Manipulator control method, control device, terminal equipment and readable storage medium
A control method and manipulator technology, applied in the field of robotics, can solve the problems of time-consuming, inability to quickly determine the grasping posture, etc., and achieve the effect of rapid grasping posture
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0032] The following describes the manipulator control method provided in Embodiment 1 of the present application, please refer to the attached figure 1 , the control method includes:
[0033] In step S101, the center of gravity position information of the object to be captured is obtained, and the point cloud data of the captured scene is obtained, wherein the captured scene is a scene including the object to be captured;
[0034] In Embodiment 1 of the present application, it is first necessary to obtain the center of gravity position information of the object to be captured and the point cloud data of the above-mentioned captured scene.
[0035] Among them, the position information of the center of gravity of the object to be grasped can be determined through manual experiments in advance. However, for objects with relatively uniform mass distribution, the position information of the center of gravity can also be directly determined. For example, for a cuboid with uniform d...
Embodiment 2
[0059] Another manipulator control method provided in Embodiment 2 of the present application is described below, please refer to the attached image 3 , the method includes:
[0060] In step S301, the center of gravity position information of the object to be captured is obtained, and the point cloud data of the captured scene is obtained, wherein the captured scene is a scene including the object to be captured;
[0061] In step S302, based on the above-mentioned point cloud data of the captured scene, identify each point cloud point belonging to the object to be captured in the point cloud data, and determine the object to be captured according to each point cloud point belonging to the edge Get the three-dimensional size information of the object;
[0062] In step S303, the above-mentioned three-dimensional size information and the above-mentioned center of gravity position information are input into the pre-trained first neural network model to obtain the grasping postur...
Embodiment 3
[0073] Embodiment 3 of the present application provides a manipulator control device. For ease of description, only the relevant parts of the application are shown, such as Figure 4 As shown, the control device 400 includes:
[0074] The information acquisition module 401 is configured to acquire the position information of the center of gravity of the object to be captured, and acquire the point cloud data of the captured scene, wherein the captured scene is a scene including the above-mentioned object to be captured;
[0075] The size determining module 402 is configured to identify each point cloud point belonging to the edge of the object to be captured in the above point cloud data based on the point cloud data of the above captured scene, and determine the above mentioned point cloud point according to each point cloud point belonging to the above edge The three-dimensional size information of the object to be captured;
[0076] The posture determination module 403 is...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More