user position information relative to the rehabilitation mechanism, including:

The environmental sensor collects the environmental characteristics of the surrounding environment of the rehabilitation institution, and sends the environmental characteristics to the control module; wherein the environmental characteristics include binocular vision images and laser radar point cloud images of the surrounding environment of the rehabilitation institution ;

The human body sensor collects the user's use posture information of the rehabilitation mechanism, and sends the use posture information to the control module; wherein the use posture information includes the user's real-time image data collected by the human body sensor;

The displacement sensor collects the position information of the user relative to the rehabilitation mechanism, and sends the position information to the control module; wherein, the position information includes the offset of the hanging plate of the rehabilitation mechanism relative to the center of the hanger .

In some embodiments, the control module receives the environmental characteristics, the use posture information and the location information, and controls the movement of the rehabilitation institution according to the environment characteristics, the use posture information and the location information. The walking module can walk autonomously in all directions, including:

The environment perception processing unit receives the environment features, and generates a grid map represented by a matrix according to the environment features;

The human body posture processing unit receives the user's use posture information of the rehabilitation mechanism, judges whether the user is in the posture information about to fall according to the user's use posture information of the rehabilitation mechanism, and calculates the deviation of the user relative to the center of the hanger. displacement;

The position detection processing unit judges the walking distance according to the position information of the user relative to the rehabilitation mechanism collected by the displacement sensor and the offset of the user relative to the center of the hanger calculated by the human body posture processing unit. The expected value of movement of the module; wherein the expected value of movement includes the direction of expected movement and the distance of expected movement;

The path planning unit determines whether the walking module can continue to move and the target variation between the displacement of the walking module and the posture of the human body according to the grid map and the expected movement value of the walking module.

In some embodiments, after the sensing module detects environmental features, user posture information, and user position information relative to the rehabilitation mechanism, it further includes:

The emergency sensor collects an emergency signal indicating whether the emergency sensor is triggered.

In some embodiments, after the path planning unit determines whether the walking module can continue to move and the target variation of the walking module displacement and human body posture according to the grid map and the expected movement value of the walking module, Also includes:

The emergency state detection unit is based on whether the user is in a posture information about to fall sent by the human body posture processing unit, the signal sent by the path planning unit whether the walking module can continue to move, and whether the emergency sensor is activated. Triggered emergency signal, generating emergency stop command and emergency event type.

In some embodiments, in the emergency state detection unit, according to whether the user is in a posture information about to fall sent by the human body posture processing unit, whether the walking module can continue to move according to the information sent by the path planning unit The signal and the emergency signal of whether the emergency sensor is triggered, after generating the emergency stop command and the emergency event type, also include:

According to the emergency stop command, the control unit controls the driving source of the rehabilitation mechanism to stop the walking module by emergency braking, and controls the driving of the rehabilitation mechanism according to the target change amount of the displacement of the walking module and the posture of the human body The source drives the walking module to walk;

According to the emergency stop command and the emergency event type, the control unit controls the display module to display emergency information, and controls the voice module to give a voice warning.

In some specific embodiments, according to the emergency stop command, the control unit controls the driving source of the rehabilitation mechanism to stop the walking module by emergency braking, and according to the relationship between the displacement of the walking module and the posture of the human body, The target variation controls the driving source of the rehabilitation mechanism to drive the walking module to walk, including:

When the emergency stop command is triggered, the control unit outputs a target speed of zero, and the driving source makes emergency braking to stop the walking module from walking;

When the emergency stop command is not triggered, the control unit calculates the target movement speed of the walking module in proportion according to the error between the current displacement of the walking module and the target displacement and the error size between the current human body posture and the target human body posture; Decomposition algorithm, decomposing the target motion speed of the walking module into the target speed of the driving source of the walking module, and outputting the target speed to the governor of the driving source; the speed governor passes Adjust the rotation speed of the drive source to control the walking speed of the walking module.

In some specific embodiments, the environment awareness processing unit receives the environment features, and generates a grid map represented by a matrix according to the environment features, including:

According to the binocular vision image of the surrounding environment of the rehabilitation institution collected by the environmental sensor, the environmental perception processing unit uses the texture feature of the pixel to find the vanishing point in the form of voting for the static object, and extracts the static object by using the color feature The edge of the static object is obtained through the preset operator, and then the static object is marked in the grid map; for the dynamic static object, the instantaneous moving speed of the pixel on the imaging plane is used to determine whether the pixel has moved. And identify the pixel moving path in the grid map to generate a grid map represented by a matrix;

When the environment sensor cannot collect the binocular vision image of the surrounding environment of the rehabilitation institution, the environment perception processing unit uses the depth information in the scene to reflect the relationship between the mobile hanger and the surrounding environment according to the lidar point cloud image obtained by the environment sensor The interrelationship between objects, and use the environment sensor to obtain the depth data of the surrounding environment, and use the color data to interpolate the depth data to form a small-grained depth image, and form a high-resolution scene of the surrounding environment in the grid map image, generating a matrix representation of a raster map.

In some specific embodiments, The human body posture processing unit receives the user's real-time image data collected by the human body sensor; and judges whether the user is in a posture about to fall and the offset of the user relative to the center of the hanger, including:

According to the user's real-time image data collected by the human body sensor, the human body posture processing unit uses a preset algorithm to extract different feature points of the user, connects the feature points with line segments according to the human body structure, and obtains the user's skeletal structure;

Through the adjacent image data of the preset number of frames, the data characteristics of the angle, angular velocity and angular acceleration of the user's joint motion direction are obtained, and the algorithm is used for pattern recognition to determine whether the person is in a posture about to fall;

Obtain the initial position data of the center points of the five feature points of the user's right eye, right ear, nose, left eye, and left ear when the user is standing in the middle of the walking hanger in the initial state; , the current position data of the central point of the five feature points of the user's right eye, right ear, nose, left eye, and left ear; Difference, to get the offset of the user relative to the center of the hanger.

In some specific embodiments, the position detection processing unit is based on the offset of the hanging plate of the rehabilitation mechanism relative to the center of the hanger and the center of the hanger of the user relative to the hanger of the rehabilitation mechanism collected by the displacement sensor The offset to calculate the expected value of movement of the walking module, including:

The position detection processing unit multiplies the offset of the user relative to the center of the hanger of the rehabilitation mechanism and the offset of the hanging plate of the rehabilitation mechanism relative to the center of the hanger by different weight coefficients through a weighting algorithm Carry out vector summation afterward, obtain the moving expected value of described walking module; Wherein, the weight coefficient of the offset of the hanger center of the user relative to the hanger of the described rehabilitation mechanism is greater than the deviation of the hanging hanger of the rehabilitation mechanism relative to the center of the hanger The weighting factor for the displacement.

In some specific embodiments, the path planning unit determines whether the walking module can continue to move and the target variation between the displacement of the walking module and the posture of the human body according to the grid map and the expected movement value of the walking module ,include:

According to the grid map input by the environment perception module and the movement expectation value of the walking hanger input by the position detection module, the distance information from the current position to all other points is established in the grid map; through a preset algorithm, in the path planning process Calculate the distance measurement information of each node to obtain the target variation of the displacement of the walking module and the posture of the human body;

If there is an obstacle, cancel the search along the pre-path, and output a prompt message that there is an obstacle ahead, and determine that the walking module cannot continue to move; wherein, the grid map identifies surrounding obstacles, walking hangers and other modules , the obstacle is displayed as a broken circuit in the grid map.

In the second aspect, an embodiment of the present invention provides a control system of a rehabilitation institution, which implements any control method of the rehabilitation institution described in the first aspect;

The control system of the rehabilitation institution includes:

A sensing module, configured to detect environmental features, user posture information and position information of the user relative to the rehabilitation mechanism;

A control module, configured to receive the environmental characteristics, the use posture information and the position information, and control the walking module of the rehabilitation mechanism to be omnidirectional and autonomous according to the environmental characteristics, the use posture information and the position information walk.

In the third aspect, the embodiment of the present invention proposes a rehabilitation device, including the control system of the rehabilitation mechanism described in the second aspect; the control system of the rehabilitation mechanism includes: a sensing module and a control module;

The rehabilitation equipment also includes: a hanger body and a walking module; the hanger body is a gantry;

The walking module is arranged below the vertical section of the gantry, the walking module has a driving source, and the driving source can drive the walking module to walk autonomously in all directions;

The sensing module is arranged on the hanger body, and the sensing module can detect environmental characteristics, user posture information and position information of the user relative to the hanger body;

The control module is arranged below the vertical section of the gantry and adjacent to the walking module, the sensing module is connected to the control module, and the control module is used to receive the environmental features, The use posture information and the position information, and control the walking module of the rehabilitation mechanism to walk autonomously in all directions according to the environmental characteristics, the use posture information and the position information.

In some embodiments, the rehabilitation equipment further includes: a suspension module, the suspension module is arranged on the horizontal section of the gantry, the suspension module includes a suspension bracket and a suspension hanging plate, the The suspension hanging plate is slidably arranged on the suspension bracket along two mutually perpendicular directions; the suspension bracket includes: an X-direction bracket and a Y-direction bracket, and the X-direction brackets are two arranged at intervals, The two ends of the Y-direction bracket are slidably arranged on the two X-direction brackets, and the suspension hanging plate is slidably arranged on the Y-direction bracket;

The sensing module includes an environment sensor, a human body sensor and a displacement sensor; the environment sensor is arranged around the hanger body, and the environment sensor is used for collecting environmental characteristics; the human body sensor is arranged at the hanger body The top of the top, the environment sensor is used to collect user posture information; the displacement sensor includes an X-direction displacement sensor on the X-direction support and a Y-direction displacement sensor on the Y-direction support, The displacement sensor is used to collect the position information of the user.

In some embodiments, the rehabilitation equipment also includes:

An emergency sensor, the emergency sensor is electrically connected to the control module, and the emergency sensor is used to collect an emergency signal indicating whether the emergency sensor is triggered; the emergency sensor includes an emergency stop button, and the emergency stop button is located on the hanger body and/or, the emergency sensor includes a plurality of pressure-sensitive handrails, and the plurality of pressure-sensitive handrails are vertically spaced on the hanger body.

Beneficial effect

The control method of the rehabilitation mechanism provided by the embodiment of the present invention detects the environmental characteristics, the user's use posture information and the position information of the user relative to the rehabilitation mechanism through the sensing module, and the control module receives the environmental characteristics and the use posture information and the position information, and control the walking module of the rehabilitation mechanism to walk autonomously in all directions according to the environmental characteristics, the use posture information and the position information, detect the user's rehabilitation status in real time, and facilitate the planning of rehabilitation training, On the other hand, it is possible to plan the walking strength of the entire hanger system according to the position of the user relative to the rehabilitation institution and the environmental characteristics, which can realize fully automatic omnidirectional self-following, reduce interference to patients, reduce the workload of nursing staff, and improve The effect of rehabilitation training on patients.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings that need to be used in the description of the embodiments of the present invention. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention For those skilled in the art, other drawings can also be obtained according to the contents of the embodiments of the present invention and these drawings without any creative work.

Fig. 1 is a flow chart of a control method of a rehabilitation mechanism provided by an embodiment of the present invention;

Fig. 2 is a flow chart of another control method of a rehabilitation mechanism provided by an embodiment of the present invention;

Fig. 3 is a flow chart of another control method of a rehabilitation mechanism provided by an embodiment of the present invention;

Fig. 4 is a flowchart of another control method of a rehabilitation mechanism provided by an embodiment of the present invention. ;

Fig. 5 is a flow chart of another control method of a rehabilitation mechanism provided by an embodiment of the present invention;

Fig. 6 is a flow chart of another control method of a rehabilitation mechanism provided by an embodiment of the present invention;

Fig. 7 is a schematic structural diagram of a control system of a rehabilitation mechanism provided by an embodiment of the present invention;

Fig. 8 is a schematic structural diagram of another rehabilitation mechanism control system provided by an embodiment of the present invention;

Fig. 9 is a schematic structural diagram of another control system of a rehabilitation mechanism provided by an embodiment of the present invention;

Fig. 10 is a schematic structural diagram of another rehabilitation mechanism control system provided by an embodiment of the present invention;

Fig. 11 is a schematic structural diagram of a rehabilitation device provided by an embodiment of the present invention;

Fig. 12 is a schematic structural diagram of another rehabilitation device provided by an embodiment of the present invention;

Fig. 13 is a schematic structural diagram of a walking module provided by an embodiment of the present invention;

Fig. 14 is a partial structural schematic diagram of a transmission assembly provided by an embodiment of the present invention;

Fig. 15 is another partial structural schematic diagram of the transmission assembly according to the embodiment of the present invention;

Fig. 16 is a schematic structural diagram of a suspension module provided by an embodiment of the present invention;

Fig. 17 is a schematic structural diagram of a suspension hanging board according to an embodiment of the present invention.

Reference signs:

1. Hanger body;

2. Walking module;

21. Driving source; 22. Traveling bracket; 23. Omnidirectional traveling wheel; 231. Input axle;

24. Transmission assembly; 241. Coupling; 242. Power input shaft; 243. First synchronous pulley; 244. Second synchronous pulley; 245. First bearing; 246. Second bearing; 247. Shaft sleeve;

3. Suspension module;

31. Suspension bracket; 310. X-direction bracket; 311. X-direction slider; 312. X-direction optical axis; 313. X-direction buffer block; 314. X-direction limit block; 315. Y-direction bracket; 316. Y To the slider; 317, Y to the optical axis; 318, to the Y to the buffer block; 319, to the Y to the limit block;

32. Suspension hanging plate; 321. Hanging plate body; 322. Lifting ring screw; 323. Lifting ring nut; 324. Thrust bearing;

41. X-direction displacement sensor; 42. Y-direction displacement sensor; 43. Environmental sensor; 44. Human body sensor; 45. Displacement sensor;

5. Emergency sensor; 51. Emergency stop button; 52. Pressure-sensitive handrail;

6. Control module; 7. Sensing module;

721. Environment perception processing unit; 722. Human body posture processing unit; 723. Position detection processing unit; 724. Path planning unit; 725. Emergency state detection unit; Control unit 726;

100. Control systems of rehabilitation institutions; 200. Rehabilitation equipment.

Embodiments of the present invention

The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention. In addition, it should be noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings but not all structures.

In describing the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", " Back", "Left", "Right", "Vertical", "Horizontal", "Top", "Bottom", "Inner", "Outer", "Clockwise", "Counterclockwise", "Axial" , "radial", "circumferential" and other indicated orientations or positional relationships are based on the orientations or positional relationships shown in the drawings, which are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying the referred device or Elements must have certain orientations, be constructed and operate in certain orientations, and therefore should not be construed as limitations on the invention.

In addition, the features defined as "first" and "second" may explicitly or implicitly include one or more of these features, which are used to describe the features differently, without order or importance. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

In the description of the present invention, it should be noted that unless otherwise specified and limited, the terms "installation", "connection" and "connection" should be understood in a broad sense, for example, it can be a fixed connection or a detachable connection. Connected, or integrally connected; it can be mechanically connected or electrically connected; it can be directly connected or indirectly connected through an intermediary, and it can be the internal communication of two components. Those of ordinary skill in the art can understand the specific meanings of the above terms in the present invention in specific situations.

Based on the above technical problems, this embodiment proposes the following solutions:

Fig. 1 is a flowchart of a control method of a rehabilitation mechanism provided by an embodiment of the present invention. Referring to Fig. 1, the control method of the rehabilitation mechanism provided by the embodiment of the present invention includes:

S101. The sensing module detects environmental features, user posture information, and user position information relative to the rehabilitation mechanism.

Specifically, the sensing module may include an environment sensor, a human body sensor, a displacement sensor and a control module.

S102. The control module receives the environmental characteristics, the use posture information and the position information, and controls the walking module of the rehabilitation mechanism to walk independently in all directions according to the environment characteristics, the use posture information and the position information .

Specifically, the sensing module can detect the environmental characteristics, the user's posture and the position of the user relative to the rehabilitation mechanism. Since the control module receives the environmental characteristics, usage posture information and location information, and , carry out comprehensive calculations, and control the walking module of the rehabilitation institution to walk autonomously in all directions. The control module can comprehensively consider factors such as the real-time environmental characteristics of the rehabilitation institution, the use posture information, the location information of the rehabilitation institution, and the relative position information of the user and the rehabilitation institution. , plan the route of the rehabilitation institution in time, and can control the walking module of the rehabilitation institution to walk autonomously in all directions. On the one hand, this setting can detect the user’s rehabilitation status in real time and facilitate the planning of rehabilitation training. On the other hand, it can plan the walking strength of the entire hanger system according to the position of the user relative to the rehabilitation mechanism and the environmental characteristics, which improves the hanger system. safety of use.

The control method of the rehabilitation mechanism provided in this embodiment detects the environmental characteristics, the user's use posture information and the position information of the user relative to the rehabilitation mechanism through the sensing module, the control module receives the environmental characteristics, the use posture information and the position information, and Control the walking module of the rehabilitation institution to walk autonomously in all directions according to the environmental characteristics, use posture information and position information, realize real-time detection of the user's rehabilitation status, and facilitate the planning of rehabilitation training. Features Planning the walking strength of the entire hanger system can realize fully automatic omnidirectional self-following, reduce interference to patients, reduce the workload of nursing staff, and improve the effect of patient rehabilitation training.

In some embodiments, FIG. 2 is a flowchart of another control method of a rehabilitation mechanism provided by an embodiment of the present invention. On the basis of the above embodiments, referring to Fig. 2, the control method of the rehabilitation mechanism provided by the embodiments of the present invention includes:

S201. The environmental sensor collects environmental features of the surrounding environment of the rehabilitation institution, and sends the environmental features to the control module; wherein the environmental features include binocular vision images and laser radar points of the surrounding environment of the rehabilitation institution cloud image.

Specifically, the environmental sensor may include a binocular camera and a lidar, the binocular camera is used to collect binocular vision images of the surrounding environment of the rehabilitation institution, and the laser radar is used to collect lidar point cloud images of the surrounding environment of the rehabilitation institution.

S202. The human body sensor collects the user's use posture information of the rehabilitation mechanism, and sends the use posture information to the control module; wherein the use posture information includes the user's real-time image data collected by the human body sensor .

Specifically, the human body sensor includes a camera, a depth camera, or an infrared camera, etc., and the human body sensor is used to collect user posture information on the rehabilitation mechanism.

S203. The displacement sensor collects the position information of the user relative to the rehabilitation mechanism, and sends the position information to the control module; wherein, the position information includes the deviation of the hanging plate of the rehabilitation mechanism relative to the center of the hanger displacement.

Specifically, the displacement sensor can include an X-direction displacement sensor and a Y-direction displacement sensor. Exemplarily, the fixed end of the X-direction displacement sensor can be installed on the X-direction bracket, the movable end can be installed on the X-direction slider, and the Y-direction displacement The fixed end of the sensor can be installed on the Y-direction bracket, and the movable end is installed on the Y-direction slider. The position information of the user relative to the rehabilitation mechanism is collected in real time through the X-direction displacement sensor and the Y-direction displacement sensor.

In some embodiments, FIG. 3 is a flowchart of another control method of a rehabilitation mechanism provided by an embodiment of the present invention. On the basis of the above embodiments, referring to Fig. 3, the control method of the rehabilitation mechanism provided by the embodiments of the present invention includes:

S301. The environment perception processing unit receives the environment feature, and generates a grid map represented by a matrix according to the environment feature.

In some specific embodiments, the environmental perception processing unit can use the binocular vision image of the surrounding environment of the rehabilitation institution collected by the environmental sensor, and for static objects, use the texture features of pixels to find the vanishing point in the form of voting, and use the color feature to extract the edge of the static object, obtain the edge information of the static object through the preset operator, and then mark the static object in the grid map; for the dynamic static object, use the instantaneous moving speed of the pixel on the imaging plane to judge the pixel Whether motion occurs, and the pixel movement path is identified in the grid map to generate a grid map represented by a matrix. When the environmental sensor cannot collect the binocular vision image of the surrounding environment of the rehabilitation institution, the environmental perception processing unit uses the depth information in the scene to reflect the distance between the mobile hanger and the surrounding environment objects based on the lidar point cloud image obtained by the environmental sensor. Interrelationship, and use the environmental sensor to obtain the depth data of the surrounding environment, use the color data to interpolate the depth data to form a small-grained depth image, form a high-resolution scene image of the surrounding environment in the grid map, and generate a grid represented by a matrix map.

Specifically, the input source of the environmental perception processing unit is the environmental sensor, the input information is the binocular vision image of the surrounding environment, the lidar point cloud image, the output object is the path planning unit; the output information is the grid map represented by the matrix. According to the image transmitted by the environmental sensor, for static objects, such as static obstacles or rehabilitation training modules, etc., use the texture features of pixels, use the form of voting to find the vanishing point, use color features to extract obstacles or module edges, and calculate through Robert Operator, soble operator, canny operator or Mean-shift operator, etc., to obtain obstacle edge information, and then mark obstacles or rehabilitation training modules in the grid map. For dynamic objects, such as dynamic obstacles, hanger body or moving rehabilitation training modules, etc., use the instantaneous moving speed of the pixels on the imaging plane to judge whether the pixels have moved, for example, the optical flow method can be used to detect and move the pixels Routes are identified in a raster map. When the use of the binocular camera is affected by the ambient light, shadows, etc., and it is difficult to obtain effective obstacle types and location information in the surrounding environment, the environment perception processing unit will use the lidar to obtain point cloud images, and use the depth information in the scene to reflect Interrelationships between mobile hangers and surrounding environment objects. Use the lidar to obtain the depth data of the surrounding environment, interpolate the depth data with the color data to form a small-grained depth image, and form a high-resolution scene image of the surrounding environment in the grid map.

S302. The human body posture processing unit receives the user's use posture information of the rehabilitation mechanism, judges whether the user is in the posture information about to fall according to the user's use posture information of the rehabilitation mechanism, and calculates the user's relative hanger center offset.

In some specific embodiments, The human body posture processing unit uses the preset algorithm to extract different feature points of the user according to the real-time image data of the user collected by the human body sensor, connects the feature points with line segments according to the human body structure, and obtains the user's bone structure; through the preset frame The data characteristics of the angle, angular velocity, and angular acceleration of the user's joint movement direction are obtained through several adjacent image data, and the algorithm is used for pattern recognition to determine whether the person is in a posture about to fall; obtain the user's standing position in the initial state When walking in the middle position of the hanger, the initial position data of the center point of the five feature points of the user's right eye, right ear, nose, left eye, and left ear; when the user is in use, the user's right eye, The current position data of the center point of the five feature points of the right ear, nose, left eye, and left ear; the human body posture processing unit obtains the offset of the user relative to the center of the hanger according to the difference between the current position data and the initial position data quantity.

Specifically, the input source of the human body posture processing unit is the human body sensor; the input information is the real-time image data of the user; the output objects are the position detection processing unit and the emergency state detection unit; the output information is respectively whether the user is in a posture about to fall , The offset of the user relative to the center of the hanger. The image data of the user is collected by the human body sensor, and the OpenPose algorithm is used to extract 18 key points, for example, right eye, right ear, left eye, left ear, nose, neck, right shoulder, right elbow, right wrist, left shoulder, left Elbow, left wrist, right crotch, right knee, right ankle, left crotch, left knee and left ankle, use line segments to connect the above points according to the human body structure to obtain the skeleton structure of the human body. Exemplarily, 12 joint motion directions can be obtained through 3 to 10 frames of adjacent image data, for example, the left shoulder joint along the sagittal plane, the left shoulder joint along the coronal plane, the left elbow joint, the right shoulder joint along the sagittal plane, the right Angles at the shoulder in the coronal plane, right elbow, left hip in the sagittal plane, left hip in the coronal plane, left knee, right hip in the sagittal plane, right hip in the coronal plane, and right knee , angular velocity and angular acceleration, a total of 36 data features, through SVM, LDA, KNN or ANN algorithm for pattern recognition, to determine whether the person is in a posture about to fall. In the initial state, the user stands in the middle of the hanger body, and the center point of the five key points of the user's right eye, right ear, nose, left eye, and left ear is taken as the initial position point. When in use, extract the center point of the five key points of the user's right eye, right ear, nose, left eye, and left ear as the current position point. The offset of the user relative to the center of the hanger is obtained by the difference between the coordinates of the previous position point and the coordinates of the initial position point.

S303. The position detection processing unit determines the position of the user based on the position information of the user relative to the rehabilitation mechanism collected by the displacement sensor and the offset of the user relative to the center of the hanger calculated by the human body posture processing unit. The expected movement value of the walking module; wherein, the expected movement value includes the direction of the expected movement and the distance of the expected movement.

In some specific embodiments, the position detection processing unit multiplies the offset of the user relative to the center of the hanger of the rehabilitation mechanism and the offset of the hanging plate of the rehabilitation mechanism relative to the center of the hanger by different weighting algorithms. After the weight coefficients, the vector summation is performed to obtain the expected value of movement of the walking module; wherein, the weight coefficient of the offset of the user relative to the center of the hanger of the rehabilitation mechanism is greater than the weight of the offset of the hanging plate of the rehabilitation mechanism relative to the center of the hanger coefficient.

S304. The path planning unit determines whether the walking module can continue to move and the target variation of the walking module displacement and human body posture according to the grid map and the expected movement value of the walking module.

In some specific embodiments, the path planning unit establishes the distance information from the current position to all other points in the grid map according to the grid map input by the environment perception module and the expected movement value of the walking hanger input by the position detection module; The preset algorithm calculates the distance measurement information of each node during the path planning process, and obtains the target variation of the displacement of the walking module and the posture of the human body; if an obstacle appears, cancel the search along the pre-path, and output a prompt message that there is an obstacle ahead , it is determined that the walking module cannot continue to move; wherein, the grid map identifies surrounding obstacles, walking hangers and other modules, and obstacles are displayed as broken circuits in the grid map.

Specifically, the input sources of the path planning unit are the environment perception processing unit and the position detection processing unit; the input information is the grid map represented by the matrix and the expected movement value of the hanger body, for example, including the expected movement direction of the hanger body and distance; the output object is the emergency state detection unit and the control unit; the output information is whether the hanger can continue to move and the target change of the hanger body displacement and attitude. According to the grid map that identifies the surrounding obstacles, the hanger body and other modules input by the environment perception module, and the expected movement value of the hanger body input by the position detection module, the distance information from the current position to all other points is established in the grid map , according to the moving expected value of the hanger body, calculate the distance measurement information of each node in the path planning process, if there is an obstacle, cancel the search along the pre-path, and output the obstacle prompt information ahead.

In some embodiments, FIG. 4 is a flowchart of another control method of a rehabilitation mechanism provided by an embodiment of the present invention. On the basis of the above embodiments, referring to Fig. 4, the control method of the rehabilitation mechanism provided by the embodiment of the present invention includes:

S401. The emergency sensor collects an emergency signal indicating whether the emergency sensor is triggered.

Specifically, the emergency sensor may include an emergency stop button and/or a plurality of pressure-sensitive handrails, and the emergency sensor is used to collect an emergency signal indicating whether the emergency sensor is triggered.

In some embodiments, FIG. 5 is a flowchart of another control method of a rehabilitation mechanism provided by an embodiment of the present invention. On the basis of the above embodiments, referring to Fig. 5, the control method of the rehabilitation mechanism provided by the embodiment of the present invention includes:

S501. The emergency state detection unit is based on the information sent by the human body posture processing unit whether the user is in a posture about to fall, the signal sent by the path planning unit whether the walking module can continue to move, and the emergency sensor Whether the emergency signal was triggered, generated emergency stop command and emergency event type.

Specifically, the input sources of the emergency state detection unit are the human body posture processing unit, the path planning unit, and emergency sensors, such as emergency stop buttons or pressure-sensitive handrails; the input information is whether the user is in a posture about to fall, whether the hanger can Continue to move, whether the emergency switch or the pressure-sensitive handrail is triggered; the output object is the control unit; the output information is the emergency stop command and the emergency event type. When the hanger body is immovable, the emergency switch is triggered or the pressure-sensitive handrail is triggered, an emergency stop command is issued. The emergency detection unit judges the emergency type according to the current information and sends it to the control unit.

In some embodiments, FIG. 6 is a flow chart of another method for controlling a rehabilitation mechanism provided by an embodiment of the present invention. On the basis of the above embodiments, referring to Fig. 6, the control method of the rehabilitation mechanism provided by the embodiment of the present invention includes:

S601. According to the emergency stop command, the control unit controls the driving source of the rehabilitation mechanism to stop the walking module by emergency braking, and controls the rehabilitation mechanism according to the target change amount of the displacement of the walking module and the posture of the human body The driving source drives the walking module to walk.

In some specific embodiments, When the emergency stop command is triggered, the control unit outputs a target speed of zero, and the driving source brakes in an emergency to stop the walking module from walking; Calculate the target motion speed of the walking module in proportion to the error between the human body posture and the target human body posture; use the motion decomposition algorithm to decompose the target motion speed of the walking module into the target speed of the driving source of the walking module, and output the target speed A governor to the drive source; the governor controls the walking speed of the walking module by adjusting the speed of the drive source.

Specifically, the driving source can be one of brushless motor, stepping motor or brushed motor, and has an angle Hall sensor or a photoelectric encoder to realize servo control. Of course, the specific type of driving source can be selected according to actual needs, and is not limited to the above-mentioned limitations. The input source of the control unit is the emergency state detection unit and the path planning unit; the input information is the emergency stop command and the target change of displacement and attitude; the output object is the motor speed controller; the output information is the respective target speed of the four motors. Exemplarily, when the emergency stop command is triggered, the control unit outputs the target speed as 0. When the emergency stop command is not triggered, the control unit calculates the target speed of the hanger body motion proportionally according to the error between the current pose and the target pose, and uses the motion decomposition algorithm to decompose the target speed of the walking hanger into four parts. The target rotational speed of an omnidirectional traveling wheel, and output the target rotational speed to the governor of the drive source, such as the motor governor.

S602. The control unit controls the display module to display emergency information according to the emergency stop command and the emergency event type, and controls the voice module to issue a voice warning.

Specifically, the control unit controls the voice module, such as a loudspeaker to sound an alarm, and controls the display module, such as a display to issue a corresponding warning reminder, according to the received emergency event type output by the emergency detection unit.

An embodiment of the present invention provides a control system of a rehabilitation institution, which executes the control method of the rehabilitation institution in any of the foregoing embodiments. Fig. 7 is a schematic structural diagram of a control system of a rehabilitation mechanism provided by an embodiment of the present invention. On the basis of the above embodiments, referring to Fig. 7, the control system 100 of the rehabilitation institution provided by the embodiment of the present invention includes:

The sensing module 7 is used to detect the environmental features, the user's posture information and the position information of the user relative to the rehabilitation mechanism.

The control module 6 is used to receive environmental characteristics, use posture information and location information, and control the walking module of the rehabilitation mechanism to walk autonomously in all directions according to the environment characteristics, use posture information and location information.

In some specific embodiments, FIG. 8 is a schematic structural diagram of another control system of a rehabilitation mechanism provided by an embodiment of the present invention. On the basis of the above embodiments, referring to FIG. 8, the sensor module 7 of the control system 100 of the rehabilitation mechanism provided by the embodiment of the present invention includes:

The environmental sensor 43 is used to collect the environmental characteristics of the surrounding environment of the rehabilitation institution, and send the environmental characteristics to the control module; wherein, the environmental characteristics include binocular vision images and laser radar point cloud images of the surrounding environment of the rehabilitation institution.

The human body sensor 44 is used to collect the user's use posture information on the rehabilitation mechanism, and send the use posture information to the control module; wherein the use posture information includes the user's real-time image data collected by the human body sensor.

The displacement sensor 45 is used to collect the position information of the user relative to the rehabilitation mechanism, and send the position information to the control module; wherein, the position information includes the offset of the hanging plate of the rehabilitation mechanism relative to the center of the hanger.

In some specific embodiments, FIG. 9 is a schematic structural diagram of another control system of a rehabilitation mechanism provided by an embodiment of the present invention. On the basis of the above embodiments, referring to FIG. 9 , the control module 6 of the control system 100 of the rehabilitation mechanism provided by the embodiment of the present invention includes:

The environment perception processing unit 721 is configured to receive environment features, and generate a grid map represented by a matrix according to the environment features.

The human body posture processing unit 722 is used to receive the user's use posture information of the rehabilitation mechanism, judge whether the user is in the posture information about to fall according to the user's use posture information of the rehabilitation mechanism, and calculate the deviation of the user relative to the center of the hanger. displacement.

The position detection processing unit 723 is used to determine the movement expectation value of the walking module according to the position information of the user relative to the rehabilitation mechanism collected by the displacement sensor, and the offset of the user relative to the hanger center calculated by the human body posture processing unit; , the expected value of movement includes the expected direction of movement and the expected distance of movement.

The path planning unit 724 is used to determine whether the walking module can continue to move and the target variation of the walking module displacement and human body posture according to the grid map and the expected movement value of the walking module.

In some specific embodiments, FIG. 10 is a schematic structural diagram of another control system of a rehabilitation mechanism provided by an embodiment of the present invention. On the basis of the above embodiments, referring to FIG. 10 , the sensing module 7 of the control system 100 of the rehabilitation mechanism provided by the embodiment of the present invention further includes:

The emergency sensor 53 is used to collect an emergency signal indicating whether the emergency sensor 53 is triggered.

The control module 72 of the control system 100 of the rehabilitation institution also includes:

The emergency state detection unit 725 is used for whether the user is in the posture information about to fall sent by the human body posture processing unit, whether the walking module sent by the path planning unit can continue to move, and whether the emergency sensor 53 is triggered. Generate emergency stop commands and emergency event types.

The control unit 726 is used to stop the walking module by controlling the driving source of the rehabilitation mechanism to brake in an emergency according to the emergency stop command, and control the driving source of the rehabilitation mechanism to drive the walking module to walk according to the target variation of the displacement of the walking module and the posture of the human body. The control unit 726 is further configured to control the display module to display emergency information according to the emergency stop command and the type of emergency event, and control the voice module to perform voice warnings.

The control system of the rehabilitation mechanism provided by the embodiment of the present invention detects the environmental characteristics, the user's use posture information and the position information of the user relative to the rehabilitation mechanism through the sensing module, and receives the environmental characteristics, use posture information and position information through the control module, And according to the environmental characteristics, use posture information and position information, the walking module of the rehabilitation mechanism is controlled to walk autonomously in all directions, so as to realize the real-time detection of the user's rehabilitation status and facilitate the planning of rehabilitation training. Environmental characteristics carry out the walking force planning of the entire hanger system, which improves the safety of the hanger system.

Fig. 11 is a schematic structural diagram of a rehabilitation device provided by an embodiment of the present invention. Fig. 12 is a schematic structural diagram of another rehabilitation device provided by an embodiment of the present invention. Fig. 13 is a schematic structural diagram of a walking module provided by an embodiment of the present invention. On the basis of the above-mentioned embodiments, referring to Fig. 11-Fig. 13, the rehabilitation equipment 200 provided by the embodiment of the present invention includes the control system 100 of the rehabilitation institution proposed in any of the above-mentioned embodiments, and the control system 100 of the rehabilitation institution includes a sensor module and Control module, rehabilitation equipment 200 comprises: hanger body 1 and walking module 2; Hanger body 1 is a gantry; It can drive the walking module 2 to walk autonomously in all directions; the sensing module is arranged on the hanger body 1, and the sensing module can detect environmental characteristics, the user's use posture information and the position information of the user relative to the hanger body; the control module 6 is set Below the vertical section of the gantry, and adjacent to the walking module 2, the sensing module is connected to the control module 6, and the control module 6 is used to receive environmental characteristics, use posture information and position information, and Information and position information control the walking module 2 of the rehabilitation institution to walk autonomously in all directions.

Specifically, as shown in FIG. 12 , there may be four walking modules 2 , and the four walking modules 2 are respectively located under the two vertical sections of the gantry. As shown in FIG. 13 , each walking module 2 includes a driving source 21 , a walking support 22 , an omnidirectional traveling wheel 23 and a transmission assembly 24 , and the driving source 21 can be a motor and can drive the omnidirectional traveling wheel 23 to travel autonomously in all directions. Fig. 14 is a partial structural schematic diagram of a transmission assembly provided by an embodiment of the present invention; Fig. 15 is another partial structural schematic diagram of a transmission assembly according to an embodiment of the present invention. As shown in Figures 14-15, the transmission assembly 24 may include a coupling 241, a power input shaft 242, a first synchronous pulley 243, and a second synchronous pulley 244, and the coupling 241 is connected to the output shaft of the drive source 21 , one end of the power input shaft 242 is connected with the shaft coupling 241; the other end is rotatably fitted on the walking bracket 22, the first synchronous pulley 243 is located on the power input shaft 242, and the first synchronous pulley 243 is provided on both sides The first bearing 245 is arranged, the second synchronous pulley 244 cooperates with the first synchronous pulley 243 through a synchronous transmission belt, the second synchronous pulley 244 is installed on the input wheel shaft 231 of the omnidirectional traveling wheel 23, and the second synchronous pulley 244 There are second bearings 246 on both sides. The bushing 247 is located on both sides of the second synchronous pulley 244 , and the bushing 247 is interposed between the second synchronous pulley 244 and the second bearing 246 .

In some specific embodiments, FIG. 16 is a schematic structural diagram of a suspension module provided by an embodiment of the present invention. On the basis of the above-mentioned embodiments, with reference to Fig. 12 and Fig. 16, the rehabilitation equipment provided by the embodiment of the present invention further includes: a suspension module 3, which is arranged on the horizontal section of the gantry frame, and the suspension module 3 includes a suspension The suspension bracket 31 and the suspension hanging plate 32, the suspension hanging plate 32 is slidably arranged on the suspension bracket 31 along two mutually perpendicular directions; The two ends of the Y-direction support 315 are slidably arranged on the two X-direction supports 310 respectively, and the suspension hanging plate 32 is slidably arranged on the Y-direction support 315; Module comprises environmental sensor 43, human body sensor 44 and displacement sensor 45; Environmental sensor 43 is located at the periphery of hanger body 1, and environmental sensor 43 is used for collecting environmental characteristics; Human body sensor 44 is located at the top of hanger body 1, and environmental sensor 43 Used to collect the user's use posture information; the displacement sensor 45 includes the X-direction displacement sensor 41 located on the X-direction support 310 and the Y-direction displacement sensor 42 located on the Y-direction support 315, and the displacement sensor 45 is used to collect the user's posture information. location information.

Specifically, the suspension bracket 31 includes an X-direction bracket 310, an X-direction slider 311, an X-direction optical axis 312, an X-direction buffer block 313, an X-direction limit block 314, a Y-direction bracket 315, a Y-direction slider 316, a Y-direction To the optical axis 317 , the Y-direction buffer block 318 and the Y-direction limit block 319 . There are two X-direction brackets 310 arranged at intervals. The X-direction slider 311 is connected to the Y-direction bracket 315 , and the X-direction optical axis 312 is installed on the X-direction bracket 310 and cooperates with the X-direction slider 311 . The X-direction buffer blocks 313 are disposed at both ends of the X-direction optical axis 312 , and the X-direction buffer blocks 313 are further provided with X-direction limit blocks 314 . Two Y-direction brackets 315 are arranged at intervals, and the two ends of each Y-direction bracket 315 are slidably arranged on two X-direction brackets 310 respectively, and the suspension hanging plate 32 is slidably arranged on the Y-direction bracket 315 . There are four Y-direction sliders 316 , and the four Y-direction sliders 316 are all connected to the suspension plate 32 , and the Y-direction optical axis 317 is installed on the Y-direction bracket 315 and cooperates with the Y-direction slider 316 . Each Y-direction optical axis 317 is provided with two Y-direction sliding blocks 316 , and Y-direction buffer blocks 318 are disposed at two ends of the Y-direction optical axis 317 , and a Y-direction limiting block 319 is provided outside the Y-direction buffer blocks 318 .

In some embodiments, on the basis of the above embodiments, continue to refer to FIG. 12 , the rehabilitation equipment 200 provided by the embodiment of the present invention further includes an emergency sensor 5, which is electrically connected to the control module 6, and the emergency sensor 5 is used to collect An emergency signal whether the emergency sensor is triggered; the emergency sensor 5 includes an emergency stop button 51, and the emergency stop button 51 is located on the hanger body 1; and/or, the emergency sensor 5 includes a plurality of pressure-sensitive handrails 52, and a plurality of pressure-sensitive handrails 52 are arranged on the hanger body 1 at intervals along the vertical direction. Optionally, FIG. 17 is a schematic structural diagram of a suspension hanging board according to an embodiment of the present invention. As shown in Figure 17, the suspension hanging plate 32 includes a hanging plate body 321, an eye screw 322, an eye nut 323 and a thrust bearing 324, the hanging plate body 321 is slidably arranged on the suspension bracket 31, and the eye screw 322 is passed through On the suspension plate body 321, the suspension ring nut 323 fits on the suspension ring screw 322, and there are two thrust bearings 324, and the two thrust bearings 324 are installed on the suspension ring screw 322 and stop against the upper side wall and the lower side of the suspension plate body 321 on the wall.

The rehabilitation equipment provided by the embodiments of the present invention includes the control system of the rehabilitation mechanism proposed in any of the above embodiments, and because the hanger body is formed as a gantry, on the one hand, it can better bear the weight of the user, ensuring that the entire hanger system can be stable. On the other hand, the gantry structure enables the hanger to pass through rehabilitation tools such as stairs or slopes, thereby expanding the scope of application of the hanger system, expanding the user's rehabilitation actions, and improving the user's rehabilitation effect. Since the lower end of the gantry is equipped with a walking module, the walking module can realize omnidirectional walking under the drive of its own driving source, which realizes that the hanger system can automatically follow the user in all directions during use, and can lift the hanger system It is safe to use and can reduce the workload of nursing staff. The slidable suspension module can follow the movement of the user to reduce the influence of inertia and system response delay, thereby reducing the interference of the suspension system to the user and ensuring the rehabilitation effect.

Note that the above are only preferred embodiments of the present invention and applied technical principles. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the present invention, and the present invention The scope is determined by the scope of the appended claims.

Claims

A control method for a rehabilitation institution, characterized in that it includes:

The sensing module detects environmental features, user posture information, and user position information relative to the rehabilitation mechanism;

The control module receives the environmental characteristics, the use posture information and the position information, and controls the walking module of the rehabilitation mechanism to walk autonomously in all directions according to the environment characteristics, the use posture information and the position information.
The control method of the rehabilitation institution according to claim 1, wherein the sensing module detects environmental characteristics, user posture information and position information of the user relative to the rehabilitation institution, including:

The environmental sensor collects the environmental characteristics of the surrounding environment of the rehabilitation institution, and sends the environmental characteristics to the control module; wherein the environmental characteristics include binocular vision images and laser radar point cloud images of the surrounding environment of the rehabilitation institution ;

The human body sensor collects the user's use posture information of the rehabilitation mechanism, and sends the use posture information to the control module; wherein the use posture information includes the user's real-time image data collected by the human body sensor;

The displacement sensor collects the position information of the user relative to the rehabilitation mechanism, and sends the position information to the control module; wherein, the position information includes the offset of the hanging plate of the rehabilitation mechanism relative to the center of the hanger .
The control method of the rehabilitation institution according to claim 2, wherein the control module receives the environmental characteristics, the use posture information and the position information, and according to the environmental characteristics, the use posture information and the The position information controls the walking module of the rehabilitation mechanism to walk autonomously in all directions, including:

The environment perception processing unit receives the environment features, and generates a grid map represented by a matrix according to the environment features;

The human body posture processing unit receives the user's use posture information of the rehabilitation mechanism, judges whether the user is in the posture information about to fall according to the user's use posture information of the rehabilitation mechanism, and calculates the deviation of the user relative to the center of the hanger. displacement;

The position detection processing unit judges the walking distance according to the position information of the user relative to the rehabilitation mechanism collected by the displacement sensor and the offset of the user relative to the center of the hanger calculated by the human body posture processing unit. The expected value of movement of the module; wherein the expected value of movement includes the direction of expected movement and the distance of expected movement;

The path planning unit determines whether the walking module can continue to move and the target variation between the displacement of the walking module and the posture of the human body according to the grid map and the expected movement value of the walking module.
The control method of the rehabilitation mechanism according to claim 3, characterized in that, after the sensing module detects environmental features, user posture information and position information of the user relative to the rehabilitation mechanism, further comprising:

The emergency sensor collects an emergency signal indicating whether the emergency sensor is triggered.
According to the control method of the rehabilitation institution according to claim 4, it is characterized in that, in the path planning unit, it is determined whether the walking module can continue to move and whether the walking module can continue to move according to the grid map and the expected movement value of the walking module. After the target variation of displacement and human posture, it also includes:

The emergency state detection unit is based on whether the user is in a posture information about to fall sent by the human body posture processing unit, the signal sent by the path planning unit whether the walking module can continue to move, and whether the emergency sensor is activated. Triggered emergency signal, generating emergency stop command and emergency event type.
According to the control method of the rehabilitation mechanism described in claim 5, it is characterized in that, in the emergency state detection unit, according to the posture information of whether the user is in the posture information sent by the human body posture processing unit, the path planning unit The sent signal of whether the walking module can continue to move and the emergency signal of whether the emergency sensor is triggered, after generating the emergency stop command and the emergency event type, also includes:

According to the emergency stop command, the control unit controls the driving source of the rehabilitation mechanism to stop the walking module by emergency braking, and controls the driving of the rehabilitation mechanism according to the target change amount of the displacement of the walking module and the posture of the human body The source drives the walking module to walk;

According to the emergency stop command and the emergency event type, the control unit controls the display module to display emergency information, and controls the voice module to give a voice warning.
The control method of the rehabilitation mechanism according to claim 6, characterized in that, the control unit controls the driving source of the rehabilitation mechanism to make the walking module stop walking according to the emergency stop order by controlling the driving source of the rehabilitation mechanism to stop walking. The target variation of the displacement of the walking module and the posture of the human body controls the driving source of the rehabilitation mechanism to drive the walking module to walk, including:

When the emergency stop command is triggered, the control unit outputs a target speed of zero, and the driving source makes emergency braking to stop the walking module from walking;

When the emergency stop command is not triggered, the control unit calculates the target movement speed of the walking module in proportion according to the error between the current displacement of the walking module and the target displacement and the error size between the current human body posture and the target human body posture; Decomposition algorithm, decomposing the target motion speed of the walking module into the target speed of the driving source of the walking module, and outputting the target speed to the governor of the driving source; the speed governor passes Adjust the rotation speed of the drive source to control the walking speed of the walking module.
The control method of the rehabilitation institution according to claim 3, wherein the environment perception processing unit receives the environment characteristics, and generates a grid map represented by a matrix according to the environment characteristics, including:

According to the binocular vision image of the surrounding environment of the rehabilitation institution collected by the environmental sensor, the environmental perception processing unit uses the texture feature of the pixel to find the vanishing point in the form of voting for the static object, and extracts the static object by using the color feature The edge of the static object is obtained through the preset operator, and then the static object is marked in the grid map; for the dynamic static object, the instantaneous moving speed of the pixel on the imaging plane is used to determine whether the pixel has moved. And identify the pixel moving path in the grid map to generate a grid map represented by a matrix;

When the environment sensor cannot collect the binocular vision image of the surrounding environment of the rehabilitation institution, the environment perception processing unit uses the depth information in the scene to reflect the relationship between the mobile hanger and the surrounding environment according to the lidar point cloud image obtained by the environment sensor The interrelationship between objects, and use the environment sensor to obtain the depth data of the surrounding environment, and use the color data to interpolate the depth data to form a small-grained depth image, and form a high-resolution scene of the surrounding environment in the grid map image, generating a matrix representation of a raster map.
According to the control method of the rehabilitation mechanism described in claim 3, it is characterized in that, the human body posture processing unit receives the real-time image data of the user collected by the human body sensor; and judges whether the user is in a posture about to fall and the user is relatively The offset of the center of the hanger, including:

According to the user's real-time image data collected by the human body sensor, the human body posture processing unit uses a preset algorithm to extract different feature points of the user, connects the feature points with line segments according to the human body structure, and obtains the user's skeletal structure;

Through the adjacent image data of the preset number of frames, the data characteristics of the angle, angular velocity and angular acceleration of the user's joint motion direction are obtained, and the algorithm is used for pattern recognition to determine whether the person is in a posture about to fall;

Obtain the initial position data of the center point of the five feature points of the user's right eye, right ear, nose, left eye, and left ear when the user stands in the middle of the walking hanger in the initial state;

Obtain the current position data of the center point of the five feature points of the user's right eye, right ear, nose, left eye, and left ear when the user is in use;

The human body posture processing unit obtains the offset of the user relative to the center of the hanger according to the difference between the current position data and the initial position data.
According to the control method of the rehabilitation mechanism according to claim 3, it is characterized in that, the position detection processing unit collects the offset of the suspension suspension plate of the rehabilitation mechanism relative to the center of the hanger and the relative relative value of the user according to the displacement sensor. The offset of the hanger center of the rehabilitation mechanism calculates the expected movement value of the walking module, including:

The position detection processing unit multiplies the offset of the user relative to the center of the hanger of the rehabilitation mechanism and the offset of the hanging plate of the rehabilitation mechanism relative to the center of the hanger by different weight coefficients through a weighting algorithm Carry out vector summation afterward, obtain the moving expected value of described walking module;

Wherein, the weight coefficient of the offset of the user relative to the center of the hanger of the rehabilitation mechanism is greater than the weight coefficient of the offset of the hanging plate of the rehabilitation mechanism relative to the center of the hanger.
The control method of the rehabilitation institution according to claim 3, wherein the path planning unit determines whether the walking module can continue to move and whether the walking module can continue to move according to the grid map and the expected movement value of the walking module. The target variation of displacement and human posture, including:

According to the grid map input by the environment perception module and the movement expectation value of the walking hanger input by the position detection module, the distance information from the current position to all other points is established in the grid map; through a preset algorithm, in the path planning process Calculate the distance measurement information of each node to obtain the target variation of the displacement of the walking module and the posture of the human body;

If an obstacle occurs, cancel the search along the pre-path, and output an obstacle prompt message ahead, and determine that the walking module cannot continue to move;

Wherein, the grid map identifies surrounding obstacles, traveling hangers and other modules, and the obstacles are displayed as broken circuits in the grid map.
A control system of a rehabilitation institution, characterized by comprising: the control system of the rehabilitation institution executes the control method of the rehabilitation institution in any one of claims 1-11;

The control system of the rehabilitation institution includes:

A sensing module, configured to detect environmental features, user posture information and position information of the user relative to the rehabilitation mechanism;

A control module, configured to receive the environmental characteristics, the use posture information and the position information, and control the walking module of the rehabilitation mechanism to be omnidirectional and autonomous according to the environmental characteristics, the use posture information and the position information walk.
A rehabilitation device, characterized by comprising: the control system of the rehabilitation institution according to claim 12; the control system of the rehabilitation institution includes: a sensing module and a control module;

The rehabilitation equipment also includes: a hanger body and a walking module; the hanger body is a gantry;

The walking module is arranged below the vertical section of the gantry, the walking module has a driving source, and the driving source can drive the walking module to walk autonomously in all directions;

The sensing module is arranged on the hanger body, and the sensing module can detect environmental characteristics, user posture information and position information of the user relative to the hanger body;

The control module is arranged below the vertical section of the gantry and adjacent to the walking module, the sensing module is connected to the control module, and the control module is used to receive the environmental features, The use posture information and the position information, and control the walking module of the rehabilitation mechanism to walk autonomously in all directions according to the environmental characteristics, the use posture information and the position information.
The rehabilitation device according to claim 13, characterized in that,

The rehabilitation equipment also includes: a suspension module, the suspension module is arranged on the horizontal section of the gantry, the suspension module includes a suspension bracket and a suspension hanging plate, and the suspension hanging plate is Two mutually perpendicular directions are slidably arranged on the suspension bracket; the suspension bracket includes: an X-direction bracket and a Y-direction bracket, the X-direction brackets are two spaced apart, and the Y-direction brackets The two ends are slidably arranged on the two X-direction brackets, and the suspension hanging plate is slidably arranged on the Y-direction bracket;

The sensing module includes an environment sensor, a human body sensor and a displacement sensor;

The environmental sensor is arranged around the hanger body, and the environmental sensor is used to collect environmental characteristics;

The human body sensor is arranged on the top of the hanger body, and the environment sensor is used to collect user posture information;

The displacement sensor includes an X-direction displacement sensor disposed on the X-direction support and a Y-direction displacement sensor disposed on the Y-direction support, and the displacement sensor is used to collect user position information.
The rehabilitation device according to claim 14, wherein the rehabilitation device further comprises:

An emergency sensor, the emergency sensor is electrically connected to the control module, and the emergency sensor is used to collect an emergency signal indicating whether the emergency sensor is triggered;

The emergency sensor includes an emergency stop button, and the emergency stop button is arranged on the hanger body; and/or:

The emergency sensor includes a plurality of pressure-sensitive handrails, and the plurality of pressure-sensitive handrails are vertically spaced on the hanger body.