CN117045497B - Massaging robot, control method and massaging method - Google Patents
Massaging robot, control method and massaging method Download PDFInfo
- Publication number
- CN117045497B CN117045497B CN202311033198.9A CN202311033198A CN117045497B CN 117045497 B CN117045497 B CN 117045497B CN 202311033198 A CN202311033198 A CN 202311033198A CN 117045497 B CN117045497 B CN 117045497B
- Authority
- CN
- China
- Prior art keywords
- massage
- track
- image
- massaged
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000033001 locomotion Effects 0.000 claims abstract description 22
- 230000001133 acceleration Effects 0.000 claims description 42
- 238000004422 calculation algorithm Methods 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 14
- 238000010438 heat treatment Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000013016 damping Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 20
- 230000008569 process Effects 0.000 abstract description 10
- 238000003825 pressing Methods 0.000 abstract description 8
- 230000007704 transition Effects 0.000 abstract description 5
- 210000003128 head Anatomy 0.000 description 17
- 238000005516 engineering process Methods 0.000 description 7
- 230000004048 modification Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000037396 body weight Effects 0.000 description 2
- 230000036461 convulsion Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000012636 effector Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000001125 extrusion Methods 0.000 description 1
- 210000000245 forearm Anatomy 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 238000000059 patterning Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 230000006461 physiological response Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H39/00—Devices for locating or stimulating specific reflex points of the body for physical therapy, e.g. acupuncture
- A61H39/04—Devices for pressing such points, e.g. Shiatsu or Acupressure
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H7/00—Devices for suction-kneading massage; Devices for massaging the skin by rubbing or brushing not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/008—Manipulators for service tasks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1661—Programme controls characterised by programming, planning systems for manipulators characterised by task planning, object-oriented languages
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
- A61H2201/5007—Control means thereof computer controlled
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
- A61H2201/5058—Sensors or detectors
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Rehabilitation Therapy (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- Animal Behavior & Ethology (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Physical Education & Sports Medicine (AREA)
- Pain & Pain Management (AREA)
- Epidemiology (AREA)
- Dermatology (AREA)
- Massaging Devices (AREA)
Abstract
A massage robot, a control method and a massage method, comprising: an information acquisition part, a system control part and a massage execution part; the system control part plans a massage track, a pose track and a massage force position; the massage executing unit executes the massage according to the system control unit plan. The invention ensures that the whole massage process is closer to manual massage, improves the massage effect, fits the massage track, meets the effect of fitting the human track, achieves smooth transition among curves of each section, ensures that the track of the middle section passes at a constant speed in the whole motion process, ensures that the motion track is more stable, keeps constant-force pressing, and achieves the massage effect.
Description
Technical Field
The invention relates to the technical field of robot massage, in particular to a massage robot, a control method and a massage method.
Background
The massage is to apply special techniques on specific parts or specific acupoints to achieve physical effects in order to induce physiological responses in the designated areas, dredge channels and collaterals, and balance human body functions. The massage can promote metabolism of human body, and can be used as a commonly applied health care method. The popular massage equipment in the market at present is a massage chair and a massage bed, however, the massage chair and the massage bed are both of a passive type, the control method is that the massaged person applies force from bottom to top, the massaged person relies on the body weight to implement the massage, the massaged person is required to adjust the muscles of the massaged person to 'seek' the massage pressure point, and the massaged part is under the pressure of the body weight and can not receive the massage in a relax manner; in addition, the massage technique of the traditional massage chair and the massage bed is single, and the simulation teaching massage action can not be completed, so that the expected effect can not be achieved.
Intelligent robotics are technology developed rapidly for many years, have interactive efficacy, are a key target for going to society and serving life of people, and have the advantage of inexhaustible fatigue and infinite strength. Based on the traditional Chinese medicine massage technique, the artificial intelligence, the intelligent perception, the robot technology and the modern rehabilitation theory are integrated, so that the massage robot is generated, the massage robot can help or replace a massage engineer to perform the action of the conventional massage technique, and the massage technique can be standardized by using the accurate force/position feedback control, so that the massage effect is stable. By means of intelligent robot technology, massage robot research is a key means for promoting massage modernization. Therefore, the modern intelligent robot technology and the traditional massage theory are combined into the key development direction of the massage robot.
As early as 1996, japan Masao Kume et al designed a mechanical unit (MTU) with 4 degrees of freedom, which verified the feasibility of developing an intelligent massage robot by using a two-cycle control strategy to complete the massage action on the shoulders. In 2009 to 2010, taiwan university in China proposes a multi-finger manipulator impedance control method based on analysis of myoelectricity information. Recording forearm electromyogram during massage, and obtaining a proper input command range of the robot during massage according to the relationship between human feeling and massage force. Finally, the effective and comfortable massage by using the multi-finger mechanical arm is realized. However, the technology relies on manual data input, cannot be adjusted adaptively, and is low in intelligent degree.
Disclosure of Invention
Object of the invention
The invention aims to provide a massage robot, a control method and a massage method, which can improve the intelligent degree, ensure that the constant force pressing is kept in the direction of contacting a massage executing part with a human body without manual positioning and improve the massage effect.
(II) technical scheme
In order to solve the problems, the invention provides a massage robot, which comprises a robot body, a massage device and a massage device, wherein the robot body comprises an information acquisition part, a system control part and a massage execution part; the information acquisition part, the system control part and the massage execution part are electrically connected;
the information acquisition part acquires an image of the region to be massaged;
The system control part plans a massage track, a pose track and a massage force position according to the image acquired by the information acquisition part; the massage executing unit executes massage according to the plan of the system control unit.
In another aspect of the present invention, preferably, the system control part includes a model training subsystem, a track generating subsystem, a pose control subsystem, and a force and position hybrid control subsystem;
The model training subsystem obtains three-dimensional point cloud data of a general massage area through deep learning training, the track generation subsystem plans a massage track according to the image of the massage area to be massaged, which is acquired by the information acquisition part, the pose control subsystem generates a pose track according to the planned massage track, and the force and position hybrid control subsystem plans massage force positions according to the pose track.
In another aspect of the present invention, preferably, the massage performing part includes a massage mechanical arm, a massage head, and a heating member; the massage head is arranged at the end part of the massage mechanical arm, the heating component is arranged inside the massage head and is used for heating the massage head.
In another aspect of the present invention, preferably, a control method of the massage robot as described above includes:
Acquiring an image of an area to be massaged;
The obtained image of the area to be massaged is in one-to-one correspondence with three-dimensional point cloud data of a preset general massage area, and massage key points and positions on the image of the area to be massaged are obtained; the three-dimensional point cloud data of the preset general massage area are obtained through training;
Planning a massage track by utilizing a preset NURBS curve according to the massage key points on the image of the area to be massaged;
the massage track is adjusted in real time by using a preset force-position hybrid control algorithm;
And finishing the massage according to the massage track and the force position mixed control algorithm.
In another aspect of the present invention, the method, preferably,
The image of the region to be massaged is acquired and comprises a two-dimensional image and a three-dimensional image;
the obtained image of the area to be massaged is in one-to-one correspondence with three-dimensional point cloud data of a preset general massage area, and massage key points on the image of the area to be massaged are obtained, and the method comprises the following steps:
Generating a two-dimensional track and two-dimensional track key points according to the two-dimensional image of the region image to be massaged;
Converting the two-dimensional track key points into three-dimensional key points in a three-dimensional image of the region image to be massaged according to a preset first conversion rule;
And the three-dimensional key points are in one-to-one correspondence with the three-dimensional point cloud data of the preset general massage area, and the massage key points on the image of the area to be massaged are obtained.
In another aspect of the present invention, preferably, the obtaining the pose on the image of the area to be massaged by corresponding the obtained image of the area to be massaged to the three-dimensional point cloud data of the preset general massage area one by one includes:
Obtaining positions and normal vectors of the three-dimensional point cloud data corresponding to the massage key points;
And converting the position and the normal vector into a pose according to a preset second conversion rule.
In another aspect of the present invention, preferably, the planning the massage track further includes adjusting the pose track in the massage track in real time by using a preset pose algorithm; the preset pose algorithm comprises an S-shaped acceleration and deceleration or sine-shaped acceleration and deceleration control algorithm, and the S-shaped acceleration and deceleration or sine-shaped acceleration and deceleration control algorithm comprises a track look-ahead algorithm.
In another aspect of the present invention, preferably, the preset force-bit mixture control algorithm includes:
Acquiring a force to be applied to the massage region;
Calculating acceleration of the massage executing section according to the force to be applied to the massage region;
Calculating the tail end pose of the massage executing part according to the force and the acceleration to be applied to the massage area;
and calculating the motion angle of the massage executing part according to the tail end pose and the mechanical arm kinematics inverse solution.
In another aspect of the present invention, preferably, the preset force-bit hybrid control algorithm calculation formula includes:
The acceleration is calculated and the acceleration is calculated,
The position and the posture of the tail end are calculated,
Wherein F is the force applied to the human body, M is the inertia parameter of the impedance control, B is the damping parameter of the impedance control, K is the rigidity parameter of the impedance control, deltat is the calling period, x is the position of the massage executing part,Representing the speed of the massage execution unit,/>The acceleration of the massage execution unit is shown.
In another aspect of the present invention, preferably, a massage method controls massage by a massage robot using the control method as described above.
(III) beneficial effects
The technical scheme of the invention has the following beneficial technical effects:
the massage robot setting system control part of the invention plans the massage track, the pose track and the massage force position, so that the whole massage process is closer to manual massage, and the massage effect is improved, wherein the planned massage track fits the massage track, the effect of fitting the human body track is met, and the smooth transition between each section of curves is achieved; the pose track enables each section of motion track to accelerate, uniformly speed and decelerate stably, and the track of the middle section passes uniformly in the whole motion process, so that the motion track is more stable; the massage force position ensures that the constant force pressing is kept in the contact direction of the massage head and the human body, thereby achieving the massage effect and solving the problem that the position and the gesture of the point cloud which are visually identified are not attached or extruded due to the inherent error.
Drawings
Fig. 1 is a schematic view showing the overall structure of a massage robot according to an embodiment of the present invention;
FIG. 2 is a schematic overall flow diagram of a control method according to one embodiment of the invention;
Reference numerals:
1: a robot body; 2: a system control unit; 3: a massage executing part; 4: an information acquisition unit; 3-1: a massage mechanical arm; 3-2: a massage head.
Detailed Description
The objects, technical solutions and advantages of the present invention will become more apparent by the following detailed description of the present invention with reference to the accompanying drawings. It should be understood that the description is only illustrative and is not intended to limit the scope of the invention. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the present invention.
A layer structure schematic diagram according to an embodiment of the present invention is shown in the drawings. The figures are not drawn to scale, wherein certain details may be exaggerated and some details may be omitted for clarity. The shapes of the various regions, layers and relative sizes, positional relationships between them shown in the drawings are merely exemplary, may in practice deviate due to manufacturing tolerances or technical limitations, and one skilled in the art may additionally design regions/layers having different shapes, sizes, relative positions as actually required.
It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be noted that the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In addition, the technical features of the different embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
The invention will be described in more detail below with reference to the accompanying drawings. Like elements are denoted by like reference numerals throughout the various figures. For clarity, the various features of the drawings are not drawn to scale.
Example 1
Fig. 1 is a schematic view showing the overall structure of a massage robot according to an embodiment of the present invention, as shown in fig. 1, including: a robot body 1, wherein the robot body 1 comprises an information acquisition part 4, a system control part 2 and a massage execution part 3; the information acquisition part 4, the system control part 2 and the massage execution part 3 are electrically connected; the information acquisition part 4 acquires an image of the region to be massaged; the system control part 2 plans a massage track, a pose track and a massage force position according to the region to be massaged acquired by the information acquisition part; the massage execution unit 3 executes massage according to the plan of the system control unit; the specific contents of the information acquisition part 4, the system control part 2 and the massage execution part 3 are not limited, the information acquisition part 4 can be a two-dimensional camera or a depth camera, alternatively, in this embodiment, the specific contents of the information acquisition part 4 include a depth camera for acquiring an image of a region to be massaged, further, in this embodiment, the contents acquired by the information acquisition part 4 include a two-dimensional image and a three-dimensional image of the region to be massaged, the position of the region to be massaged in the three-dimensional image is obtained by matching the two-dimensional image with the three-dimensional image, and the information acquisition part 4 is used for acquiring the image of the region to be massaged; the specific content of the system control part 2 is not limited, and optionally, the system control part 2 in this embodiment includes a track generation subsystem, a pose control subsystem and a force-position hybrid control subsystem; the track generation subsystem plans a massage track according to the image of the region to be massaged, which is acquired by the information acquisition part, the pose control subsystem generates a pose track according to the planned massage track, and the force and position hybrid control subsystem plans a massage force position according to the pose track; further, the track generation subsystem fits the massage track, so that the effect of fitting the human track is met, and smooth transition among all sections of curves is achieved; the pose control subsystem enables each section of motion track to accelerate, uniformly speed and decelerate stably, and the track of the middle section passes uniformly in the whole motion process, so that the motion track is more stable; the force-position mixed control subsystem ensures that constant force pressing is kept in the contact direction of the massage head and the human body, and the system control part further comprises a model training subsystem, wherein the model training subsystem trains to obtain general three-dimensional point cloud data according to a deep learning technology, trains images of all massage areas based on the deep learning technology, can further distinguish which part of the human body is the position to be massaged, and the boundary point is at which position, so that the massage track is customized for each user; the specific content of training is not limited, and the training can be according to preset user attribute items and massage service scheme categories; collecting sample behavior data of training samples corresponding to user attribute items, and determining a massage service scheme of a client to be massaged according to attribute information of the client to be massaged corresponding to the user attribute items and a massage service scheme identification model so as to achieve a massage effect; the massage executing part comprises a massage mechanical arm and a massage head; the massage head is arranged at the end part of the massage mechanical arm; the system control part controls the massage mechanical arm to move according to the pose track, and controls the massage head to move according to the planned massage force position; further, the massage executing part further comprises a heating part, the heating part is arranged inside the massage head and is used for heating the massage head to increase the massage effect; the number of specific joints of the mechanical arm is not limited, and the specific structure of the massage head is not limited;
the information acquisition part is arranged on the side surface of the end part of the massage mechanical arm, and the specific position of the information acquisition part is not limited; the depth camera can be a binocular structure optical infrared camera, further, the binocular structure optical infrared camera is used for collecting under different viewing angles such as overlooking and head-up, and further, the specific model of the selected binocular structure optical infrared camera is REALSENSE D435i.
The massage robot is provided with the track generation subsystem, the pose control subsystem and the force and position mixed control subsystem, so that the whole massage process is closer to manual massage, and the massage effect is improved, wherein the track generation subsystem fits the massage track, the effect of fitting the human track is met, and smooth transition among curves is achieved; the pose control subsystem enables each section of motion track to accelerate, uniformly speed and decelerate stably, and the track of the middle section passes uniformly in the whole motion process, so that the motion track is more stable; the force-position hybrid control subsystem ensures that the constant force pressing is kept in the contact direction of the massage head and the human body, the massage effect is achieved, the deep learning-based visual recognition system is added, the massage track can be really customized for each user, the defect that the independent track planning can only be applied to the movement of the position and the gesture on a fixed object is overcome, and the problem that the position and the gesture of the point cloud which are visually recognized are not attached or extruded due to the inherent error of the point cloud is solved.
Example two
Fig. 2 shows a flowchart of the overall control method of the massaging robot according to an embodiment of the invention, as shown in fig. 2, comprising:
Acquiring an image of an area to be massaged; the image of the area to be massaged is collected by the control information collecting part 4, the specific content collected can be a two-dimensional camera or a depth camera, optionally, in this embodiment, the specific content of the information collecting part 4 includes a depth camera, which is used for collecting the image of the area to be massaged, and further, in this embodiment, the content of the image of the area to be massaged includes a two-dimensional image and a three-dimensional image of the area to be massaged; optionally, in this embodiment, the position of the human body in the three-dimensional image is obtained by matching the two-dimensional image with the three-dimensional image; further, a depth camera is adopted to simultaneously acquire a two-dimensional digital image and a three-dimensional depth image which comprise a human body image of a massage part of a user, the two-dimensional digital image is used for identifying massage key points of a region to be massaged, the three-dimensional depth image is used for three-dimensional reverse modeling, and three-dimensional space positions of the massage key points are determined; removing background noise by adopting a digital image segmentation method, extracting an image of a region to be massaged in a two-dimensional digital image, removing redundant image information, reducing a target range, reducing data volume and improving calculation efficiency; the position of the image of the region to be massaged in the three-dimensional depth image is obtained through matching the two-dimensional digital image and the three-dimensional depth image, background noise in the three-dimensional depth image is removed, the data size of the three-dimensional image is reduced, and the calculation efficiency is improved;
The method comprises the steps of corresponding an acquired image of a region to be massaged with three-dimensional point cloud data of a preset general massage region one by one, and acquiring massage key points and positions on the image of the region to be massaged; the three-dimensional point cloud data of the preset general massage area are obtained through training; the specific content of the three-dimensional point cloud data of the preset general massage area is not limited, and the specific content can be massage acupoint information suitable for the shoulder and neck, or can be whole massage acupoint information, and the corresponding purpose is to find the massage key points and the positions of the current massage person. Generating a two-dimensional track and two-dimensional track key points according to the two-dimensional image of the region image to be massaged; converting the two-dimensional track key points into massage key points in a three-dimensional image of the area image to be massaged according to a preset first conversion rule; the specific content of the first conversion rule is not limited herein, and optionally, in this embodiment, a two-dimensional track and a two-dimensional track key point are generated by using a parameter equation, which may be a track similar to a spiral circle, and the two-dimensional track key point is converted into a massage key point in a three-dimensional image of an image of the region to be massaged by using a transformation matrix; the massage key points are in one-to-one correspondence with the three-dimensional point cloud data of the preset general massage area; specific content of the three-dimensional point cloud data of the preset general massage area is not limited, and optionally, the three-dimensional point cloud data can be trained data; obtaining positions and normal vectors of the three-dimensional point cloud data corresponding to the massage key points; the position and the normal vector are converted into pose according to a preset second conversion rule, and the specific content of the preset second conversion rule is not limited, and optionally, in this embodiment, the preset second conversion rule is that the position and the normal vector are added into a preset X-axis coordinate, and after a corresponding direction vector is generated, the position and the normal vector are converted into a pose expression form represented by a position and a quaternion;
Planning a massage track by utilizing a preset NURBS curve according to the massage key points on the image of the area to be massaged; the massage track is planned by adopting a NURBS curve, the NURBS curve is adopted to fit the massage track, the effect of fitting the human body track is met, the NURBS curve is a universal curve for representing spline curves, any point, straight line, circular arc or free curve in a three-dimensional space can be uniformly represented by the curve expression, and the method has generality and universality. The NURBS curve is based on a B spline curve, and a weight value is added to a control point of the NURBS curve so as to increase the modeling capability of the curve. The curve can solve the problems of connection and smoothness between complex curves. Therefore, NURBS curves are commonly applied to curve fitting of numerical control machine tools, are curve surface expression forms commonly adopted in computer aided design software systems at present, and utilize good mathematical characteristics of the NURBS curves in robot motion to plan complex track curves; further, in this embodiment, the method further includes generating a gesture track for adjusting the massage track in real time by using a preset gesture algorithm; the specific content of the preset pose algorithm is not limited, and optionally, in this embodiment, the preset pose algorithm includes an S-type acceleration/deceleration or sinusoidal acceleration/deceleration control algorithm to enable each motion track to accelerate, decelerate at a uniform speed; in order to frequently start and stop, the preset pose algorithm also comprises a track look-ahead algorithm, so that the speed reduction and acceleration conditions between each track segment are reduced to the minimum, the tracks of the middle segment pass through at a constant speed in the whole motion process, the motion track is more stable, and the S-shaped acceleration and deceleration is realized: the traditional S-shaped acceleration and deceleration model is based on a common speed curve model, introduces the physical concept of jerk and is used for measuring the flexibility of a mechanical system. The introduction of jerk can reduce the impact on the motor and the robot system in the running process. The S-shaped acceleration and deceleration model can be divided into 7 parts according to stages: acceleration stage, uniform acceleration stage, deceleration stage, uniform speed stage, acceleration and deceleration stage, uniform speed stage, and deceleration stage. The sinusoidal acceleration and deceleration control algorithm segments acceleration and deceleration of the motion process, and the principle is that the acceleration stage is: the acceleration a varies with time according to a sine law, from 0 to a maximum value and then to 0. The acceleration value is always positioned on the positive half axis of the y coordinate axis in the whole acceleration stage, and the speed reaches the maximum value from 0 in the stage, namely the speed cm in the uniform speed stage; constant speed stage: run at constant speed vm to a deceleration phase, which is also the main phase of robot end effector operation; a deceleration stage: the acceleration a varies with time according to a sine rule, from 0 to a minimum value and then to 0. In the whole acceleration stage, the acceleration value is always positioned on a negative half axis of a y coordinate axis, the speed vm is reduced to 0 in a uniform speed stage, at the moment, the robot end effector finishes a preset track, reaches a target position, and ends the operation; normal acceleration constraint is introduced on a track look-ahead algorithm, the maximum feeding speed of arc machining is limited, the feeding speed of the engagement points is optimized through comprehensive constraint conditions such as motion vector relation, system dynamics performance and track section length, smooth transition of continuous track sections in robot motion is realized, and stability is improved;
Planning a massage force position by using a preset force position hybrid control algorithm, and adjusting a massage track in real time according to the massage force position; the specific content of the preset force-position hybrid control algorithm is not limited, and optionally, in the embodiment, the force-position hybrid control is realized by using admittance impedance control, so that the effect of normal constant force pressing of the massage head is further realized, and further, in the embodiment, the preset force-position hybrid control algorithm is used for acquiring the force to be applied to the human body; calculating acceleration of the massage executing section by a force to be applied to the human body; calculating the tail end pose of the massage executing part according to the force and the acceleration to be applied to the human body, and calculating the movement angle of the massage executing part according to the tail end pose and the mechanical arm kinematics inverse connection; force-position mixed control is introduced, so that constant force pressing is kept in the contact direction of the massage head and the human body, the massage effect is achieved, and the problem that the point cloud position and the gesture which are visually recognized are not attached or extruded due to inherent errors is solved. Further, in this embodiment, the preset force-bit hybrid control algorithm calculation formula includes:
The acceleration is calculated and the acceleration is calculated,
The position and the posture of the tail end are calculated,
Wherein F is the force to be applied to the human body, M is the inertia parameter of the impedance control, B is the damping parameter of the impedance control, K is the stiffness parameter of the impedance control, deltat is the calling period, x is the position of the massage executing part,Representing the speed of the massage execution unit,/>The acceleration of the massage execution unit is shown.
The position and the gesture of the point cloud recognized by vision have certain errors, and even if the position is 1mm different from the target position when the point cloud is completely operated according to the planned track, the situation of non-fitting or extrusion can be caused, so that the force-position mixed control is introduced, the constant force pressing is ensured in the contact direction of the massage head and the human body, and the massage effect is achieved;
Completing the massage according to the pose track and the massage force position; the visual recognition algorithm, the irregular track planning algorithm and the force-position hybrid control algorithm based on deep learning act together to achieve the mutual coordination of eyes, hands, touch and brains. Avoiding the speed of 'eyes', avoiding the stop and go of the track and avoiding the negligence of force. The massage effect is more balanced and smooth and is more fit than the human hand force.
Example III
A massage method, the massage robot is controlled to massage by using the control method as described above.
It is to be understood that the above-described embodiments of the present invention are merely illustrative of or explanation of the principles of the present invention and are in no way limiting of the invention. Accordingly, any modification, equivalent replacement, improvement, etc. made without departing from the spirit and scope of the present invention should be included in the scope of the present invention. Furthermore, the appended claims are intended to cover all such changes and modifications that fall within the scope and boundary of the appended claims, or equivalents of such scope and boundary.
In the above description, technical details of patterning, etching, and the like of each layer are not described in detail. It will be appreciated by those skilled in the art that layers, regions, etc. of the desired shape may be formed by various means known in the art. In addition, to form the same structure, those skilled in the art can also devise methods that are not exactly the same as those described above.
The invention has been described above with reference to the embodiments thereof. These examples are for illustrative purposes only and are not intended to limit the scope of the present invention. The scope of the invention is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the invention, and such alternatives and modifications are intended to fall within the scope of the invention.
Claims (7)
1. A method of controlling a massage robot, the massage robot comprising: a robot body (1), wherein the robot body (1) comprises an information acquisition part (4), a system control part (2) and a massage execution part (3); the information acquisition part (4), the system control part (2) and the massage execution part (3) are electrically connected;
the information acquisition part (4) acquires an image of the region to be massaged;
The system control part (2) plans a massage track, a pose track and a massage force position according to the image acquired by the information acquisition part; the massage execution unit (3) executes massage according to the plan of the system control unit;
The control method comprises the following steps:
Acquiring an image of an area to be massaged;
The obtained image of the area to be massaged is in one-to-one correspondence with three-dimensional point cloud data of a preset general massage area, and massage key points and positions on the image of the area to be massaged are obtained; the three-dimensional point cloud data of the preset general massage area are obtained through training;
Planning a massage track by utilizing a preset NURBS curve according to the massage key points on the image of the area to be massaged;
the massage track is adjusted in real time by using a preset force-position hybrid control algorithm;
Completing the massage according to the massage track and the force position mixed control algorithm;
the preset force bit hybrid control algorithm comprises the following steps:
Acquiring a force to be applied to the massage region;
Calculating acceleration of the massage executing section according to the force to be applied to the massage region;
Calculating the tail end pose of the massage executing part according to the force and the acceleration to be applied to the massage area;
and calculating the motion angle of the massage executing part according to the tail end pose and the mechanical arm kinematics inverse solution.
2. The control method according to claim 1, characterized in that: the system control part (2) comprises a model training subsystem, a track generation subsystem, a pose control subsystem and a force and position mixed control subsystem;
The model training subsystem obtains three-dimensional point cloud data of a general massage area through deep learning training, the track generation subsystem plans a massage track according to the image of the massage area to be massaged, which is acquired by the information acquisition part, the pose control subsystem generates a pose track according to the planned massage track, and the force and position hybrid control subsystem plans massage force positions according to the pose track.
3. The control method according to claim 1, characterized in that: the massage executing part (3) comprises a massage mechanical arm (3-1), a massage head (3-2) and a heating component; the massage head (3-2) is arranged at the end part of the massage mechanical arm (3-1), the heating component is arranged inside the massage head (3-2), and the heating component is used for heating the massage head (3-2).
4. The control method according to claim 1, wherein,
The image of the region to be massaged is acquired and comprises a two-dimensional image and a three-dimensional image;
the obtained image of the area to be massaged is in one-to-one correspondence with three-dimensional point cloud data of a preset general massage area, and massage key points on the image of the area to be massaged are obtained, and the method comprises the following steps:
Generating a two-dimensional track and two-dimensional track key points according to the two-dimensional image of the region image to be massaged;
Converting the two-dimensional track key points into three-dimensional key points in a three-dimensional image of the region image to be massaged according to a preset first conversion rule;
And the three-dimensional key points are in one-to-one correspondence with the three-dimensional point cloud data of the preset general massage area, and the massage key points on the image of the area to be massaged are obtained.
5. The control method according to claim 4, wherein the step of obtaining the pose on the image of the area to be massaged by one-to-one correspondence between the obtained image of the area to be massaged and the three-dimensional point cloud data of the preset general massage area comprises:
Obtaining positions and normal vectors of the three-dimensional point cloud data corresponding to the massage key points;
And converting the position and the normal vector into a pose according to a preset second conversion rule.
6. The control method according to claim 1, wherein planning the massage trajectory further comprises adjusting the pose trajectory in the massage trajectory in real time using a preset pose algorithm; the preset pose algorithm comprises an S-shaped acceleration and deceleration or sine-shaped acceleration and deceleration control algorithm, and the S-shaped acceleration and deceleration or sine-shaped acceleration and deceleration control algorithm comprises a track look-ahead algorithm.
7. The control method according to claim 1, wherein the preset force-bit hybrid control algorithm calculation formula includes:
The acceleration is calculated and the acceleration is calculated,
The position and the posture of the tail end are calculated,
Wherein F is the force applied to the human body, M is the inertia parameter of the impedance control, B is the damping parameter of the impedance control, K is the rigidity parameter of the impedance control, deltat is the calling period, x is the position of the massage executing part,Representing the speed of the massage execution unit,/>The acceleration of the massage execution unit is shown.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311033198.9A CN117045497B (en) | 2023-08-16 | 2023-08-16 | Massaging robot, control method and massaging method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311033198.9A CN117045497B (en) | 2023-08-16 | 2023-08-16 | Massaging robot, control method and massaging method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117045497A CN117045497A (en) | 2023-11-14 |
CN117045497B true CN117045497B (en) | 2024-04-23 |
Family
ID=88654832
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311033198.9A Active CN117045497B (en) | 2023-08-16 | 2023-08-16 | Massaging robot, control method and massaging method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117045497B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109674647A (en) * | 2019-03-07 | 2019-04-26 | 西安伊蔓蒂电子科技有限公司 | A kind of massage robot |
CN113221958A (en) * | 2021-04-19 | 2021-08-06 | 深圳瀚维智能医疗科技有限公司 | Method, device and system for matching massage track with massage area and storage medium |
CN115533906A (en) * | 2022-10-09 | 2022-12-30 | 网易(杭州)网络有限公司 | Robot control method, device, electronic device and storage medium |
CN115741732A (en) * | 2022-11-15 | 2023-03-07 | 福州大学 | Interactive path planning and motion control method of massage robot |
CN115944518A (en) * | 2023-02-13 | 2023-04-11 | 天津尼瑞艾特测控技术有限公司 | Back massage manipulator, intelligent back massage robot and massage method thereof |
-
2023
- 2023-08-16 CN CN202311033198.9A patent/CN117045497B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109674647A (en) * | 2019-03-07 | 2019-04-26 | 西安伊蔓蒂电子科技有限公司 | A kind of massage robot |
CN113221958A (en) * | 2021-04-19 | 2021-08-06 | 深圳瀚维智能医疗科技有限公司 | Method, device and system for matching massage track with massage area and storage medium |
CN115533906A (en) * | 2022-10-09 | 2022-12-30 | 网易(杭州)网络有限公司 | Robot control method, device, electronic device and storage medium |
CN115741732A (en) * | 2022-11-15 | 2023-03-07 | 福州大学 | Interactive path planning and motion control method of massage robot |
CN115944518A (en) * | 2023-02-13 | 2023-04-11 | 天津尼瑞艾特测控技术有限公司 | Back massage manipulator, intelligent back massage robot and massage method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN117045497A (en) | 2023-11-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ma et al. | Hand rehabilitation learning system with an exoskeleton robotic glove | |
Ning et al. | Autonomic robotic ultrasound imaging system based on reinforcement learning | |
Agah | Human interactions with intelligent systems: research taxonomy | |
Ben-Tzvi et al. | The design evolution of a sensing and force-feedback exoskeleton robotic glove for hand rehabilitation application | |
JPWO2016002885A1 (en) | Rehabilitation support device and control program for rehabilitation support device | |
Kawasaki et al. | Humanoid robot hand and its applied research | |
Nakata et al. | Development of ‘ibuki’an electrically actuated childlike android with mobility and its potential in the future society | |
Kuang et al. | A wearable haptic device for the hand with interchangeable end-effectors | |
CN117045497B (en) | Massaging robot, control method and massaging method | |
Ma et al. | Sensing and force-feedback exoskeleton robotic (SAFER) glove mechanism for hand rehabilitation | |
Ketkar et al. | Design and development of a spherical 5-bar thumb exoskeleton mechanism for poststroke rehabilitation | |
Srimathveeravalli et al. | Comparative study: Virtual fixtures and shared control for rehabilitation of fine motor skills | |
Infantino et al. | A cognitive architecture for robotic hand posture learning | |
Assad Uz Zaman et al. | Robot sensor system for supervised rehabilitation with real-time feedback | |
Fernando et al. | Experiencing ones own hand in telexistence manipulation with a 15 DOF anthropomorphic robot hand and a flexible master glove | |
Tzafestas et al. | Human–machine interaction in intelligent robotic systems: A unifying consideration with implementation examples | |
James et al. | Realtime hand landmark tracking to aid development of a prosthetic arm for reach and grasp motions | |
Parida | Kinematic analysis of multi-fingered, anthropomorphic robotic hands | |
Ayub et al. | ‘AZ’Humanoid Robot Head with Object and Color Tracking Capabilities | |
Gentili et al. | Human-robotic collaborative intelligent control for reaching performance | |
Lee | Modeling articulated figure motion with physically-and physiologically-based constraints | |
Li | Research on robot boxing movement simulation based on kinect sensor | |
Rodriguez et al. | A 3-D hand rehabilitation system using haptic device | |
Xu | Design, Development, and Control of an Assistive Robotic Exoskeleton Glove Using Reinforcement Learning-Based Force Planning for Autonomous Grasping | |
He et al. | Spherical parallel instrument for daily living emulation (SPINDLE) to restore motor function of stroke survivors |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |