Intelligent robot system and method for grabbing small industrial parts

Abstract

The invention provides an intelligent robot system and method for grabbing small industrial parts. The intelligent robot system for grabbing the small industrial parts comprises an operation module, a mobile platform module, a sensing module and a control module. The operation module and the control module are both installed on the mobile platform module, the sensing module is installed on the operation module, the operation module is used for providing an object grabbing function, and the mobile platform module is used for executing a mobile function of the intelligent robot. And the sensing module is used for the positioning and mapping of the intelligent robot and the positioning and visual grabbing algorithm of a target area. The intelligent robot system for grabbing the small industrial parts, provided by the invention, has high movement flexibility and fine operation capability, can adapt to complex and changeable industrial scenes, can complete complex movement operation work, and can be effectively applied to a small industrial part grabbing task.

Description

Technical Field

[0001] The present invention relates to the technical field of robots, and in particular to an intelligent robot system and method for grasping small industrial parts. Background Art

[0002] Currently, most robot grasping systems often adopt a fixed design. Although this design performs stably in a specific environment, it lacks the flexibility required to handle complex environments. The operating range of a fixed robot is limited by its mechanical structure and installation position, resulting in the inability to grasp objects outside the preset working space.

[0003] In addition, although existing vision-guided grasping methods can improve the grasping success rate in a cluttered scene to a certain extent, most of them are aimed at objects with regular shapes and obvious textures, and are mainly applied to scenes with relatively simple object arrangements. For industrial parts with complex shapes, weak textures, and small sizes, these methods often perform poorly, especially in complex scenes where these parts are densely stacked and mutually occluded. On the one hand, objects such as parts often have irregular geometric appearances, mostly small sizes, complex shapes, and similar colors, lacking obvious texture features. On the other hand, in the actual scene, objects are often randomly distributed in the material box and are prone to being stacked together, resulting in mutual occlusion between them, which exacerbates the complexity of the scene. The above problems are extremely likely to confuse the visual perception of the robot, resulting in the current grasping algorithms being unable to be directly deployed in industrial scenarios.

[0004] Therefore, it is necessary to provide an intelligent robot system and method for grasping small industrial parts to solve the above technical problems. Summary of the Invention

[0005] The present invention provides an intelligent robot system and method for grasping small industrial parts, which solves the problem of lacking the flexibility required to handle complex environments.

[0006] To solve the above technical problems, the intelligent robot system for grasping small industrial parts provided by the present invention includes: an operation module, a mobile platform module, a perception module, and a control module;

[0007] The operation module and the control module are both installed on the mobile platform module, the perception module is installed on the operation module, the operation module is used to provide the function of grasping objects, the mobile platform module is used to execute the moving function of the intelligent robot, the perception module is used for the positioning and mapping of the intelligent robot and the positioning of the target area and the visual grasping algorithm, and the control module is used to process and manage the related tasks of the operation of the intelligent robot.

[0008] Preferably, the operating module includes a mechanical arm and an electric gripper, and the mobile platform module includes a quadruped bionic robot with twelve leg and foot joints.

[0009] Preferably, the perception module includes a laser radar, an inertial measurement unit and a depth camera; wherein the laser radar and the inertial measurement unit are used for positioning and mapping of the intelligent robot, and the depth camera is used for target area positioning and visual capture algorithms.

[0010] Preferably, the control module is used to coordinate the intelligent robot to perform various tasks, and is responsible for complex tasks such as visual processing, navigation decision-making, and high-level motion control. It also schedules the motion control and signal acquisition of the underlying hardware through control instructions, and acts as a bridge for coordination and information transmission between various modules.

[0011] Preferably, based on the functional architecture, the intelligent robot system for grasping small industrial parts is divided into environmental perception, data processing, and planning execution.

[0012] Preferably, the operating module is rotatably connected to a rotating block, the rotating block is rotatably connected to a rotating sleeve, the rotating sleeve is equipped with a mounting block, the mounting block is equipped with a toggle piece, the toggle piece is used to toggle the workpiece in the material frame to change the clamping posture of the workpiece, the operating module is equipped with a driving piece for driving the rotating sleeve to rotate, the operating module is internally slidably connected to a sliding block, the sliding block is fixedly connected to a connecting rod, one end of the connecting rod passes through the middle of the rotating sleeve and is equipped with a grabbing assembly, the grabbing assembly is used to grab the workpiece, the operating module is internally equipped with a pushing piece, the pushing piece is fixedly connected to the sliding block, and is used to drive the sliding block to move linearly to achieve feeding of the grabbing assembly.

[0013] Preferably, the operating module is rotatably connected to a mounting sleeve, the sensing module is mounted on the mounting sleeve, a connecting block is mounted on the rotating block, and one end of the connecting block is fixed on the mounting sleeve to achieve rotation of the mounting sleeve when the rotating block rotates.

[0014] Preferably, the outer surface of the connecting rod is rotatably connected to an auxiliary block, the auxiliary block is fixedly connected to a first docking piece, the rotating sleeve is fixedly connected to a second docking piece, the second docking piece is used to cooperate with the first docking piece to achieve docking between the rotating sleeve and the auxiliary block, the auxiliary block is fixedly connected to a guide rod, one end of the guide rod is installed with a third docking piece, the rotating block is installed with a fourth docking piece, the fourth docking piece is used to cooperate with the third docking piece to achieve docking between the guide rod and the rotating block.

[0015] A control method for an intelligent robot for grasping small industrial parts, including a robot push action posture estimation method and a multi-object grasping method combined with push operation auxiliary grasping;

[0016] Among them, the method for estimating the pushing action pose of the robot includes the following steps:

[0017] S1. Obtain image data and screen target objects;

[0018] S2. The grasping pose detection network predicts grasping parameters;

[0019] S3. Judge the primitive actions to be executed;

[0020] S4. Estimate the pushing action pose;

[0021] S5. Execute primitive actions.

[0022] The multi-object grasping method combining pushing operations to assist grasping includes the following steps:

[0023] S1. Obtain image data according to the perception module and screen target objects to obtain a color image block containing a single object and a corresponding edge image block;

[0024] S2. Send it into the grasping pose detection network to predict the planar grasping configuration composed of the grasping point and the grasping plane rotation angle parameter, and convert it into the grasping pose of the end gripper of the robotic arm in combination with the depth image;

[0025] S3. Perform collision detection on the grasping, and judge the primitive actions to be executed according to the result; if there is no grasping collision, control the robot to move and execute the grasping action, otherwise use the grasping detection network to predict again; if no feasible grasping can be found after three consecutive predictions, use the point cloud data converted from the depth image as the input, estimate a reasonable pushing position of the robotic arm, execute the pushing action to adjust the position relationship of the objects in the scene, separate the dense object clusters, and create a favorable space for subsequent grasping;

[0026] S4. Execute in a loop according to the above process until there are no objects in the bin.

[0027] Compared with the related technology, the intelligent robot system and method for small industrial part grasping provided by the present invention have the following beneficial effects:

[0028] (1) The intelligent grasping robot system proposed by the present invention, which is composed of a quadruped robot, a robotic arm, an electric gripper, various sensors, a control module, etc., has high motion flexibility and fine operation ability, can adapt to complex and changeable industrial scenarios, can complete complex mobile operation tasks, and can be effectively applied to small industrial part grasping tasks;

[0029] (2) The method for estimating the pose of the robot's pushing action proposed by the present invention can effectively separate densely packed objects, improve or create a feasible grasping space, reduce the probability of collision between the end effector and non-target objects or the material frame when grasping objects subsequently, and provide more favorable conditions for successful grasping;

[0030] (3) The multi-object grasping method combining pushing operation to assist grasping proposed by the present invention can, to a great extent, avoid the problem of grasping failure caused by collision during the grasping process in cases such as multi-object stacking and occlusion due to only using the grasping operation in the previous methods, and improve the grasping success rate in unstructured scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a schematic structural diagram of the first embodiment of the intelligent robot system for grasping small industrial parts provided by the present invention;

[0032] Figure 2 It is the overall framework diagram of the intelligent grasping robot system;

[0033] Figure 3 It is the flow block diagram of the present invention;

[0034] Figure 4 It is a schematic diagram of the key grasping points (left) and a schematic diagram of the grasping center point (right);

[0035] Figure 5 It is the architecture diagram of the grasping detection network;

[0036] Figure 6 It is a simplified schematic diagram of the pushing strategy 1 from the perspective of the camera perpendicular to the plane of the material frame;

[0037] Figure 7 It is a simplified schematic diagram of the pushing strategy 2 from the perspective of the camera perpendicular to the plane of the material frame;

[0038] Figure 8 It is a simplified schematic diagram of the pushing strategy 3 from the perspective of the camera perpendicular to the plane of the material frame;

[0039] Figure 9 It is a schematic structural diagram of the second embodiment of the intelligent robot system for grasping small industrial parts provided by the present invention;

[0040] Figure 10 It is for Figure 9 The partial enlarged view of A shown;

[0041] Figure 11 It is for Figure 9 The sectional schematic diagram of the operation module shown.

[0042] Markings in the figure: 1. operation module, 2. mobile platform module, 3. perception module, 4. control module, 5. rotating block, 6. rotating sleeve, 7. mounting block, 8. toggle member, 9. driving member, 10. sliding block, 11. connecting rod, 12. grabbing assembly, 13. pushing member, 14. mounting sleeve, 15. connecting block, 16. auxiliary block, 17. first docking member, 18. second docking member, 19. guide rod, 20. third docking member, 21. fourth docking member. DETAILED DESCRIPTION

[0043] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.

[0044] First embodiment

[0045] Please refer to Figures 1-8 ,in, Figure 1 A schematic structural diagram of a first embodiment of an intelligent robot system for grasping small industrial parts provided by the present invention; Figure 2 This is the overall framework diagram of the intelligent grasping robot system; Figure 3 It is a flowchart of the present invention; Figure 4 Schematic diagram of grasping key points (left) and grasping center points (right); Figure 5 To capture the detection network architecture diagram; Figure 6 It is a simplified schematic diagram of push strategy 1 when the camera is perpendicular to the plane of the material frame; Figure 7 It is a simplified schematic diagram of push strategy 2 when the camera is perpendicular to the plane of the frame; Figure 8 It is a simplified schematic diagram of the push strategy 3 when the camera is perpendicular to the plane of the material frame. The intelligent robot system for grasping small industrial parts includes: an operation module 1, a mobile platform module 2, a perception module 3 and a control module 4;

[0046] The operation module 1 and the control module 4 are both installed on the mobile platform module 2, and the perception module 3 is installed on the operation module 1. The operation module 1 is used to provide the function of grasping objects, and the mobile platform module 2 is used to execute the movement function of the intelligent robot. The perception module 3 is used for the positioning and mapping of the intelligent robot and the positioning and visual grasping algorithm of the target area. The control module 4 is used to process and manage related tasks of the operation of the intelligent robot.

[0047] The operation module 1 includes a mechanical arm and an electric gripper, and the mobile platform module 2 includes a quadruped bionic robot with twelve leg and foot joints.

[0048] The perception module 3 includes a laser radar, an inertial measurement unit and a depth camera; wherein the laser radar and the inertial measurement unit are used for positioning and mapping of the intelligent robot, and the depth camera is used for target area positioning and visual capture algorithm.

[0049] The control module 4 is used to coordinate the intelligent robot to execute various tasks, responsible for complex tasks such as visual processing, navigation decision-making, and high-level motion control, and schedules the motion control and signal acquisition of the underlying hardware through control instructions, playing the role of a bridge for coordination and information transmission between various modules.

[0050] According to the functional architecture, the intelligent robot system for grasping small industrial parts is divided into environment perception, data processing, and planning execution.

[0051] In this embodiment, as Figure 2 shown, in the environment perception part, the lidar collects scene point cloud data, the IMU (Inertial Measurement Unit) obtains the robot state information including data such as acceleration and angular velocity, and the depth camera obtains color images and depth images.

[0052] In the data processing part, it is mainly divided into two parts. One part is used to calculate the motion information of the mobile platform. It is necessary to process the scene data obtained by the lidar and fuse the IMU (Inertial Measurement Unit) data to generate a three-dimensional point cloud map of the environment and convert it into a two-dimensional grid map. Then, combined with the AprilTag code to assist in positioning the area where the part to be grasped is located, and determine the target pose that the mobile platform needs to move to. The other part is used to calculate the motion information of the robotic arm. It is necessary to process the original images obtained by the depth camera and use the visual grasping algorithm to obtain the grasping configuration information. Combined with the camera internal parameter information, the obtained grasping configuration information is converted to obtain the gripper target pose in the camera coordinate system, and then the target pose is converted through the result of hand-eye calibration to obtain the target pose in the robotic arm base coordinate system.

[0053] In the planning execution part, it is responsible for the motion planning and underlying control of the intelligent grasping robot. According to the pose information that the mobile platform and the operating device need to move to respectively obtained in the previous layer, a reasonable planning path is formed, and the planning instructions are converted into robot underlying control instructions and sent to the controllers corresponding to the quadruped robot, the robotic arm, and the gripper respectively to execute motion control.

[0054] A control method for an intelligent robot for grasping small industrial parts, including a robot pushing action pose estimation method and a multi-object grasping method combining pushing operations to assist grasping;

[0055] Among them, the robot pushing action pose estimation method includes the following steps:

[0056] S1. Obtain image data and screen target objects;

[0057] First, obtain the color image and the aligned depth image of the scene from the depth camera. Then, input the color image into an object detection network such as YOLOV5 to predict the approximate area range where each object is located, that is, obtain multiple bounding boxes containing single objects and their confidence scores. Next, take the center point coordinates of each bounding box as the centroid position of the corresponding object, and combine the Kernel Density Estimation (KDE) method to estimate the density of the area around each object. The formula is as follows:

[0058]

[0059] where \(x\) is the centroid coordinate of the target object, \(x_j\) is the centroid coordinate of the \(j\)-th object around the target object, \(K\) is the Gaussian kernel function, and \(h\) is the smoothing parameter. j is the centroid coordinate of the \(j\)-th object around the target object, \(K\) is the Gaussian kernel function, and \(h\) is the smoothing parameter.

[0060] Calculate the \(D\) value of each object to represent the density of the area around the object, and record it as set \(T\). Select the object corresponding to the minimum value in \(T\) as the target object to be grasped (if there are multiple identical minimum values, select the one with the highest bounding box confidence score), that is, screen out the possible isolated object with the lowest grasping space restriction degree. Crop the original color image according to the bounding box coordinates of the target object to obtain a color image patch containing only a single object. Use the sobel operator to perform edge detection on the color image patch to obtain the corresponding edge image patch. Finally, adjust the two image patches to the predefined fixed width and height dimensions and splice them in the channel dimension as the input data of the grasping pose detection network.

[0061] S2. The grasping pose detection network predicts the grasping parameters;

[0062] Referring to the grasping parameter configuration used by Kumra et al., the grasping is characterized as \(G=(x,y,w,\theta,q)\), where \((x,y)\) represents the coordinates of the grasping point in the pixel coordinate system, \(w\) represents the gripper width during grasping, \(\theta\) represents the plane rotation angle of grasping, and \(q\) is the quality score of each grasping. Additionally, based on the method proposed by Sun et al.

[16] proposed to use the grasping center point \(P\) c \(=(x,y)\) and the grasping key points \(P1=(x1,y1)\) and \(P2=(x2,y2)\) to determine the grasping representation \(g\), and these points are predicted through the heat map predicted by the grasping pose detection network, as Figure 4 shown.

[0063] The entire grasping pose detection network adopts an encoder-decoder architecture, as Figure 5As shown in the figure, the model structure refers to the DeeplabV3+ model commonly used in semantic segmentation tasks and modifies it by adding an additional output head to achieve pixel-level prediction. The input of the encoder is the color image patch and the edge image patch obtained from the previous step. Through the Residual Network (ResNet) module with dilated convolution and the Atrous Spatial Pyramid Pooling (ASPP) module, low-level features and high-level features are respectively extracted and fed into the decoder. In the decoder part, the low-level features and high-level features are further processed through convolution, combined with upsampling and splicing operations, and finally the predicted grasping center point heat map and the grasping key point heat map are output to achieve pixel-level regression tasks.

[0064] The model parameters are optimized according to the following loss function:

[0065] L = αL c + βL k

[0066] where L c and L k are the SmoothL1 losses of the grasping center point and the grasping key points respectively, and α and β are their respective weight factors.

[0067] From the grasping center point heat map and the grasping key point heat map, the grasping center point P c and the grasping key points P1 and P2 can be determined according to their maximum confidence values. Based on these points, the grasping representation G can be constructed. Among them, the coordinates (x, y) of the grasping points in the pixel coordinate system in G correspond to the point P c , the grasping width is determined in advance according to the type of the object to be grasped, and the plane rotation angle θ can be obtained based on the points P1 and P2. The formula is as follows:

[0068] θ = arctan2(-(y2 - y1), (x2 - x1)) + π / 2

[0069] where arctan2 is the function for calculating the arctangent.

[0070] Combining the above-obtained grasping representation G with the depth image information of the scene, the grasping parameters including position information and pose information can be obtained.

[0071] S3. Determine the primitive actions to be executed;

[0072] Collision detection is performed on the grasping parameters obtained in the previous step to ensure that the gripper does not collide with the bin or other objects when grasping the target object. The method of collision detection is to transform the point cloud of the simplified gripper model to the specific position of the scene point cloud according to the grasping parameters, and check whether there is a point cloud near the gripper model area to determine whether a collision occurs. If the detection result shows no collision, it means the grasping is feasible; if there is a collision, the grasping pose detection network is reused for prediction. If no feasible grasping scheme is found after three consecutive predictions, estimate the appropriate pushing action pose to adjust the positional relationship between objects in the scene, separate dense objects, and create a feasible operation space for subsequent grasping.

[0073] S4. Estimation of pushing action pose;

[0074] 1) Point cloud preprocessing and selection of the operation target area

[0075] First, convert the scene depth image obtained from the depth camera into a point cloud according to the camera internal parameters, and extract the point cloud of the area where the bin is located. Then, use the statistical filtering method to remove isolated points, and use the Random Sample Consensus (RANSAC) method to detect and segment the bottom surface of the bin, and screen to obtain the point cloud containing only objects. Then use the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to cluster the object point cloud, and extract the cluster with the most points as the target area for the pushing operation.

[0076] 2) Obtain the operation position of the pushing action

[0077] Referring to the definition of the pushing operation by Danielczuk et al., represent a single pushing action as where q = (x1, y1, z1) is the starting position of the pushing operation, r = (x2, y2, z2) is the ending position of the pushing operation, and both are in the camera coordinate system. The fingertip position of the two-finger gripper is the origin of the pushing operation. Except for special case descriptions, it is default that the two-finger gripper remains closed during the pushing operation.

[0078] According to the number of points contained in the target area, select different heuristic operations to push and separate the objects. When the number of points contained in the target area is large (the number of points is greater than 4000), use pushing operation 1 to separate the target object cluster. When the number of points contained in the target area is small (the number of points is less than 1000), use pushing operation 2 to separate the target object cluster. In other cases, use pushing operation 3 to separate the target object cluster.

[0079] Please refer to Figure 6, Pushing Strategy 1: Zigzag two-step pushing operation. Specifically, calculate the axis-aligned bounding box of the cluster of point clouds, obtain the coordinates of the four upper vertices of the axis-aligned bounding box and the coordinates of the center point of the axis-aligned bounding box. Replace the z-axis values of the four vertex coordinates with the z-axis value of the center point coordinate to obtain a new set of four vertices. Use the rectangular area formed by these four points as the candidate area for the pushing operation. Arbitrarily select one vertex A, and determine the other vertex B on the long side where it is located and the midpoint E on the corresponding opposite side of the long side. Take point A as the first starting position of the pushing operation, point E as the first ending position and the second starting position of the pushing operation, and point B as the second ending position of the pushing operation. Move from A to E, and then from E to B, and perform two pushing operations quickly and continuously to disperse the object.

[0080] Please refer to Figure 7 , Pushing Strategy 2: Combine the opening and closing degrees of freedom of the gripper for the pushing operation. Specifically, calculate the centroid O of the cluster of point clouds and the maximum distance D from the points included in the cluster of point clouds to the centroid. Construct a circle with O as the center and a radius of D, evenly sample 40 points at equal intervals on the circumference, then arbitrarily select two points to connect to form a line segment and calculate the number of points passed through by the line segment. Find the line segment that passes through the most points, and draw a perpendicular line segment AB with a length of 2D through the midpoint A of the line segment. Take the end point B and the end point A of the perpendicular line segment as the starting position and the ending position of the pushing operation respectively, and quickly open the gripper at the ending position A to separate the object.

[0081] Please refer to Figure 8 , Pushing Strategy 3: Push the object along the direction passing through the most objects. Specifically, calculate the centroid O of the cluster of point clouds and the maximum distance D from the points included in the cluster of point clouds to the centroid. Construct a line segment with O as the midpoint and a length of 2D, and rotate the line segment clockwise by 9 degrees around point O in turn. Finally, obtain 20 line segments as candidate pushing operation directions. Traverse these line segments, find the line segment AB that passes through the most points, and take the two end points A and B of the line segment as the starting position and the ending position of the pushing operation respectively to disperse the object.

[0082] S5. Execute primitive actions.

[0083] Convert the gripper target pose in the camera coordinate system corresponding to the feasible grasping operation or pushing operation obtained in the above steps to the base coordinate system of the robotic arm for controlling the movement of the robotic arm. Specifically, according to the relevant theory of robot coordinate transformation, the following formula holds:

[0084]

[0085] where is the transformation matrix from the base coordinate system of the robotic arm corresponding to the current camera view to the end coordinate system of the robotic arm, which can be calculated from the array of joint angles q read by the robotic arm controller and the forward kinematics of the robot; is the hand-eye calibration matrix.

[0086] Performing a transformation on yields:

[0087]

[0088] where, is the transformation matrix from the end coordinate system to the gripper coordinate system.

[0089] Combining the above formulas and further transforming gives:

[0090]

[0091] where, is the target pose command actually sent to the robotic arm controller.

[0092] After calculating the target pose perform trajectory planning using cubic spline interpolation and send it to the robot controller to control the movement of the robotic arm and its end effector, and execute the corresponding primitive actions. After the movement is completed, control the robotic arm and its end effector to return to the initial position and return to step 1.

[0093] The multi-object grasping method combining pushing operation to assist grasping is specifically as Figure 3 shown, including the following steps:

[0094] S1. Obtain image data according to the perception module and screen the target objects to obtain a color image block containing a single object and the corresponding edge image block;

[0095] S2. Send it into the grasping pose detection network to predict the planar grasping configuration composed of the grasping point and the grasping plane rotation angle parameter, and convert it into the grasping pose of the end gripper of the robotic arm in combination with the depth image;

[0096] S3. Perform collision detection on this grasping and judge the primitive actions to be executed according to the result; if there is no grasping collision, control the robot to move and execute the grasping action, otherwise re-predict using the grasping detection network; if no feasible grasping can be found after three consecutive predictions, use the point cloud data converted from the depth image as the input, estimate a reasonable pushing position of the robotic arm, and execute the pushing action to adjust the position relationship of the objects in the scene, separate the dense object clusters, and create a favorable space for subsequent grasping;

[0097] S4. Execute in a loop according to the above process until there are no objects in the bin.

[0098] Compared with the related art, the intelligent robot system and method for grasping small industrial parts provided by the present invention have the following beneficial effects:

[0099] (1) The intelligent grasping robot system proposed in the present invention, which is composed of a quadruped robot, a mechanical arm, an electric gripper, various sensors, a control module, etc., has a high degree of motion flexibility and fine operation ability, can adapt to complex and changeable industrial scenes, can complete complex mobile operation operations, and can be effectively applied to small industrial parts grasping tasks;

[0100] (2) The robot pushing motion pose estimation method proposed in the present invention can effectively separate densely packed objects, improve or create a feasible grasping space, reduce the probability of the end effector colliding with non-target objects or material frames during subsequent grasping of objects, and provide more favorable conditions for successful grasping;

[0101] (3) The multi-object grasping method combined with push operation assisted grasping proposed in the present invention can largely avoid the problem of grasping failure caused by collision during the grasping process due to the use of only grasping operations, such as multi-object stacking and occlusion, thereby improving the grasping success rate in unstructured scenarios.

[0102] Second embodiment

[0103] Please refer to Figures 9-11 Based on the intelligent robot system for grasping small industrial parts provided by the first embodiment of the present application, the second embodiment of the present application proposes another intelligent robot system for grasping small industrial parts. The second embodiment is only a preferred embodiment of the first embodiment, and the implementation of the second embodiment will not affect the independent implementation of the first embodiment.

[0104] Specifically, the difference of the intelligent robot system for grasping small industrial parts provided by the second embodiment of the present application is that the operating module 1 is rotatably connected to a rotating block 5, the rotating block 5 is rotatably connected to a rotating sleeve 6, the rotating sleeve 6 is installed with a mounting block 7, the mounting block 7 is installed with a toggle member 8, the toggle member 8 is used to toggle the workpiece in the material frame to change the clamping posture of the workpiece, the operating module 1 is installed with a driving member 9 for driving the rotating sleeve 6 to rotate, the operating module 1 is internally slidably connected to a sliding block 10, the sliding block 10 is fixedly connected to a connecting rod 11, one end of the connecting rod 11 passes through the middle of the rotating sleeve 6 and is installed with a grasping component 12, the grasping component 12 is used to grasp the workpiece, and the operating module 1 is internally installed with a pushing member 13, the pushing member 13 is fixedly connected to the sliding block 10, and is used to drive the sliding block 10 to move linearly to realize the feeding of the grasping component 12.

[0105] The shifting member 8 includes but is not limited to a shifting rod, a shifting block or a special-shaped shifting bar, and the installation method is fixed or detachable. It only needs to realize the shifting of the workpiece, and the size can be adjusted according to actual needs.

[0106] The driving member 9 includes a power member and a transmission member, wherein the power member includes but is not limited to an electric motor, a motor, and a transmission machine, and the transmission member includes but is not limited to a friction wheel, a belt and a pulley, a gear and a gear, a worm gear and a worm, a sprocket and a chain, and can drive the rotating sleeve 6 when the driving member 9 rotates.

[0107] The grasping assembly 12 includes but is not limited to a bilateral clamp, a three-axis clamp, and a four-axis clamp, and any one of them can realize the grasping function and is used to grasp the workpiece.

[0108] The pusher 13 includes but is not limited to an electric push rod, a linear motor, a hydraulic rod, and a reciprocating mechanical component, and any of them can drive the sliding block 10 to move linearly.

[0109] The operating module 1 is rotatably connected with a mounting sleeve 14, the sensing module 3 is mounted on the mounting sleeve 14, a connecting block 15 is mounted on the rotating block 5, and one end of the connecting block 15 is fixed on the mounting sleeve 14 to realize the rotation of the mounting sleeve 14 when the rotating block rotates.

[0110] The outer surface of the connecting rod 11 is rotatably connected with an auxiliary block 16, and a first docking piece 17 is fixedly connected to the auxiliary block 16. The rotating sleeve 6 is fixedly connected with a second docking piece 18, and the second docking piece 18 is used to cooperate with the first docking piece 17 to achieve docking between the rotating sleeve 6 and the auxiliary block 16. A guide rod 19 is fixedly connected to the auxiliary block 16, and a third docking piece 20 is installed at one end of the guide rod 19. A fourth docking piece 21 is installed on the rotating block 5, and the fourth docking piece 21 is used to cooperate with the third docking piece 20 to achieve docking between the guide rod 19 and the rotating block 5.

[0111] The connection between the first connection member 17 and the second connection member 18 includes, but is not limited to, a snap-on connection and a magnetic connection.

[0112] When the card connection is adopted, the first docking member 17 is provided with a card slot, and the second docking member 18 is provided with a card block corresponding to the card slot, and the two can realize transmission after docking;

[0113] When the magnetic attraction method is adopted, a magnetic block is provided on the first docking member 17, and another magnetic block is provided on the second docking member 18, and transmission can be achieved between the two docking. Preferably, the magnetic block is an electromagnetic block, which can be quickly separated by turning the power on and off, and the magnetic force can meet the requirements.

[0114] The first butt joint member 17 , the second butt joint member 18 and the third butt joint member 20 , the fourth butt joint member 21 may be of the same type.

[0115] During operation, the driving member 9 drives the rotating sleeve 6 to rotate, which can make the shifting member 8 move in a circle, and can shift the workpiece in the material frame to adjust the position of the workpiece;

[0116] The push of the push member 13 can drive the sliding block 10 to move to the left, so that the connecting rod 11 can move to the left, driving the grabbing assembly 12 to extend out to grab the workpiece;

[0117] By rotating the rotating sleeve 6, the posture of the workpiece in the material frame can be adjusted individually; by pushing the pushing member 13, the feeding of the grasping component 12 can be realized individually, so that the grasping component 12 can grasp the workpiece; when the pushing member 13 is pushing, the driving member 9 is also driving the toggle member 8 to move in a circle. At this time, the two will cooperate with each other, indirectly driving the installation sleeve 14 to rotate, so as to adjust the position of the perception module 3, so that the perception module 3 can perceive in all directions, provide better scene data acquisition, and facilitate subsequent work.

[0118] Compared with the related art, the intelligent robot system for grasping small industrial parts provided by the present invention has the following beneficial effects:

[0119] During the clamping operation, if the posture of the workpiece in the material frame is not good and the grasping component 12 is difficult to grasp, the operating module 1 is stretched and deformed to make the toggle member 8 extend into the material frame, and the driving member 9 drives the rotating sleeve 6 to rotate, thereby indirectly driving the toggle member 8 to move in a circle, so that the posture of the workpiece can be adjusted, and then the connecting rod 11 is driven to stretch by the pushing member 13, thereby driving the grasping component 12 to grasp the workpiece. When the pushing member 13 pushes, the auxiliary block 16 will move to the left, so that the first docking member 17 docks with the second docking member 18, and the guide rod 19 will also move to the left, so that the third docking member 20 docks with the fourth docking member 21. At this time, in conjunction with the rotation of the rotating sleeve 6, the auxiliary block 16 will rotate, thereby driving the rotating block 5 to rotate, and indirectly causing the mounting sleeve 14 to rotate to adjust the position of the sensing module 3, so that perception in different directions can be performed, thereby improving the comprehensiveness of perception.

[0120] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent robot system for grasping small industrial parts, characterized in that, include: Operation module, mobile platform module, perception module and control module; The operation module and the control module are both installed on the mobile platform module, and the perception module is installed on the operation module. The operation module is used to provide the function of grasping objects, and the mobile platform module is used to execute the movement function of the intelligent robot. The perception module is used for the positioning and mapping of the intelligent robot and the target area positioning and visual grasping algorithm. The control module is used to process and manage related tasks of the operation of the intelligent robot.

2. The intelligent robot system for grasping small industrial parts according to claim 1, characterized in that, The operation module includes a mechanical arm and an electric gripper, and the mobile platform module includes a four-legged bionic robot with twelve leg and foot joints.

3. The intelligent robot system for grasping small industrial parts according to claim 1, characterized in that, The perception module includes a laser radar, an inertial measurement unit and a depth camera; wherein the laser radar and the inertial measurement unit are used for positioning and mapping of the intelligent robot, and the depth camera is used for target area positioning and visual capture algorithms.

4. The intelligent robot system for grasping small industrial parts according to claim 1, wherein, The control module is used to coordinate the intelligent robot to perform various tasks. It is responsible for complex tasks such as visual processing, navigation decision-making, and high-level motion control. It also dispatches the motion control and signal acquisition of the underlying hardware through control instructions, and serves as a bridge for coordination and information transmission between various modules.

5. The intelligent robot system for grasping small industrial parts according to claim 1, characterized in that, According to the functional architecture, the intelligent robot system for grasping small industrial parts is divided into environmental perception, data processing, and planning execution.

6. The intelligent robot system for grasping small industrial parts according to claim 1, characterized in that, The operating module is rotatably connected to a rotating block, the rotating block is rotatably connected to a rotating sleeve, the rotating sleeve is equipped with a mounting block, the mounting block is equipped with a toggle piece, the toggle piece is used to toggle the workpiece in the material frame to change the clamping posture of the workpiece, the operating module is equipped with a driving piece for driving the rotating sleeve to rotate, the operating module is internally slidably connected to a sliding block, the sliding block is fixedly connected to a connecting rod, one end of the connecting rod passes through the middle of the rotating sleeve and is equipped with a grabbing assembly, the grabbing assembly is used to grab the workpiece, the operating module is internally equipped with a pushing piece, the pushing piece is fixedly connected to the sliding block, and is used to drive the sliding block to move linearly to achieve feeding of the grabbing assembly.

7. The intelligent robot system for grasping small industrial parts according to claim 6, characterized in that, The operating module is rotatably connected with a mounting sleeve, the sensing module is mounted on the mounting sleeve, a connecting block is mounted on the rotating block, and one end of the connecting block is fixed on the mounting sleeve to realize the rotation of the mounting sleeve when the rotating block rotates.

8. The intelligent robot system for grasping small industrial parts according to claim 6, characterized in that The outer surface of the connecting rod is rotatably connected to an auxiliary block, the auxiliary block is fixedly connected to a first docking piece, the rotating sleeve is fixedly connected to a second docking piece, the second docking piece is used to cooperate with the first docking piece to achieve docking between the rotating sleeve and the auxiliary block, the auxiliary block is fixedly connected to a guide rod, one end of the guide rod is installed with a third docking piece, the rotating block is installed with a fourth docking piece, the fourth docking piece is used to cooperate with the third docking piece to achieve docking between the guide rod and the rotating block.

9. A control method for an intelligent robot for grasping small industrial parts, characterized in that, It includes a robot pushing action pose estimation method and a multi-object grasping method combined with pushing operation assisted grasping; The robot pushing motion posture estimation method comprises the following steps: S1, obtain image data and screen target objects; S2, grasping posture detection network predicts grasping parameters; S3, determine the primitive action to be executed; S4. Estimate the pose of the pushing action; S5. Execute the primitive action.

10. The control method of the intelligent robot for grasping small industrial parts according to claim 9, characterized in that, The multi-object grasping method combined with pushing operation for assisting grasping includes the following steps: S1. Obtain image data according to the perception module and screen the target objects to obtain a color image patch containing a single object and the corresponding edge image patch; S2. Send it into the grasping pose detection network to predict the planar grasping configuration composed of the grasping point and the grasping plane rotation angle parameter, and convert it into the grasping pose of the end gripper of the robotic arm in combination with the depth image; S3. Perform collision detection on the grasping, and judge the primitive action to be executed according to the result; if there is no grasping collision, control the robot to move and execute the grasping action, otherwise use the grasping detection network to predict again; if no feasible grasping can be found after three consecutive predictions, use the point cloud data converted from the depth image as the input, estimate a reasonable pushing position of the robotic arm, execute the pushing action to adjust the positional relationship of the objects in the scene, separate the dense object clusters, and create a favorable space for subsequent grasping; S4. Execute in a loop according to the above process until there are no objects in the bin.

Images