Navigation method and system for semi-automatic robot

Abstract

The invention relates to the technical field of orthodontics, in particular to a navigation method and system for a semi-automatic robot, and the method comprises the following steps: setting a reference mark; defining a first space coordinate system by adopting an optical positioning camera, wherein the first space coordinate system is used for defining a first coordinate of the reference mark; the target model defines the relative position between the reference mark and the teeth through a second space coordinate system; registering the first space coordinate system and the second space coordinate system by adopting a coordinate system registration algorithm, and correspondingly converting the first coordinates to obtain first and second reference coordinates of the first and second reference points in the first space coordinate system; calculating a first reference distance and a second reference distance of the first reference point and the second reference point in the first space coordinate system and the second space coordinate system; if the difference value between the first reference distance and the second reference distance is smaller than a set reference threshold value, a first navigation point of the grabbing mechanism is determined according to the reference point. The invention solves the problem that the existing navigation method has high performance requirements on hardware equipment.

Description

[0001] Divisional application This application is a divisional application of the patent application

Application No.: CN202411338484.0

Invention Title: A Robot Navigation Method and System for Batch Installation of Brackets

[0002] The present invention relates to an orthodontic robot, and more particularly to a navigation method and system applicable to a semi-automatic robot. Background technique

[0003] Defects such as malocclusion of teeth will not only affect the appearance, but also have an irresistible impact on chewing, pronunciation, etc., seriously reducing the quality of life of patients.

[0004] Orthodontics is aimed at tooth malocclusion. By using an appliance to apply mechanical corrective forces and moments to the teeth, the balance and coordination among the facial bones, teeth, and maxillofacial muscles are adjusted. After a period of orthodontic treatment, the facial shape can be improved, the tooth alignment can be corrected, and the chewing efficiency can be enhanced.

[0005] In traditional orthodontic clinical operations, especially bracket bonding operations, they are mainly completed manually by orthodontists, which requires high doctor experience and fine manual operation skills. Moreover, there are large artificial operation errors and significant differences in operation techniques, resulting in high technical thresholds and irregular treatments in orthodontic clinical operations. Clinically, to improve the accuracy of bracket bonding, an indirect bonding method is proposed, that is, designing a bonding guide plate to assist in the transfer of bracket positions. However, even with this auxiliary method, extremely high requirements are still placed on the doctor's manual operation force and accuracy.

[0006] Patent application CN116737031A discloses a root information visualization system and method based on mixed reality. The system includes a tracking rigid body 1, a tracking rigid body 2, a probe, an optical tracking device, a mixed reality glasses, a checkerboard calibration board, an orthodontic anchorage screw implantation navigation system, and a visualization system. The method includes an optical tracking device - mixed reality glasses calibration method and a complete dentition virtual model - patient real space registration method. The optical tracking device - mixed reality glasses calibration method is used to unify the internal coordinate systems of the optical tracking device and the mixed reality glasses. The complete dentition virtual model - patient real space registration method is used to unify the coordinate system of the complete dentition virtual model with the coordinate system of the patient's real space.

[0007] Patent application CN112545650A discloses a navigation positioning method and system for dentistry, which comprises the following steps: attaching a developing ball to a dental retainer, placing the dental retainer on the target dentition of the patient, acquiring the data of the target dentition and the hard and soft tissues of the oral and maxillary bones at the target dentition by scanning, and establishing a corresponding target dentition reference space three-dimensional model with developing points in the three-dimensional navigation map in the navigation system; before the operation, the developing ball is clicked by a surgical instrument to match the target dentition with the reference space three-dimensional model to complete the reference positioning of the target dentition; during the operation, a positioning rod arranged in the oral cavity acquires the position and posture of the target dentition in the oral cavity in real time through a first vision system in coordination with a second vision system arranged in the surgical instrument, as well as the position and posture of the surgical instrument; and marking the spatial position in the three-dimensional coordinate system of the reference space three-dimensional model, thereby achieving real-time tracking and positioning of the positional relationship between the surgical instrument and the target dentition during the operation.

[0008] Patent application CN101249001A also discloses a three-dimensional image navigation positioning method and a special device for orthodontic implant support, which uses an infrared camera lens to emit or receive infrared rays, and determines the specific position of the device by tracking the position of the infrared reflective ball on the self-designed orthodontic implant support positioning device, and transmits the signal back to the computer so that the position of the positioning device can be displayed on the patient's preoperative or intraoperative image data. The software is used to compare the three-dimensional spatial orientation of the positioning device determined before the operation, and the connected mechanical arm is used to adjust the orientation of the positioning device to meet the preoperative design requirements. When the designed position is reached, the implant support can be accurately implanted according to the orientation and depth guided by the stereotactic device.

[0009] However, traditional surgical robots have high performance requirements for hardware equipment, which is not conducive to practical application. Summary of the invention

[0010] The object of the present invention is to provide a robot navigation method for batch installation of brackets, which partially solves or alleviates the above-mentioned deficiencies in the prior art and can reduce the computational pressure of real-time navigation by means of segmented navigation.

[0011] In order to solve the above-mentioned technical problems, the present invention specifically adopts the following technical solutions: A first aspect of the present invention is a robot navigation method for batch installation of brackets, comprising the steps of: S200, setting reference marks, the reference marks comprising: a first reference mark set at at least one first target position on the mouth opener, and a second reference mark set at at least another first target position on the mouth opener, the mouth opener being worn in the oral cavity of the subject to open and fix the oral cavity; S201, define a first spatial coordinate system using an optical positioning camera, where the first spatial coordinate system is used to define the first coordinates of the current first reference mark and the second reference mark; S202, provide a preset target model for simulating the oral cavity and the mouth opener, where the target model defines the relative positions between at least one reference mark and the teeth through a second spatial coordinate system; at least two grasping mechanisms are provided at the end of the robot, and the grasping mechanisms are used to grasp and install the brackets; the at least two grasping mechanisms can simultaneously install the brackets on a set of teeth; S203, perform registration on the first spatial coordinate system and the second spatial coordinate system using a coordinate system registration algorithm, and obtain the first reference coordinate of the first reference point in the first spatial coordinate system through corresponding transformation of one of the first coordinates, and obtain the second reference coordinate of the second reference point in the first spatial coordinate system through corresponding transformation of the other first coordinate; the reference point is the tooth; S204, calculate the first reference distance and the second reference distance of the first reference point and the second reference point in the first spatial coordinate system and the second spatial coordinate system respectively; S205, determine whether the difference between the first reference distance and the second reference distance is less than a set reference threshold, if so, execute S206; S206, determine the first navigation point of at least one grasping mechanism according to at least one reference point, and the distance between the first navigation point and the reference point is greater than a set first threshold.

[0012] In some embodiments, the first reference point and the second reference point are respectively located on different teeth in the set of teeth.

[0013] In some embodiments, the first target position includes one or more of the following: positions on the mouth opener corresponding to the labial tubercle, labial peak, vermilion border, dental midline.

[0014] In some embodiments, before step S203, it further includes: Obtain a first image of the oral cavity and the mouth opener at a first shooting angle at the first moment; wherein, the first image shows a second target position; the second target position includes one or more of the following: labial tubercle, labial peak, vermilion border, incisor, canine, premolar, molar; Obtain a second image of the target model at the first shooting angle; Calculate a first target interval D1 between the first target position and the second target position in the first image, and calculate a second target interval D2 between the corresponding first target position and the second target position in the second image; Calculate a first difference ratio X1 between the first target interval D1 and the second target interval D2; wherein, X1 = |D1 - D2| / D1; or, X1 = |D1 - D2| / D2; Determine whether the first difference ratio X1 is less than a preset second difference threshold; If so, allow the execution of S203; if not, send a first misalignment prompt signal to the user.

[0015] In some embodiments, the creating step of the target model includes: Collect multiple photos of the object wearing the mouth opener, the photos including: at least one reference mark and at least one tooth, and there is an overlapping part between any two of the multiple photos; Create the corresponding target model according to the multiple photos, and the target model is used to describe the positional relationship between the mouth opener and the teeth in the second space coordinate system.

[0016] In some embodiments, it further includes the step of: Determine the reference coordinates of the robot moving to the final target point in the second space coordinate system through the target model.

[0017] In some embodiments, it further includes: Convert the reference coordinates of the target point to obtain the first measurement coordinates of the target point in the first space coordinate system; The robot continues to move from the first navigation point to the first measurement coordinates.

[0018] In some embodiments, the step of continuing to move from the first navigation point to the first measurement coordinates includes: Determine a second navigation point, and the distance between the second navigation point and the first measurement coordinates is less than a second threshold; When the orthodontic robot moves to the second navigation point at a second speed, obtain a third image of the oral cavity at a second shooting angle through a micro camera arranged at a position adjacent to the end of the robot; Obtain a fourth image of the target model at the second shooting angle; Calculate a third target interval D3 between the first target position and the second target position in the third image, and calculate a fourth target interval D4 between the corresponding first target position and the second target position in the fourth image; Calculate a second difference ratio X2 between the third target interval D3 and the fourth target interval D4; Wherein, X2 = |D3 - D4| / D3; or X2 = |D3 - D4| / D4; Determine whether the second difference ratio X2 is less than a preset third difference threshold; If not, a second misalignment prompt signal is sent to the user.

[0019] In some embodiments, the photograph is a CT scan photograph or a standard orthodontic intraoral photograph.

[0020] The present invention also provides a robot navigation system for batch installation of brackets, comprising: Reference marks, the reference marks comprising: a first reference mark disposed at at least one first target position on the mouth opener, and a second reference mark disposed at at least one other first target position on the mouth opener, the mouth opener being worn in the oral cavity of a subject to open and fix the oral cavity; A first positioning module, used for defining a first spatial coordinate system using an optical positioning camera, wherein the first spatial coordinate system is used for defining first coordinates of the first reference mark and the second reference mark; A second positioning module is used to provide a preset target model for simulating the oral cavity and the mouth opener, wherein the target model defines the relative position between at least one reference mark and the teeth through a second spatial coordinate system; at least two grasping mechanisms are provided at the end of the robot, and the grasping mechanisms are used to grasp and install the brackets; the at least two grasping mechanisms can simultaneously install the brackets on a group of teeth; a third positioning module, configured to align the first spatial coordinate system and the second spatial coordinate system by using a coordinate system alignment algorithm, and obtain a first reference coordinate of a first reference point in the first spatial coordinate system by corresponding transformation of one of the first coordinates, and obtain a second reference coordinate of a second reference point in the first spatial coordinate system by corresponding transformation of another of the first coordinates; the reference point is the tooth; A reference distance calculation module, used to calculate a first reference distance and a second reference distance of the first reference point and the second reference point in the first spatial coordinate system and the second spatial coordinate system respectively; The first judgment module is used to judge whether the difference between the first reference distance and the second reference distance is less than a set reference threshold value. If so, a first navigation point of at least one grasping mechanism is determined based on at least one reference point, and the distance between the first navigation point and the reference point is less than a set first threshold value.

[0021] Beneficial technical effects: The present invention provides a segmented navigation method based on finite optical markers. This segmented navigation method based on finite optical markers can reduce the real-time computing pressure of robot navigation during orthodontic process to a certain extent, thereby reducing the application cost of robot equipment.

[0022] Specifically, the segmented navigation of the present invention can be combined with the remote operation of doctors: By selecting the first and second navigation points and performing segmented navigation, the robot can be quickly positioned and navigated to the operable area (when the robot moves to the operable area, the robot can complete the positioning and installation of the bracket only through a small displacement amount), and the subsequent precise positioning and installation are completed by the doctor manually controlling the robot coordinates, thereby reducing the manual operation workload of the doctor.

[0023] For remote areas with relatively scarce medical resources, it is difficult to bear the economic cost of configuring high-precision medical equipment. And a semi-automatic operation robot implemented based on segmented navigation provided by the present invention can effectively reduce the computing pressure of the robot's automatic navigation, thereby reducing the requirements of the robot for hardware performance and reducing the implementation cost.

[0024] When the robot is connected to the computer system, the doctor can perform remote orthodontic operations with the help of the robot. For example, when the patient's malocclusion defect is relatively serious and assistance from doctors in other places is required, or when the doctor fails to arrive at the orthodontic site for some reason, the orthodontic operation can be completed by controlling the robot. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts do not necessarily draw according to the actual ratio. Obviously, the following-described drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 It is a schematic diagram of the navigation path in an exemplary embodiment of the present invention; Figure 2 It is a schematic diagram of the operation state of the robot in an exemplary embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of the equipment table in an exemplary embodiment of the present invention; Figure 4 It is a schematic diagram of the structure of the mouth opener in an exemplary embodiment of the present invention; Figure 5 It is a schematic diagram of the structure of the bracket in an exemplary embodiment of the present invention; Figure 6 It is a schematic diagram of the flow step of the robot navigation method in an exemplary embodiment of the present invention; Figure 7Schematic flow chart of the method for batch installation of brackets in another embodiment of the present invention.

[0027] Summary of reference numeral identifications: 001 is the equipment table, 002 is the bracket, 003 is the mouth opener, 004 is the robot, 005 is the reference mark, O1 is the initial point, O2 is the first navigation point, and O3 is the target point. Detailed implementation manners

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0029] In this article, suffixes such as "module", "component", or "unit" used to represent elements are only for the convenience of describing the present invention, and they have no specific meaning themselves. Therefore, "module", "component", or "unit" can be used interchangeably.

[0030] In this article, terms such as "upper", "lower", "inner", "outer", "front", "rear", "one end", "the other end", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. They are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0031] In this article, unless otherwise clearly specified and limited, terms such as "installation", "provided with", "connection", etc. should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, a direct connection, or an indirect connection through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0032] In this article, "and / or" includes any and all combinations of one or more of the listed related items.

[0033] In this article, "a plurality of" means two or more, that is, it includes two, three, four, five, etc.

[0034] It should be noted that, in this text, the term "comprise", "include" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device that comprises a series of elements not only includes those elements but also includes other elements not expressly listed, or elements that are inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device that comprises such element.

[0035] As used in this specification, the term "about" typically means + / - 5% of the stated value, more typically + / - 4% of the stated value, more typically + / - 3% of the stated value, more typically + / - 2% of the stated value, even more typically + / - 1% of the stated value, and even more typically + / - 0.5% of the stated value.

[0036] In this specification, certain embodiments may be disclosed in a format that is within a certain range. It should be understood that this type of "within a certain range" description is merely for convenience and brevity and should not be construed as a rigid limitation on the disclosed range. Accordingly, the description of a range should be considered to have specifically disclosed all possible sub-ranges and the individual numerical values within that range. For example, the description of the range 1 - 6 should be regarded as having specifically disclosed sub-ranges such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6, etc., as well as the individual numbers within that range, such as 1, 2, 3, 4, 5, and 6. This rule applies regardless of the breadth of the range.

[0037] In this text, the mouth gag is also called the oral speculum. When a patient wears the mouth gag, it can keep the mouth open. For example, the mouth gag body can be in a "U" shape, and a handle is fixedly connected to each of the two end portions of the mouth gag body. The mouth gag body is elastic, and the two side arms of the mouth gag body can bend towards the inside or outside of the mouth gag body when pressed by an external pressure, and when the external pressure disappears, the two side arms of the mouth gag body return to their original positions.

[0038] In this text, the "optical positioning camera" can use visible light and computer vision to detect passive marker targets (i.e., reference markers) and track these targets by processing standard video images.

[0039] In this article, "coordinate system registration" refers to the process of converting the coordinates of one spatial reference system into another spatial reference system. For example, in order to improve orthodontic efficiency, before the robot performs the bracket installation task, the oral area of ​​the object (i.e., the patient) can be 3D modeled to create a target model, where the target model will define the relative position relationship between the mouth opener (especially the reference mark) and the teeth (or the target point to which the robot needs to run) through the second spatial coordinate system. Furthermore, when it is necessary to perform actual orthodontic operations on the object, a first spatial coordinate system can be created based on the current environment, and the coordinates I of at least one reference mark (such as at least three reference marks) in the first spatial coordinate system can be obtained through an optical positioning camera. With the help of the relative position relationship in the second spatial coordinate system, the coordinates II of the teeth (or target point) in the first spatial coordinate system can be indirectly calculated through the coordinates I. This process is also called coordinate system registration.

[0040] In this article, "image positioning" refers to the process of obtaining image data through an image acquisition device (such as a camera), preprocessing the image data, including denoising, enhancement, and segmentation, extracting image feature information such as color, texture, shape, etc., and then using a specific positioning algorithm to match and locate the image features to determine the location of the target. For example, image positioning can be achieved through deep learning technology.

[0041] Embodiment 1 See also Figure 6 As shown, the present invention provides a navigation method for an orthodontic robot, which comprises the steps of: S100, setting reference marks, the reference marks comprising: a first reference mark set at at least one first target position on the mouth opener, and a second reference mark set at at least another first target position on the mouth opener, the mouth opener 003 being worn in the oral cavity of the subject to open and fix the oral cavity; For example, in some embodiments, the first target position includes one or more of the following: a position on the mouth opener corresponding to a lip bead, a lip peak, a lip vermilion, a midline of a dentition (such as a gap between adjacent incisors); Preferably, the reference marking is an optical marking.

[0042] Preferably, the optical marker can be a marker ball with an infrared sensitive coating or a visible light marker target.

[0043] Preferably, the optical mark can be set as an indicator graphic such as a triangle or a straight line to assist the user in adjusting the wearing position of the mouth opener.

[0044] S101. Define a first spatial coordinate system W1 using an optical positioning camera. The first spatial coordinate system W1 is used to define the first coordinates A1 of the current first reference mark and the second reference mark. For example, when a patient wears a mouth gag and lies on a dental chair, the optical positioning camera can identify the actual coordinates of the reference marks.

[0045] S102. Provide a preset target model for simulating the oral cavity and the mouth gag. The target model defines the relative positions between at least one reference mark and a target point or a tooth through a second spatial coordinate system W2. The target point is the position where the orthodontic robot installs a bracket on the tooth. S103. Register the first spatial coordinate system W1 and the second spatial coordinate system W2 using a coordinate registration algorithm, and correspondingly transform the first coordinates A1 to obtain the first measurement coordinates B1 of the target point or the tooth in the first spatial coordinate system. That is to say, the position of the target point or the tooth in the first spatial coordinate system, namely the first measurement coordinates B1, can be indirectly measured through the actual coordinates of the reference marks. In some embodiments, the optical positioning camera can be a binocular vision optical positioning camera.

[0046] For example, in some embodiments, the total number of the first reference mark and the second reference mark in S101 is at least three. Or, in order to improve the registration accuracy, more reference marks can also be used.

[0047] S104. Determine a first navigation point according to the first measurement coordinates. The orthodontic robot moves to the first navigation point at a first speed. The first distance between the first navigation point and the first measurement coordinates is greater than a set first threshold. S105. When the orthodontic robot moves to the first navigation point, obtain the second coordinates of the first reference mark and the second reference mark in the first spatial coordinate at the second moment. S106. Calculate at least one first difference between the first coordinates and the second coordinates. S107. Determine whether the first difference is less than a set first difference threshold. If so, allow the orthodontic robot to continue moving from the first navigation point to the first measurement coordinates.

[0048] In this embodiment, the first difference refers to the distance between the positions of the reference mark 005 at the first moment and the second moment.

[0049] For example, in some embodiments, at least one first difference can be calculated based on at least one first reference mark, and at least one second difference can be calculated based on at least one second reference mark. When multiple first differences are all less than the first difference threshold, it is considered that the position offset of the mouth opener at the first and second moments is within the tolerable range. At this time, the movement can continue as planned from the first navigation point to the next desired position (such as at the first measurement coordinate).

[0050] In this embodiment, preferably, a plurality of reference marks are provided on the mouth opener, which helps the doctor to judge the wearing position of the mouth opener, so that the position of the mouth opener during orthodontic treatment is the same as (or has a relatively small deviation from) the position of the mouth opener in the target model, and further enables the robot to indirectly locate the teeth or target points through the target model during the actual navigation process.

[0051] In some embodiments, the first speed is greater than the second speed.

[0052] This embodiment actually provides a segmented navigation method.

[0053] It should be noted that during orthodontic treatment, brackets need to be pasted on multiple teeth of the patient. During this long pasting process, the patient's oral cavity may continuously shift due to head movement. Moreover, to ensure the orthodontic effect, the brackets need to be accurately installed in specific areas on the teeth. If the position deviates, the bracket installation will fail. Therefore, this places higher requirements on the real-time navigation ability of the robot.

[0054] In response to this, the traditional orthodontic robot navigation idea is: collect the real-time facial skin point cloud data of the patient, and calculate the navigation path of the robot through the real-time facial skin point cloud data. However, the applicant has found that when this method of real-time collecting and calculating point cloud data is applied to scenarios with a large target activity range (for example, especially when the patient is a child, it is very difficult for them to maintain a relatively fixed posture for a long time), the data collection and monitoring difficulty will increase significantly.

[0055] On the contrary, for this orthodontic operation scenario where the patient has a high degree of freedom (that is, the head may move at any time), the present invention provides a segmented navigation method based on limited optical marks. This segmented navigation method based on limited optical marks can reduce the real-time operation pressure of robot navigation during orthodontics to a certain extent, and thus reduce the application cost of the robot device.

[0056] For example, referring to Figures 1 - 5 As shown, the working process of the orthodontic robot is as follows: The robot 004 needs to grasp the bracket 002 from the equipment table 001, and then move from the initial point O1 to the target point O3 to complete the automatic installation of the bracket. Specifically, when moving from the initial point O1 (i.e., the current position of the orthodontic robot) to the target point O3 (i.e., the position where the robot needs to move to paste the bracket), a first navigation point O2 can be created first at the first moment T1, and by setting the first navigation point O2, the long-distance path formed by the initial point O1 and the target point O3 is divided into a first path and a second path. Further, during the process of moving to the first navigation point O2 through the first path, a relatively fast speed can be adopted, and when moving to the first navigation point O2, it can be further determined whether there is a large deviation between the position of the optical marker at the current moment (i.e., the second moment T2) and the position at the first moment T1 (i.e., to judge the degree of the patient's head movement at this stage). When the position deviation between the two moments is small, the robot can move above the teeth at a slower speed under camera positioning, and then complete the installation of the bracket.

[0057] In some embodiments, before step S103, it further includes: Obtaining a first image of the oral cavity and the mouth opener at the first shooting angle at the first moment; wherein, the first image shows a second target position; the second target position includes one or more of the following: labial tubercle, lip peak, vermilion border, incisor, canine, premolar, molar. Further, the second target position can be the center points of the incisor, canine, premolar, and molar.

[0058] Obtaining a second image of the target model at the first shooting angle; Calculating a first target interval D1 between the first target position and the second target position in the first image, and calculating a second target interval D2 between the corresponding first target position and the second target position in the second image; Calculating a first difference ratio X1 between the first target interval D1 and the second target interval D2; wherein, X1 = |D1 - D2| / D1; or, X1 = |D1 - D2| / D2; Judging whether the first difference ratio X1 is less than a preset second difference threshold; If so, allowing the execution of S103; if not, sending a first misalignment prompt signal to the user.

[0059] For example, when the user receives the first misalignment prompt signal, the doctor can manually adjust the wearing position of the patient's mouth opener to make the wearing position of the mouth opener close to the set position in the target model.

[0060] For example, in some embodiments, at least two shooting angles may be selected to respectively obtain at least two first images and at least two second images. And when at least two first difference ratios of at least two groups of images are all less than a second difference threshold, it is considered that the wearing position of the mouth opener is within the fault-tolerant range, and the coordinate registration operation is allowed to be performed.

[0061] For example, in some embodiments, a user can set a specific shooting angle by himself, such as the front view, side view, and so on.

[0062] Again, for example, in some embodiments, the shooting angle can be randomly selected by a camera (such as an optical positioning camera or other shooting devices connected to the robot). At this time, the specific shooting angle can also be calculated according to the position of the camera (specifically, the spatial coordinates and attitude angles of the camera can be obtained) and the position of the optical marker. Correspondingly, according to the shooting angle determined by the camera itself, an image of the target model at the same angle can be output.

[0063] In some embodiments, before step S102, it further includes: Collecting multiple photos of the object wearing the mouth opener, the photos including: at least one reference mark and at least one tooth, and there is an overlapping part between any two of the multiple photos; Creating a corresponding target model according to the multiple photos, the target model being used to describe the positional relationship between the mouth opener and the teeth in a second space coordinate system; Determining the spatial coordinates of the orthodontic robot moving to the final target point in the second space coordinate system through the target model.

[0064] For example, in some embodiments, after the target model is created, a doctor can manually set the final target point.

[0065] In some embodiments, the photos are CT scan photos.

[0066] In some embodiments, the photos are standard orthodontic intraoral images. For example, the standard orthodontic intraoral images include one or more of the following: front view, side view, 45° side view, front smile view, side smile view, 45° side smile view, right intraoral view, front intraoral view, left intraoral view, upper occlusal view, lower occlusal view, overbite and overjet view. In some embodiments, a grasping mechanism is provided at the end of the orthodontic robot, and the grasping mechanism is used to grasp at least one bracket.

[0067] In some embodiments, a micro camera is further provided near the end of the orthodontic robot, which can be used to take images of the oral cavity.

[0068] In some embodiments, the step of continuing to move from the first navigation point to the first measurement coordinate (in this embodiment, the first measurement coordinate may refer to the coordinate of the target point O3) includes: Determine a second navigation point, the distance between the second navigation point and the target point being less than a second threshold; When the orthodontic robot moves to the second navigation point, obtain a third image of the oral cavity at a second shooting angle through a micro camera provided at a position adjacent to the end of the orthodontic robot; Obtain a fourth image of the target model at the second shooting angle; Calculate a third target interval D3 between the first target position and the second target position in the third image, and calculate a fourth target interval D4 between the corresponding first target position and the second target position in the fourth image; Calculate a first difference ratio X2 between the third target interval D3 and the second target interval D4; Wherein, X2 = |D3 - D4| / D3; or X2 = |D3 - D4| / D4; Judge whether the second difference ratio X2 is less than a preset third difference threshold; If not, send a second misalignment prompt signal to the user; If so, allow the robot to continue moving closer to the target position.

[0069] For example, the processes of the robot moving to the first navigation point and the second navigation point can both be set as automatic navigation processes, and when the robot moves to the second navigation point, the user (such as a doctor) can manually intervene to finely adjust the end position of the robot.

[0070] For example, in some embodiments, when the robot moves to the second navigation point, due to reasons such as the movement of the patient, there may be a certain deviation between the current position of the robot and the expected position. At this time, by comparing the deviation between the actual observed image and the expected observed image (i.e., the third and fourth images), if the deviation is within an acceptable range, the robot can continue to run freely. On the contrary, if the deviation is relatively large, the doctor can manually observe the real-time image (such as obtained through a micro camera) and manually adjust the movement parameters of the robot to finely adjust the end position of the robot.

[0071] For example, in some embodiments, to save costs, a combined solution of automatic navigation and manual navigation can be adopted. Therefore, the process of the robot actively grasping the bracket from the equipment table and moving from the equipment table to the first navigation point can be automatically completed by the robot (reducing the manual operation amount of the doctor), while in the stage of continuing to move from the first navigation point to the second navigation point or making fine adjustments to the position at the second navigation point, manual adjustment can be introduced when the computer determines that the deviation is large. Especially when the doctor and the patient are in different regions, adopting this segmented navigation solution is beneficial to realizing remote orthodontic operation.

[0072] In the present invention, through the selection of the first and second navigation points and segmented navigation, the robot can be quickly positioned and navigated to the operable area (when the robot moves to the operable area, the robot can complete the positioning and installation of the bracket only through a small displacement amount), thereby reducing the manual operation labor amount of the doctor.

[0073] It should be noted that for remote areas with relatively scarce medical resources, it is difficult to bear the economic cost of configuring high-precision medical equipment. And a semi-automatic operation robot based on segmented navigation provided by the present invention can effectively reduce the computing pressure of the robot's automatic navigation, thereby reducing the requirements of the robot for hardware performance and reducing the implementation cost.

[0074] That is to say, this semi-automatic operation robot based on segmented navigation helps to promote the application of automated medicine in remote areas.

[0075] Moreover, when the robot is connected to the computer system, the doctor can also perform remote orthodontic operations with the help of the robot. For example, when the patient's malocclusion defect is relatively serious and assistance from out-of-town doctors is needed, or when the doctor fails to arrive at the orthodontic site due to some reasons, the orthodontic operation can be completed by controlling the robot.

[0076] For example, the robot can complete the processes of obtaining the bracket from the equipment table and moving from the equipment table to the first navigation point automatically. Subsequently, when the robot automatically moves to the operable area, the doctor manually intervenes.

[0077] Of course, in some embodiments, the fine adjustment at the second navigation point can also be automatically completed by image positioning technology. Specifically, for the movement process from the first navigation point to the target point, real-time image navigation can also be adopted.

[0078] For example, by collecting photos of teeth, high-precision positioning calculation of the teeth is performed, and then high-precision fine-tuning is carried out between the second navigation point and the target point to achieve automatic installation of brackets. And because the previous segmented navigation (equivalent to preliminary navigation) can effectively reduce the pressure of high-precision navigation, the overall computing resources consumed by this segmented navigation scheme are also relatively small, which is conducive to implementation.

[0079] In some embodiments, the optical positioning camera can be set on the robot, such as being installed on the robotic arm of the robot.

[0080] Or, in some other embodiments, the optical positioning camera can be independently set with the robotic arm, thereby reducing the load of the robotic arm, which helps to improve the positioning accuracy of the robotic arm. And, in order to avoid the robotic arm blocking the light or the oral cavity during movement, in some embodiments, before step S105, it further includes: Determine whether there are at least two reference marks that are not blocked; If so, execute step S105; If not, execute the following steps: Obtain the fifth image of the unblocked reference mark and the target tooth at the third shooting angle; Obtain the sixth image of the target model at the third shooting angle; Calculate the fifth target interval D5 between the first target position and the second target position in the fifth image, and calculate the sixth target interval D6 between the corresponding first target position and the second target position in the sixth image; Calculate the third difference ratio X3 between the fifth target interval D5 and the sixth target interval D6; where, X3 = |D5 - D6| / D5; or X3 = |D5 - D6| / D6; Determine whether the third difference ratio X3 is less than the set fourth difference threshold. If so, allow the orthodontic robot to continue moving from the first navigation point to the first measurement coordinate.

[0081] Otherwise, it is recommended that the user intervene manually to determine whether fine-tuning of the robot is required.

[0082] In this embodiment, the problem of blocked reference marks can be solved by using the method of image comparison.

[0083] Embodiment Two The present invention also provides a navigation system for an orthodontic robot, including: A first positioning module is used to define a first spatial coordinate system using an optical positioning camera, wherein the first spatial coordinate system is used to define the first coordinates of a current first reference mark and a second reference mark; the first reference mark is set at at least one first target position on the mouth opener, and the second reference mark is set at at least one second target position on the mouth opener; the mouth opener is worn in the mouth of the subject to open and fix the mouth; wherein the first target position includes one or more of the following: positions on the mouth opener corresponding to a lip bead, a lip peak, a lip vermilion, and a midline of a dentition; A second positioning module is used to provide a preset target model for simulating the oral cavity and the mouth opener, wherein the target model defines a relative position between at least one reference mark and a target point or a tooth through a second spatial coordinate system; the target point is the position of the orthodontic robot when installing the bracket on the tooth; A third positioning module, configured to register the first spatial coordinate system and the second spatial coordinate system by using a coordinate system registration algorithm, and obtain a first measurement coordinate of the target point or the tooth in the first spatial coordinate system by corresponding transformation of the first coordinate; A first navigation point calculation module, used for determining a first navigation point according to the first measurement coordinates, the orthodontic robot moves to the first navigation point at a first speed, and a first distance between the first navigation point and the first measurement coordinates is greater than a set first threshold; a fourth positioning module, configured to obtain, when the orthodontic robot moves to the first navigation point, second coordinates of the first reference mark and the second reference mark in the first space coordinate at a second moment; A first difference calculation module, used for calculating at least one first difference between the first coordinate and the second coordinate; The first navigation judgment module is used to judge whether the first difference is less than a set first difference threshold. If so, the orthodontic robot is allowed to continue moving from the first navigation point to the first measurement coordinate.

[0084] It can be understood that the system in the present invention can implement the method steps described in any of the above embodiments, which will not be repeated here.

[0085] Embodiment 3 See also Figure 7 As shown, the present invention also provides a robot navigation method capable of synchronously installing brackets on multiple teeth, comprising the steps of: S200, setting reference marks, the reference marks comprising: a first reference mark set at at least one first target position on the mouth opener, and a second reference mark set at at least another first target position on the mouth opener, the mouth opener being worn in the oral cavity of the subject to open and fix the oral cavity; S201, defining a first spatial coordinate system using an optical positioning camera, where the first spatial coordinate system is used to define first coordinates of the first reference mark and the second reference mark; S202, providing a preset target model for simulating the oral cavity and the mouth opener, wherein the target model defines a relative position between at least one reference mark and the teeth through a second spatial coordinate system; at least two grasping mechanisms are provided at the end of the robot, and the grasping mechanisms are used to grasp and install the brackets; the at least two grasping mechanisms can simultaneously install the brackets on a group of teeth; S203, aligning the first spatial coordinate system and the second spatial coordinate system using a coordinate system registration algorithm, and obtaining a first reference coordinate of a first reference point in the first spatial coordinate system by corresponding transformation of one of the first coordinates, and obtaining a second reference coordinate of a second reference point in the first spatial coordinate system by corresponding transformation of another of the first coordinates; the reference point is the tooth; S204 calculates a first reference distance and a second reference distance of the first reference point and the second reference point in the first spatial coordinate system and the second spatial coordinate system respectively; In this embodiment, the first reference distance is the distance between the first reference point and the second reference point in the first spatial coordinate system, the second reference distance is the distance between the first reference point and the second reference point in the second spatial coordinate system, and the first and second spatial coordinate systems use the same coordinate scale (in other words, the ratio of the coordinate scale in the first spatial coordinate system to the size in the actual space is the same as the ratio of the coordinate scale in the second spatial coordinate system to the size in the actual space); S205 determines whether the difference between the first reference distance and the second reference distance is less than a set reference threshold, and if so, executes S206; S206: Determine a first navigation point of at least one grasping mechanism according to at least one reference point, wherein a distance between the first navigation point and the reference point is less than a set first threshold.

[0086] The batch installation scheme proposed in this embodiment can effectively improve the efficiency of bracket installation, and the navigation point (or navigation trajectory) of the orthodontic robot can be verified through the first reference point and the second reference point, thereby improving the accuracy of the navigation scheme based on limited optical markers.

[0087] In some embodiments, the first reference point and the second reference point are respectively located on different teeth of the set of teeth.

[0088] In some embodiments, the first target position includes one or more of the following: positions on the mouth opener corresponding to the labial tubercle, labial peak, vermilion border, midline of dentition.

[0089] In some embodiments, before step S203, it further includes: Obtain a first image of the oral cavity and the mouth opener at the first shooting angle at the first moment; wherein, the first image shows a second target position; the second target position includes one or more of the following: labial tubercle, labial peak, vermilion border, incisor, canine, premolar, molar; Obtain a second image of the target model at the first shooting angle; Calculate a first target interval D1 between the first target position and the second target position in the first image, and calculate a second target interval D2 between the corresponding first target position and the second target position in the second image; Calculate a first difference ratio X1 between the first target interval D1 and the second target interval D2; wherein, X1 = |D1 - D2| / D1; or, X1 = |D1 - D2| / D2; Determine whether the first difference ratio X1 is less than a preset second difference threshold; If so, allow the execution of S203; if not, send a first misalignment prompt signal to the user In some embodiments, the creating step of the target model includes: Collect multiple photos of the subject wearing the mouth opener, the photos including: at least one reference mark and at least one tooth, and there is an overlapping part between any two of the multiple photos; Create the corresponding target model according to the multiple photos, and the target model is used to describe the positional relationship between the mouth opener and the teeth in the second space coordinate system.

[0090] In some embodiments, it further includes the step: Determine the reference coordinates of the robot moving to the final target point in the second space coordinate system through the target model.

[0091] In some embodiments, it further includes: Convert the reference coordinates of the target point to obtain the first measurement coordinates of the target point in the first space coordinate system; The robot continues to move from the first navigation point to the first measurement coordinates.

[0092] For example, in this embodiment, the first measurement coordinate may refer to the spatial position of the end of the robot when the robot needs to install brackets on the corresponding teeth. For example, the first measurement coordinate may be a coordinate preset by a user (such as a doctor) with the aid of a target model.

[0093] For example, in some embodiments, the robot may first move to a first navigation point through a reference point, and then move from the first navigation point to the first measurement coordinate, reducing the real-time navigation pressure of the robot through segmented navigation. For example, during the process of the robot moving from far to near, different moving speeds can be adopted to adapt to the navigation characteristics of different navigation stages.

[0094] Also, for example, in some embodiments, the movement of the robot from the first navigation point to the first measurement coordinate can also be completed with the intervention of a doctor.

[0095] For example, in some embodiments, the step of moving from the first navigation point to the first measurement coordinate includes: Determine a second navigation point, the distance between the second navigation point and the first measurement coordinate being less than a second threshold; When the orthodontic robot moves to the second navigation point at a second speed, obtain a third image of the oral cavity at a second shooting angle through a micro camera arranged at a position adjacent to the end of the robot; Obtain a fourth image of the target model at the second shooting angle; Calculate a third target interval D3 between a first target position and a second target position in the third image, and calculate a fourth target interval D4 between the corresponding first target position and the second target position in the fourth image; Calculate a second difference ratio X2 between the third target interval D3 and the fourth target interval D4; where X2 = |D3 - D4| / D3; or X2 = |D3 - D4| / D4; Determine whether the second difference ratio X2 is less than a preset third difference threshold; If not, send a second misalignment prompt signal to the user.

[0096] In some embodiments, the photo is a CT scan photo or a standard orthodontic intraoral photo.

[0097] Embodiment Four The present invention also provides a robot navigation system for batch installation of brackets, including: Reference marks, the reference marks comprising: a first reference mark disposed at at least one first target position on the mouth opener, and a second reference mark disposed at at least one other first target position on the mouth opener, the mouth opener being worn in the oral cavity of a subject to open and fix the oral cavity; A first positioning module, used for defining a first spatial coordinate system using an optical positioning camera, wherein the first spatial coordinate system is used for defining first coordinates of the first reference mark and the second reference mark; A second positioning module is used to provide a preset target model for simulating the oral cavity and the mouth opener, wherein the target model defines the relative position between at least one reference mark and the teeth through a second spatial coordinate system; at least two grasping mechanisms are provided at the end of the robot, and the grasping mechanisms are used to grasp and install the brackets; the at least two grasping mechanisms can simultaneously install the brackets on a group of teeth; a third positioning module, configured to align the first spatial coordinate system and the second spatial coordinate system by using a coordinate system alignment algorithm, and obtain a first reference coordinate of a first reference point in the first spatial coordinate system by corresponding transformation of one of the first coordinates, and obtain a second reference coordinate of a second reference point in the first spatial coordinate system by corresponding transformation of another of the first coordinates; the reference point is the tooth; A reference distance calculation module, used to calculate a first reference distance and a second reference distance of the first reference point and the second reference point in the first spatial coordinate system and the second spatial coordinate system respectively; The first judgment module is used to judge whether the difference between the first reference distance and the second reference distance is less than a set reference threshold value. If so, a first navigation point of at least one grasping mechanism is determined based on at least one reference point, and the distance between the first navigation point and the reference point is less than a set first threshold value.

[0098] It can be understood that the system in the present invention can implement the method steps described in any of the above embodiments, which will not be repeated here.

[0099] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0100] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-described example methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases, the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a computer terminal (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0101] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific implementation manners. The above specific implementation manners are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the purpose of the present invention and the scope protected by the claims. All of these fall within the protection scope of the present invention.

[0102] References: CN202410032572 - An intelligent navigation implanting method and system for an oral implant robot; CN202110698441 - A navigation and positioning method for an implant robot; CN202110867874 - An optical navigation dental implant robot system and its calibration method; CN202310283962 - A control method, system, and storage medium for a dental surgical robot.

Claims

1. A navigation method that can be used for a semi-automatic robot, characterized in that: Includes steps: S200, setting reference marks, the reference marks comprising: a first reference mark set at at least one first target position on the mouth opener, and a second reference mark set at at least another first target position on the mouth opener, the mouth opener being worn in the oral cavity of a subject to open and fix the oral cavity; wherein the total number of the first reference marks and the second reference marks is at least three; S201, defining a first spatial coordinate system using an optical positioning camera, where the first spatial coordinate system is used to define first coordinates of the first reference mark and the second reference mark; S202, providing a preset target model for simulating the oral cavity and the mouth opener, wherein the target model defines a relative position between at least one reference mark and the teeth through a second spatial coordinate system; at least two grasping mechanisms are provided at the end of the robot, and the grasping mechanisms are used to grasp and install brackets; the at least two grasping mechanisms can simultaneously install the brackets on a group of teeth; S203, aligning the first spatial coordinate system and the second spatial coordinate system by using a coordinate system registration algorithm, and obtaining a first reference coordinate of a first reference point in the first spatial coordinate system by corresponding transformation of one of the first coordinates, and obtaining a second reference coordinate of a second reference point in the first spatial coordinate system by corresponding transformation of another of the first coordinates; S204 calculates a first reference distance and a second reference distance of the first reference point and the second reference point in the first spatial coordinate system and the second spatial coordinate system respectively; S205 determines whether the difference between the first reference distance and the second reference distance is less than a set reference threshold, and if so, executes S206; S206 determines a first navigation point of at least one grasping mechanism according to at least one reference point, wherein a distance between the first navigation point and the reference point is greater than a set first threshold.

2. The method according to claim 1, characterized in that The optical positioning camera is arranged on the robot.

3. The method according to claim 1, characterized in that Before step S203, the method further includes: Acquire a first image of the oral cavity and the mouth opener at a first shooting angle at a first moment; wherein the first image displays a second target position; the second target position includes one or more of the following: lip bead, lip peak, lip vermilion, incisor, canine, premolar, molar; Acquire a second image of the target model at the first shooting angle; Calculating a first target interval D1 between the first target position and the second target position in the first image, and calculating a second target interval D2 between the corresponding first target position and the second target position in the second image; Calculate a first difference ratio X1 between the first target interval D1 and the second target interval D2; wherein X1=|D1-D2| / D1; or, X1=|D1-D2| / D2; Determine whether the first difference ratio X1 is less than a preset second difference threshold; If yes, execution of S203 is allowed; if no, a first misalignment prompt signal is sent to the user.

4. The method according to claim 3, characterized in that The method also includes the step of: the user setting a specific shooting angle.

5. The method according to claim 1, characterized in that The steps of creating the target model include: Collecting a plurality of photos of the subject wearing the mouth opener, wherein the photos include: at least one reference mark and at least one tooth, and any two of the plurality of photos have overlapping parts; The corresponding target model is created according to the multiple photos, and the target model is used to describe the positional relationship between the mouth opener and the teeth in the second spatial coordinate system.

6. The method according to claim 5, characterized in that The photos include one or more of the following: front view, side view, 45° side view, front smiling view, side smiling view, 45° side smiling view, right side view inside the mouth, front view inside the mouth, left side view inside the mouth, upper side view, lower side view, and overlying view.

7. The method according to claim 5, characterized in that Also includes the steps: The target model is used to determine the reference coordinates of the robot moving to the final target point in the second spatial coordinate system.

8. The method according to claim 7, characterized in that Also includes: Obtaining a first measurement coordinate of the target point in the first space coordinate system by converting the reference coordinate of the target point; The robot continues to move from the first navigation point to the first measurement coordinate.

9. The method according to claim 7, characterized in that: The first measurement coordinate refers to the spatial position of the robot end when the robot needs to install a bracket on the corresponding tooth.

10. A navigation method that can be used for a semi-automatic robot, characterized in that: include: Reference marks, the reference marks comprising: a first reference mark arranged at at least one first target position on the mouth opener, and a second reference mark arranged at at least one other first target position on the mouth opener, the mouth opener being worn in the oral cavity of a subject to open and fix the oral cavity; wherein the total number of the first reference marks and the second reference marks is at least three; A first positioning module, used for defining a first spatial coordinate system using an optical positioning camera, wherein the first spatial coordinate system is used for defining first coordinates of the first reference mark and the second reference mark; A second positioning module is used to provide a preset target model for simulating the oral cavity and the mouth opener, wherein the target model defines the relative position between at least one reference mark and the teeth through a second spatial coordinate system; at least two grasping mechanisms are provided at the end of the robot, and the grasping mechanisms are used to grasp and install the brackets; the at least two grasping mechanisms can simultaneously install the brackets on a group of teeth; a third positioning module, configured to align the first spatial coordinate system and the second spatial coordinate system by using a coordinate system alignment algorithm, and obtain a first reference coordinate of a first reference point in the first spatial coordinate system by correspondingly transforming one of the first coordinates, and obtain a second reference coordinate of a second reference point in the first spatial coordinate system by correspondingly transforming another of the first coordinates; A reference distance calculation module, used to calculate a first reference distance and a second reference distance of the first reference point and the second reference point in the first spatial coordinate system and the second spatial coordinate system respectively; The first judgment module is used to judge whether the difference between the first reference distance and the second reference distance is less than a set reference threshold value. If so, a first navigation point of at least one grasping mechanism is determined based on at least one reference point, and the distance between the first navigation point and the reference point is less than a set first threshold value.

Images