Dental composite robot

By designing a dental composite robot and using AGV chassis and multi-sensor fusion technology, the inaccurate feeding problem caused by the complex classification of materials in dental treatment is solved, and the accurate identification and efficient transportation of materials are achieved, and the operation convenience is improved.

CN120458758APending Publication Date: 2025-08-12CHANGSHA INTELLIGENT ROBOT RES INST CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202510762308.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-09
Publication Date
2025-08-12

AI Technical Summary

Technical Problem

In dental treatment, there are many types of materials, and manual operation is prone to classification errors, resulting in inaccurate material supply.

Method used

A dental composite robot was designed, using AGV chassis, collaborative robot arm, servo claw and 3D camera. An environmental map was established through navigation cameras, and multi-sensor fusion technology and deep reinforcement learning were used to optimize path planning to achieve accurate identification and transportation of materials.

Benefits of technology

It realizes accurate identification and efficient transportation of materials, reduces manual operation errors, and improves the accuracy and operation convenience of material feeding.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120458758A_ABST
    Figure CN120458758A_ABST
Patent Text Reader

Abstract

The invention relates to the field of auxiliary instruments, in particular to a dental composite robot which comprises an AGV chassis, a connecting shell is mounted on the top surface of the AGV chassis, a cooperative mechanical arm is mounted on one side of the top surface of the connecting shell, and a material box cache region and a porcelain dish cache region are arranged on the connecting shell; a servo electric claw and a 3D camera are installed at the movable end of the cooperative mechanical arm, and the cooperative mechanical arm, the servo electric claw and the 3D camera are electrically connected with a control system. By controlling the AGV chassis to move to the corresponding position, feeding and transferring of materials can be achieved, and great convenience is brought to actual operation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of auxiliary instruments, and in particular to a dental composite robot. Background Art

[0002] Dentistry generally refers to dentistry. It is a medical discipline generally incorporated into the Department of Stomatology. Dentistry primarily treats diseases related to teeth and periodontium. Different materials are required for different dental lesions. However, due to the wide variety of materials, the production process of teeth requires the classification and feeding of materials to meet manufacturing requirements. This inevitably leads to errors during manual operation. Summary of the Invention

[0003] The purpose of the present invention is to provide a dental composite robot to solve the above problems and to solve the above technical problems.

[0004] To achieve the above object, the present invention provides the following solutions:

[0005] A dental composite robot comprises an AGV chassis, a connecting shell is installed on the top surface of the AGV chassis, a collaborative robotic arm is installed on one side of the top surface of the connecting shell, a material box buffer area and a porcelain plate buffer area are provided on the connecting shell, a servo electric claw and a 3D camera are installed on the movable end of the collaborative robotic arm, and the collaborative robotic arm, servo electric claw and 3D camera are electrically connected to a control system.

[0006] Preferably, the AGV chassis includes a base, auxiliary universal wheels are installed at the four corners of the bottom of the base, two driving wheels are installed in the middle of the base, and a navigation camera is installed on the bottom of the base, and the navigation camera is electrically connected to the control system.

[0007] Preferably, the material box buffer area includes a stepped storage groove opened on the top surface of the connecting shell, and the material box storage plates are placed in sequence from top to bottom in the stepped storage groove.

[0008] Preferably, the porcelain plate buffer area includes a porcelain plate storage plate installed on the top surface of the connecting shell, and the porcelain plate storage plate is provided with five storage positions and one photo taking position.

[0009] Preferably, the storage position includes a storage slot opened on the top surface of the porcelain plate storage board, and the porcelain plate rack is placed in the storage slot. The photographing position includes a photographing placement slot opened on the top surface of the porcelain plate storage board, and a background board is provided between the storage slot and the photographing placement slot.

[0010] A control method for the dental composite robot comprises the following steps:

[0011] Scan the surrounding environment with the navigation camera to obtain a scanning result;

[0012] establishing an operation map based on the scan results;

[0013] Setting a plurality of target points according to the operation map;

[0014] The composite robot plans a path according to the two adjacent target points and moves.

[0015] Preferably, laser radars are installed on the front and rear sides of the AGV chassis respectively.

[0016] The present invention has the following technical effects:

[0017] The present invention drives the servo electric claw to operate through the collaborative robot arm, and at the same time drives the D camera to keep it stationary. When it is necessary to grab a porcelain plate, the D camera takes a photo in the corresponding photo area to identify the position of the porcelain plate, and then controls the collaborative robot arm through the control system to drive the servo electric claw to move to the corresponding position to grab the porcelain plate. The grabbing of the material box stored in the material box buffer area is also done in the same way. In this way, by controlling the AGV chassis to move to the corresponding position, the loading and transportation of materials can be realized, which brings great convenience in actual operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 It is a schematic diagram of the structure of the present invention;

[0020] Figure 2 This is a structural diagram of a porcelain plate storage plate according to the present invention;

[0021] Figure 3 This is a schematic diagram of the bottom structure of the AGV chassis of the present invention.

[0022] Among them, 1. AGV chassis; 101. Drive wheel; 102. Auxiliary universal wheel; 2. Material box buffer area; 3. Collaborative robotic arm; 4. Servo electric claw; 5. 3D camera; 6. Porcelain plate buffer area; 7. Connecting shell; 8. Porcelain plate rack; 801. Background plate; 9. Porcelain plate storage plate; 901. Storage slot; 10. Porcelain plate; 11. Stepped storage slot; 12. Material box storage plate. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0024] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] A dental composite robot includes an AGV chassis 1, a connecting shell 7 is installed on the top surface of the AGV chassis 1, a collaborative robot arm 3 is installed on one side of the top surface of the connecting shell 7, a material box buffer area 2 and a porcelain plate buffer area 6 are provided on the connecting shell 7, a servo electric claw 4 and a 3D camera 5 are installed on the movable end of the collaborative robot arm 3, and the collaborative robot arm, servo electric claw 4 and 3D camera 5 are electrically connected to a control system.

[0026] The present invention drives the servo electric claw 4 to operate through the collaborative robot arm, and at the same time drives the 3D camera 5 to move synchronously. When it is necessary to grab the porcelain plate, the 3D camera 5 takes a photo in the corresponding photo area to identify the position of the porcelain plate, and then the control system controls the collaborative robot arm 3 to drive the servo electric claw 4 to move to the corresponding position to grab the porcelain plate. The material box stored in the material box buffer area 2 is also grabbed in the same way. In this way, by controlling the AGV chassis 1 to move to the corresponding position, the material loading and material transportation can be realized, which brings great convenience in actual operation.

[0027] To further optimize the solution, the AGV chassis 1 includes a base, auxiliary universal wheels 102 are installed at the four corners of the bottom of the base, two driving wheels 101 are installed in the middle of the base, and a navigation camera is installed on the bottom of the base, which is electrically connected to the control system.

[0028] The navigation camera is used to capture and detect the surrounding environment and surrounding obstacles, and transmit relevant information to the control system to establish a map model. When turning, the speed difference between the two driving wheels 101 is used to achieve steering. The function of the auxiliary universal wheel 102 is to provide support for the base 1 to ensure its walking stability.

[0029] Further optimized, the cartridge buffer area 2 includes a stepped storage slot 11 opened on the top surface of the connecting shell 7, and the cartridge storage plates 12 are placed in the stepped storage slot 11 from top to bottom. This arrangement can store more cartridges to increase the loading capacity of the entire device.

[0030] According to a further optimization scheme, the porcelain plate buffer area 6 includes a porcelain plate storage plate 9 installed on the top surface of the connecting shell 7, and five storage positions and one photo taking position are provided on the porcelain plate storage plate 9.

[0031] In a further optimized solution, the storage position includes a storage slot 901 provided on the top surface of the porcelain plate storage plate 9, the porcelain plate rack 8 is placed in the storage slot 901, and the porcelain plate 10 is installed in the porcelain plate rack 8. The photographing position includes a photographing placement slot 902 provided on the top surface of the porcelain plate storage plate 9, and a background plate 801 is provided between the storage slot 901 and the photographing placement slot 902. The background plate 801 provided at the photographing position can isolate the magnetic disk 8 being photographed to avoid interference with the photographing.

[0032] A control method for a dental composite robot comprises the following steps:

[0033] Scan the surrounding environment through the navigation camera to obtain the scanning results;

[0034] Create an operational map based on the scan results;

[0035] Set multiple target points according to the running map;

[0036] The composite robot plans a path based on two adjacent target points and moves.

[0037] To further optimize the solution, laser radars are installed on the front and rear sides of the AGV chassis 1.

[0038] Specifically, the navigation camera and the laser radar are used to scan the surrounding environment to obtain multimodal environmental data;

[0039] Input environmental data into the SLAM (Simultaneous Localization and Mapping) algorithm model to build and update a 3D environmental map in real time;

[0040] Optimize path planning through reinforcement learning algorithms and calculate the optimal movement path;

[0041] Obtain high-definition images of the porcelain plate and the material box through the 3D camera;

[0042] Feed the image into a pre-trained deep learning model to identify the location, type, and status of the material;

[0043] Based on the material identification results and task priorities, the optimal grabbing sequence is generated through the decision tree algorithm;

[0044] Monitor the robot arm's motion trajectory in real time and dynamically adjust the gripping force and angle through PID control algorithm;

[0045] Record operation data and upload it to the cloud for continuous optimization of algorithm models.

[0046] The dental composite robot uses multi-sensor fusion technology to collect environmental data in real time through navigation cameras, lidar, and IMU (inertial measurement unit);

[0047] Data collection and preprocessing

[0048] Navigation camera: A 2-megapixel global shutter camera is used to capture RGB images of the environment at a rate of 30fps for feature point extraction and visual odometry calculation.

[0049] LiDAR: Use 2D / 3D LiDAR (such as SICK or Velodyne) with a scanning frequency of 10Hz and a measurement accuracy of ±5mm for high-precision obstacle detection and contour modeling.

[0050] IMU: Provides the robot's acceleration and angular velocity data to compensate for the drift error of vision and laser SLAM.

[0051] SLAM algorithm implementation

[0052] Using a graph-optimization-based SLAM framework (such as Cartographer or LOAM) combined with visual-laser inertial odometry (V-LIO) to achieve high-precision positioning and mapping:

[0053] Front-end processing: extract visual feature points (ORB, SIFT) and laser point cloud features (edges, plane points), perform inter-frame matching, and calculate pose changes.

[0054] Backend optimization: Use GTSAM or Ceres Solver to optimize the pose graph, combine IMU data to eliminate accumulated errors, and build a 3D grid map (OctoMap).

[0055] Dynamic environment updating: Identify dynamic objects (such as moving people) through semantic segmentation networks (such as Mask R-CNN) and update the map in real time to avoid collisions.

[0056] Traditional path planning algorithms are less efficient in complex environments. This system uses deep reinforcement learning (DRL) to optimize mobility strategies:

[0057] State space definition: robot's current position, target point coordinates;

[0058] LiDAR acquires point cloud data of the surrounding environment;

[0059] Configure weights based on the urgency of materials to set task priorities;

[0060] Action space definition:

[0061] Training methods:

[0062] The PPO (Proximal Policy Optimization) algorithm is used to train 1 million iterations in a simulation environment (such as Gazebo) to optimize the movement strategy.

[0063] Reward function design:

[0064] Arrival at target point: +100

[0065] Collision with obstacles: -50

[0066] Path length optimization: +5 for every 1m reduction in distance

[0067] Online adaptive optimization:

[0068] The robot continuously collects data during actual operation and updates the strategy network through federated learning to adapt to different factory layouts.

[0069] For material identification:

[0070] A 3D camera (such as Intel RealSense D455) captures high-definition RGB-D images of the porcelain plates and boxes, which are then fed into a multimodal visual recognition system. For porcelain plate recognition, the YOLOv7 model is used, with training data containing 5,000 labeled porcelain plate images, achieving a recognition accuracy of >99%.

[0071] 3D pose estimation: Use PVNet (Pixel-wise Voting Network) to calculate the 6D pose (X / Y / Z + rotation) of the porcelain plate in the robot coordinate system.

[0072] Defect detection: Detect denture processing defects (such as cracks and bubbles) through ResNet-50+ attention mechanism.

[0073] Material box classification, based on EfficientNetV2, identifies 16 common dental materials (such as resins and metal alloys).

[0074] Quantity statistics: Instance segmentation (Mask R-CNN) is used to calculate the number of remaining materials in the box.

[0075] The present invention uses machine learning to improve environmental perception accuracy: positioning error <±2cm, adapting to dynamic environments.

[0076] Intelligent path planning: saves 35% moving time compared to traditional algorithms.

[0077] Accurate material recognition: Porcelain plate recognition rate >99.5%, supporting small sample incremental learning.

[0078] Continuous evolution capability: Cloud-based big data training, with models iterated monthly and accuracy continuously improving.

[0079] This invention completely covers the entire process from environmental perception, decision-making and planning to execution optimization, ensuring that the dental composite robot is highly intelligent and reliable in actual production.

[0080] In the description of the present invention, it should be understood that the terms "longitudinal", "transverse", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention, 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, and therefore cannot be understood as a limitation on the present invention.

[0081] The embodiments described above are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by persons skilled in the art should fall within the scope of protection defined by the claims of the present invention.

Claims

1. A dental composite robot, characterized in that: The invention comprises an AGV chassis (1), wherein a connecting shell (7) is installed on the top surface of the AGV chassis (1), a collaborative robot arm (3) is installed on one side of the top surface of the connecting shell (7), a material box buffer area (2) and a porcelain plate buffer area (6) are provided on the connecting shell (7), a servo electric claw (4) and a 3D camera (5) are installed on the movable end of the collaborative robot arm (3), and the collaborative robot arm, the servo electric claw (4) and the 3D camera (5) are electrically connected to a control system.

2. A dental composite robot according to claim 1, characterized in that: The AGV chassis (1) comprises a base, auxiliary universal wheels (102) are installed at the four corners of the bottom surface of the base, two driving wheels (101) are installed in the middle of the base, and a navigation camera is installed on the bottom surface of the base, and the navigation camera is electrically connected to the control system.

3. The dental composite robot according to claim 1, characterized in that: The material box buffer area (2) comprises a stepped storage groove (11) provided on the top surface of the connecting shell (7), wherein material box storage plates (12) are sequentially placed in the stepped storage groove (11) from top to bottom.

4. The dental composite robot according to claim 1, characterized in that: The porcelain disc buffer area (6) comprises a porcelain disc storage plate (9) mounted on the top surface of the connection shell (7), and the porcelain disc storage plate (9) is provided with five storage positions and one photographing position.

5. The dental composite robot according to claim 4, characterized in that: The storage position includes a storage slot (901) provided on the top surface of the porcelain plate storage plate (9), and the porcelain plate rack (8) is placed in the storage slot (901). The photographing position includes a photographing placement slot (902) provided on the top surface of the porcelain plate storage plate (9), and a background plate (801) is provided between the storage slot (901) and the photographing placement slot (902).

6. A control method for a dental composite robot according to any one of claims 2 to 5, characterized in that: The steps include: Scan the surrounding environment with the navigation camera to obtain a scanning result; establishing an operation map based on the scan results; Setting a plurality of target points according to the operation map; The composite robot plans a path according to the two adjacent target points and moves.

7. The control method of the dental composite robot according to claim 6, characterized in that: Laser radars are installed on the front and rear sides of the AGV chassis (1).