METHOD FOR CONTROLLING A ROBOTIC ARM FOR INTRAORAL IMAGING

Abstract

METHOD FOR CONTROLLING A ROBOTIC ARM FOR INTRAORAL IMAGING The invention relates to a method for controlling a robotic arm (102) comprising an intraoral camera (104), comprising a step of controlling the movement of the robotic arm according to a predetermined portion of its trajectory, and a step of capturing images of the oral cavity by the camera, characterized in that the method further comprises a preliminary step of defining a set of intraoral tissues to be reconstructed, a preliminary step of determining at least a portion of the trajectory of the robotic arm according to a starting position of the camera and the set of tissues to be reconstructed, a step of semantic segmentation of each pixel of each captured image to determine a set of reconstructed tissues, and after each addition of a tissue to the set of reconstructed tissues,a step of determining a new portion of the trajectory according to the set of reconstructed tissues and the set of tissues to be reconstructed. Figure for the abbreviation: figure 2,

Description

Title of the invention: METHOD FOR CONTROLLING A ROBOTIC ARM FOR INTRAORAL IMAGING Technical field of the invention

[0001] The invention relates to a method for controlling a robotic arm for intraoral imaging. In particular, the invention relates to a method for calculating a trajectory of the robotic arm carrying a camera in order to capture intraoral images, for example to perform a 3D reconstruction of elements of the oral cavity in which the robotic arm moves, in particular the reconstruction of all or part of the dental tissues of the oral cavity. Technological background

[0002] 3D reconstruction of an oral cavity makes it possible to generate a 3D model that allows, in particular, the identification of each of the teeth and tissues of the oral cavity. This reconstructed oral cavity is used as a basis for various dental treatments (prosthetic, aesthetic, etc.).

[0003] In the context of these dental treatments, impressions of the dental arch were previously taken using a physical alginate-based impression, but this technique is gradually being replaced by digital three-dimensional reconstructions obtained using intraoral cameras. These digital three-dimensional reconstructions of the dental arches allow the use of Computer-Aided Design (CAD) tools, which offer the advantages of expanding and simplifying the possibilities for treatment and / or prosthesis design.

[0004] An intraoral camera is a device composed of one or more optical sensors that acquire intraoral images and transform them into a three-dimensional reconstruction of the targeted intraoral tissues (partial or complete dental arch, palate, gingiva, isolated tooth, etc.). The images are transmitted in real time to a processing unit, which calculates the corresponding three-dimensional surface and displays the current 3D tissue reconstruction in real time on a screen to show the user what has been correctly acquired so far.

[0005] More and more intraoral cameras are regularly coming onto the market, but they all share the same drawback: a human operator must intervene to manipulate the camera in the patient's mouth, in order to continually adjust his gesture to the real-time three-dimensional reconstruction presented, to correct or complete it until complete acquisition of the desired anatomical area.

[0006] Solutions have been proposed to automate the movement of the camera in the patient's mouth, in particular by generating a movement trajectory in function of anatomical parameters of the patient's mouth.

[0007] These solutions have several disadvantages: firstly, they are restrictive for the operator who must position the robotic arm correctly in its initial position to ensure that the trajectory corresponds to the patient.

[0008] In addition, the calculated trajectory is linked to limited anatomical parameters and does not allow adaptation to any particular type of anatomy, for example a lost tooth or a dental anomaly such as the lack of one or more teeth, a supernumerary tooth, teeth or an oral cavity of dimensions too different from normal, etc.

[0009] These solutions are also used for a complete scan of the oral cavity or at least of the dental arch and do not allow selection of portions of the dental arch, or going back to obtain better images.

[0010] Finally, these predefined trajectories require complete immobilization of the patient's head because they do not foresee possible movements, even minimal, of the patient's oral cavity, even if haptic sensors are generally present to avoid any injury.

[0011] The inventors therefore sought a solution to overcome these drawbacks by providing an automatic control method. Objectives of the invention

[0012] The invention aims to provide a method for controlling a robotic arm comprising a camera configured for capturing intraoral images, overcoming the aforementioned drawbacks.

[0013] The invention aims in particular to provide, in at least one embodiment, a control method enabling the 3D reconstruction of predefined portions of the oral cavity.

[0014] The invention also aims to provide, in at least one embodiment of the invention, a control method enabling adaptation to different existing anatomies.

[0015] The invention also aims to provide, in at least one embodiment of the invention, a control method facilitating implementation by a practitioner.

[0016] The invention also aims to provide, in at least one embodiment of the invention, a control method in which the trajectory of the robotic arm can be recalculated in real time.

[0017] The invention also aims to provide, in at least one embodiment of the invention, a control system for a robotic arm comprising a camera configured for capturing intraoral images. Description of the invention

[0018] To this end, the invention relates to a method for controlling a robotic arm comprising a camera configured for capturing intraoral images, the method including a step of determining at least a portion of a trajectory of said robotic arm inside an oral cavity, a step of controlling the movement of the robotic arm in the oral cavity according to said determined portion of trajectory, and a step of capturing images of the oral cavity by the camera of the robotic arm,

[0019] characterized in that the process further comprises the following steps:

[0020] - a preliminary step of defining a set of intraoral tissues of which at least one image must be captured by the camera, referred to as the set of tissues to be reconstructed, - a preliminary step of determining at least a portion of the robotic arm's trajectory based on a starting position of the camera and the set of tissues to be reconstructed, - a semantic segmentation step for each pixel of each captured image in order to determine a set of reconstructed tissues from among the set of tissues to be reconstructed, - after each addition of a tissue in the set of reconstructed tissues, a step of determining a new portion of trajectory as a function of the set of reconstructed tissues and the set of tissues to be reconstructed.

[0021] A method according to the invention therefore allows a repeated recalculation of the trajectory during the control of the robot in order to adapt in real time to the oral cavity, to the anatomical particularities and to the possible movements of the patient, allowing a change of strategy as the reconstruction progresses.

[0022] The method also allows adaptation to all the tissues to be reconstructed, which constitute the target targeted by the robotic arm's control. The trajectory is thus fixed in relation to these targets, which can vary from one patient to another, rather than aiming for a systematically complete reconstruction of the oral cavity and / or dental arch, as is the case in anterior dentistry. The target corresponds to all the tissues to be reconstructed, defined in the preliminary definition step: this preliminary definition step can be carried out, for example, by a human operator (manual definition), possibly assisted by a computer device (semi-automatic definition), or entirely by a computer device (automatic definition) using data provided to it.A complementary objective is to minimize the duration of the reconstruction, in particular the time spent with the camera positioned in the patient's oral cavity, by implementing the most optimal trajectory possible.

[0023] A portion of the trajectory is understood to be a movement instruction allowing movement from one tissue to be reconstructed to another tissue to be reconstructed within the set of tissues to be reconstructed for image capture, and the trajectory is understood to be the sum of the portions allowing the image to be captured of all the tissues of the entire set of tissues to be reconstructed.

[0024] Taking into account the tissues already reconstructed makes it possible to offer freedom of reconstruction, for example by allowing the trajectory to start at any position and by allowing only disjointed pieces of the oral cavity to be reconstructed, for example by choosing a set of teeth that one wants to reconstruct.

[0025] Semantic segmentation is known to be achieved, for example, by a machine learning algorithm, particularly a deep learning algorithm, which makes it possible to associate each pixel of an image with a label, a category, or a tag, this label / category / tag corresponding to an object or element, generally real, present in the image. An example of semantic segmentation implemented by a fully convolutional neural network is described, for example, in the publication "LONG, Jonathan, SHELHAMER, Evan, and DARRELL, Trevor. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. p. 3431-3440."

[0026] The invention can also be used for the 3D reconstruction of a real 3D model, for example, a cast of an oral cavity, particularly a dental arch, as part of the digitization of existing casts. The camera configured for capturing intraoral images is commonly called an intraoral camera and can be of various types.

[0027] Advantageously and according to the invention, the trajectory or portion of trajectory is determined as a function of a predefined model trajectory corresponding to at least one classic trajectory used by a human operator.

[0028] According to this aspect of the invention, the trajectory is established in part by taking into account conventional trajectories as implemented by a practitioner such as a dentist. The trajectory can thus be adapted, in particular to allow for better image quality, by taking into account the conventional trajectories for which the practitioner knows how to obtain quality images through their professional experience.

[0029] In particular, according to at least one embodiment of the invention, the trajectories can be defined according to heuristic rules with respect to the robot's current situation. For example, when the robot flies over the occlusal surface of the left molars, a portion of the trajectory can be defined as a rotation of X radians about a given axis and a translation of Y mm about another axis, until it reaches the buccal surface of the left molars. Semantic segmentation makes it possible to verify that the buccal surface is indeed reached following the movement. During the movement, semantic segmentation can also make it possible to determine a trajectory anomaly and trigger a trajectory recalculation.

[0030] Advantageously, the method according to the invention includes a preliminary step of training a neural network of a robot control unit by reinforcement learning, said preliminary training step taking as input data a plurality of classic trajectories used by a human operator.

[0031] According to this aspect of the invention, reinforcement learning allows the robotic arm to follow portions of a trajectory or trajectories not defined by a human operator or not programmed in advance, but to evolve according to the output data of a neural network trained on a plurality of classic trajectories, thus being able to adapt to any type of intraoral cavities, in particular any type of dental arch. A reinforcement learning method that can be used in this context is described, for example, in the publication “CHAPLOT, Devendra Singh, GANDHI, Dhiraj Prakashchand, GUPTA, Abhinav, et al. Object goal navigation using goal-oriented semantic exploration. Advances in Neural Information Processing Systems, 2020, vol. 33, p. 4247-4258.”

[0032] Advantageously and according to the invention, the trajectory or portion of the trajectory is determined according to a predefined 3D model of the oral cavity.

[0033] According to this aspect of the invention, the use of a predefined 3D model can facilitate the determination of the trajectory. In particular, the predefined 3D model can be a simplified model, for example obtained using photographs as proposed by the applicant in patent application WO2021245274A1.

[0034] Advantageously and according to the invention, at least one portion of the trajectory comprises a displacement until a predetermined tissue is detected by the intraoral camera, said predetermined tissue being detected by semantic segmentation in at least one image of said intraoral camera.

[0035] According to this aspect of the invention, the control method allows for the implementation of conditional trajectories, in which the detection of a particular tissue triggers a new trajectory calculation or the stopping of the control method. For example, the control method can allow for the reconstruction of the patient's oral cavity palate by planning a trajectory from one tooth to the opposite tooth on the same dental arch, and recalculating a new trajectory once the opposite tooth is detected by semantic segmentation, indicating that the entire palate from tooth to tooth has been reconstructed.

[0036] Advantageously, a method according to the invention includes a step of determining a new trajectory following the detection of an unforeseen tissue by the intraoral camera, said unforeseen tissue being detected by semantic segmentation in at least one image of said intraoral camera.

[0037] According to this aspect of the invention, a recalculation of the trajectory can be performed when an unforeseen tissue, such as a hole or a supernumerary tooth, is detected, such that the portion of the originally planned trajectory is no longer suitable for reconstructing the tissues of the set of tissues to be reconstructed. The step may also include the deletion of one or more tissues in the set of tissues to be reconstructed, for example, by detecting a hole in the absence of a tooth.

[0038] Advantageously and according to the invention, the set of tissues to be reconstructed comprises at least one tissue included in the following list:

[0039] a tooth, a gum, a palate, a dental prosthesis, a dental preparation, an implant abutment.

[0040] According to this aspect of the invention, the diversity of tissues to be reconstructed allows the implementation of the control method for reconstructing different areas of the oral cavity, for different results, in particular for generating a 3D model of the oral cavity and / or the dental arch. Dental preparation refers to the tooth prepared to receive a dental crown. The implant abutment is also more commonly known as a scanbody. The invention is not limited to these tissues.

[0041] The invention also relates to an imaging system comprising a robotic arm including a camera configured for capturing intraoral images, characterized in that it includes a control unit, configured to receive the images captured by the intraoral camera, and to control the robotic arm according to a control method according to the invention.

[0042] The invention also relates to a control method and an imaging system characterized in combination by all or part of the characteristics mentioned above or below. List of figures

[0043] Other objects, features and advantages of the invention will become apparent from the following description, given by way of non-limiting example only, and which refers to the accompanying figures in which:

[0044] [Fig. 1] is a dental diagram representing the numbering of human teeth according to the notation system of the International Dental Federation,

[0045] [Fig.2] is a schematic view of an imaging system according to one embodiment of the invention,

[0046] [Fig.3] is a schematic view of a control method according to one embodiment of the invention,

[0047] [Fig.4] is a schematic view of a dental arch and a trajectory followed by the intraoral camera during the implementation of a control method according to a first embodiment of the invention,

[0048] [Fig.5] is a schematic view of a dental arch and of a trajectory followed by the intraoral camera during the implementation of a control method according to a second embodiment of the invention.

[0049] Detailed description of an embodiment of the invention

[0050] In the figures, the scales and proportions are not strictly respected for the purposes of illustration and clarity.

[0051] In addition, identical, similar or analogous elements are designated by the same references in all figures.

[0052] Figure 1 is a diagram representing an adult human dentition, in which each tooth is associated with its notation according to the Fédération Dentaire Internationale (FD1 World Dental Federation notation). In this notation, each tooth is identified by two notation numbers. The dentition is divided into four quadrants, and the quadrant in which the tooth is located corresponds to the first number of the notation: quadrant 1 upper left, quadrant 2 upper right, quadrant 3 lower right, quadrant 4 lower left ("right" and "left" being understood from the point of view of a dentist observing a patient's dentition). The second number of the notation indicates the corresponding tooth in the quadrant, from 1 the central incisor to 8 the wisdom tooth.

[0053] There is also a notation from the International Dental Federation for deciduous teeth, not detailed here.

[0054] The control method according to the invention makes it possible to control a robotic arm in order to obtain intraoral images of tissues to be reconstructed, for example of teeth to be reconstructed.

[0055] Fig. 2 schematically represents an imaging system 100 according to an embodiment of the invention, in particular configured to implement a control method according to an embodiment of the invention.

[0056] The imaging system 100 comprises a robotic arm 102, for example a six-axis robotic arm, comprising at one end a camera 104 configured for capturing intraoral images in the intraoral cavity 900 of a patient, in other words, an intraoral camera. The intraoral camera 104 may be a camera such as is currently used on the market for manual intraoral scanning, and allows the real-time acquisition of raw data on dental tissues, this data being (depending on the type of camera) 2D images, partial 3D reconstructions, or other types.

[0057] The imaging system 100 also includes a control unit 106, enabling on the one hand the piloting and control of the robotic arm 102, the reception of raw data from the intraoral camera 104, and the processing of this raw data.

[0058] The processing of raw data can, for example, be a real-time combination to produce an incremental real-time 3D model, which can be monochrome or in color. An optional step allows the application of digital processing to the latest incremental 3D model to produce a final high-precision 3D reconstruction.

[0059] According to some embodiments, the raw or processed data can be transmitted to a display system 108 such as a display screen, allowing visual control of the progress of image capture and control of the robotic arm 102.

[0060] The raw digital data or data resulting from processing by the control unit are stored in a memory storage unit 110.

[0061] Fig. 3 schematically represents a control method 200 according to an embodiment of the invention.

[0062] The process includes, in particular, the following steps:

[0063] - a preliminary step 202 of defining a set of intraoral tissues of which at least one image must be captured by the camera, referred to as the set of tissues to be reconstructed, - a preliminary step 204 of determining at least a portion of the robotic arm's trajectory based on a starting position of the camera and the set of tissues to be reconstructed, - a step 206 for controlling the movement of the robotic arm in the oral cavity according to said determined portion of trajectory, - a step 208 of capturing images of the oral cavity by the robotic arm's camera - a step 210 of semantic segmentation of each pixel of each captured image in order to determine a set of reconstructed tissues from the set of tissues to be reconstructed, - after each addition of a tissue in the set of reconstructed tissues, a step 212 of determining a new portion of trajectory as a function of the set of reconstructed tissues and the set of tissues to be reconstructed.

[0064] When all the tissues are reconstructed, a final step 214 of the process is implemented, which allows, for example, the removal of the oral camera from the patient's oral cavity.

[0065] Step 206 of controlling the robotic arm is carried out in parallel with image capture and segmentation, based on said at least a portion of the trajectory. completed by preliminary step 204 depending on the starting position, or depending on the new portion of trajectory determined in step 212.

[0066] The control method can determine a complete trajectory in the preliminary step 204 of determining at least one portion of the trajectory and / or in each step 212 of determining a new portion of the trajectory, thus optimizing the trajectory to have a minimum duration. However, any complete trajectory determined can be modified during the execution of the control method in a subsequent step 212 of determining a new portion of the trajectory.

[0067] The determination of a new portion of the trajectory is carried out using the available data which allows the current state to be characterized, in particular the current position of the camera, all the reconstructed tissues, all the tissues to be reconstructed, a predefined 3D model of the oral cavity, etc.

[0068] If the control unit implementing the control method 200 uses a neural network, the control method 200 may include a preliminary step 216 of training the neural network using data from trajectories implemented by experienced human operators on a large number of different dental arches. The neural network thus trained enables the implementation of step 212 of determining the portion or portions of the trajectory according to the current status of the process.

[0069] According to another embodiment of the invention, the control step 206 is carried out by the use of predetermined heuristic rules adjusted according to the current state.

[0070] Figures 4 and 5 schematically represent examples of trajectories that can be followed by the intraoral camera installed on the robotic arm controlled by the control unit, following the control method according to the invention.

[0071] The representation of the dental arch is analogous to that shown in [Fig.1], and the teeth are identified by their reference according to the notation of the International Dental Federation shown on this [Fig.1] and are not shown on figures 4 and 5 for reasons of clarity.

[0072] Figure 4 represents a first trajectory comprising several phases representing portions of the trajectory. The objective of this trajectory is, for example, the reconstruction of the tissues forming all the molars of the dental arch, either of a patient or of a physical 3D model. The set of molar tissues thus constitutes the set of tissues to be reconstructed, and this set is defined automatically by a computer system, manually by a human operator, or semi-automatically by a human operator assisted by a computer system.

[0073] The robotic arm or a human operator guides the camera to a position 400 of The starting point can be any position. Here, the starting position is at the level of the palatal surface of the right second molar 17. Image capture begins, and the camera follows a first portion 401 of its trajectory along the palatal surfaces to molar 18. The camera then follows a second portion 402 of its trajectory until it reaches the occlusal surface of molar 18, and then a third portion 403 of its trajectory to scan the occlusal surfaces of molars 18, 17, and 16. Since the palatal surface of molar 16 is not part of the reconstructed tissue but is part of the tissue to be reconstructed, a fourth portion 404 of its trajectory is followed by the camera until it reaches this surface.

[0074] The camera then follows the following trajectories:

[0075] - a fifth portion 405 of trajectory until reaching the vestibular face of molar 16, - a sixth portion 406 of the trajectory to capture images of the vestibular surfaces of the molars until reaching molar 18, - a seventh portion 407 of trajectory until reaching the mandibular teeth, - an eighth portion 408 of the trajectory to capture images of the vestibular surfaces of molars 48, 47 and 46, - a ninth portion 409 of the trajectory until it reaches the occlusal face of molar 46, - a tenth portion 410 of the trajectory to capture images of the occlusal surfaces of molars 46, 47 and 48, - an eleventh portion 411 of trajectory to reach the lingual face of molar 48, - a twelfth portion 412 of the trajectory to capture images of the lingual surfaces of molars 48, 47 and 46, - a thirteenth portion 413 of trajectory until reaching the lingual face of molar 36, - a fourteenth portion 414 of the trajectory to capture images of the lingual surfaces of molars 36, 37 and 38, - a fifteenth portion 415 of trajectory until reaching the occlusal face of molar 38, - a sixteenth portion 416 of trajectory to capture images of the occlusal surfaces of molars 38, 37 and 36, - a seventeenth portion 417 of trajectory until reaching the vestibular face of molar 36, - an eighteenth portion 418 of the trajectory to capture images of the vestibular surfaces of the molars until reaching molar 38, - a nineteenth portion 419 of trajectory until reaching the maxillary teeth.

[0076] Upon arrival at the location 28' of molar 28, the control method detects the absence of this molar. The tissues of molar 28 can therefore be removed from the set of tissues to be reconstructed, and the trajectory or the next portion of the trajectory can be recalculated. In particular, a twentieth portion 420 of the trajectory is followed to capture the images of the vestibular faces of molars 27 and 28, a twenty-first portion 421 of the trajectory allows reaching the occlusal face of molar 26, a twenty-second portion 422 of the trajectory allows capturing the images of the occlusal faces of molars 26 and 27. Molar 28 being absent, the twenty-third portion 423 of the trajectory allows reaching the palatal face of molar 27 and the twenty-fourth portion 424 allows capturing the images of the palatal faces of molars 27 and 26.

[0077] The process then reaches a final stage in which the intraoral camera is removed from the oral cavity.

[0078] Fig. 5 represents a second trajectory comprising several phases representing portions of trajectories, the objective of this trajectory being, for example, the reconstruction of the palate of a patient or of a physical 3D model.

[0079] The robotic arm or a human operator guides the camera to a starting position 500, which can be any position. Here, the starting position is at the level of the palatal surface of the first right molar 16. Image capture begins, and the camera follows a first portion 501 of its trajectory along the palatal surfaces as far as molar 18. The camera then follows a second portion 502 of its trajectory to capture images of the palate until it reaches the palatal surface of molar 28, thus traversing the palate across its width. Detection of this palatal surface by semantic segmentation confirms that the entire width of the palate has been captured.

[0080] The camera then follows a third trajectory segment 503 to position itself at the level of the palatal surfaces of molars 26 and 27, and a fourth trajectory segment 504 captures new images of the palate until it reaches the right maxillary molars 17 and 18. The camera then moves along a fifth trajectory segment 505 to reach the palatal surface of premolar 15 and traverses the width of the palate again in a sixth trajectory segment 506 until it reaches the palatal surface of premolar 24, then follows a seventh trajectory segment 507 to complete the capture of the palate at the level of the maxillary canines and incisors. At each traverse of the palate's width, tooth detection ensures that the entire width of the palate has been traversed.

[0081] The process then reaches a final stage in which the intraoral camera is removed from the oral cavity.

[0082] This trajectory is purely for illustrative purposes and the number of cross-passages required to capture images of the entire palate may be higher or lower, for example depending on the size of the palate or the field of view of the camera.

[0083] Similarly, other objectives can be implemented, in particular the set of tissues to be reconstructed may be the set of tissues of the dental arch so as to achieve a complete reconstruction of the dental arch.

Claims

Demands

1. A method for controlling a robotic arm (102) comprising a camera (104) configured for capturing intraoral images, the method comprising a step (204, 212) of determining at least a portion of a trajectory of said robotic arm inside an oral cavity, a step (206) of controlling the movement of the robotic arm in the oral cavity as a function of said determined portion of the trajectory, and a step (208) of capturing images of the oral cavity by the camera of the robotic arm, characterized in that the method further comprises the following steps: - a preliminary step (202) of defining a set of intraoral tissues of which at least one image is to be captured by the camera, referred to as the set of tissues to be reconstructed, - a preliminary step (204) of determining at least a portion of the trajectory of the robotic arm as a function of a starting position of the camera and the set of tissues to be reconstructed,- a step (210) of semantic segmentation of each pixel of each captured image so as to determine a set of reconstructed tissues from among the set of tissues to be reconstructed, - after each addition of a tissue to the set of reconstructed tissues, a step (212) of determining a new portion of trajectory as a function of the set of reconstructed tissues and the set of tissues to be reconstructed.

2. A control method according to claim 1, characterized in that the trajectory or portion of trajectory is determined as a function of a predefined model trajectory corresponding to at least one conventional trajectory used by a human operator.

3. Control method according to claim 1, characterized in that it comprises a preliminary step (216) of training a neural network of a robot control unit by reinforcement learning, said preliminary training step taking as input data a plurality of classic trajectories used by a human operator.

4. A control method according to any one of claims 1 to 3, characterized in that the trajectory or portion of the trajectory is determined based on a predefined 3D model of the oral cavity.

5. A control method according to any one of claims 1 to 4, characterized in that at least a portion of the trajectory comprises a movement until a predetermined tissue is detected by the intraoral camera (104), said predetermined tissue being detected by semantic segmentation in at least one image of said intraoral camera (104).

6. A control method according to any one of claims 1 to 5, characterized in that it comprises a step of determining a new trajectory following the detection of an unforeseen tissue by the intraoral camera (104), said unforeseen tissue being detected by semantic segmentation in at least one image of said intraoral camera.

7. A control method according to any one of claims 1 to 6, characterized in that the set of tissues to be reconstructed comprises at least one tissue included in the following list: • a tooth, • a gum, • a palate, • a dental prosthesis, • a dental preparation, • an implant abutment.

8. Imaging system comprising a robotic arm (102) including a camera (104) configured for capturing intraoral images, characterized in that it comprises a control unit (106), configured to receive the images captured by the intraoral camera (104), and to control the robotic arm (102) according to a control method (200) according to any one of claims 1 to 7.

Images