Intelligent detection and grabbing method based on ROS platform

An intelligent detection and platform technology, applied in the direction of program-controlled manipulators, manufacturing tools, chucks, etc., can solve the problems of long target detection time and low grasping accuracy, and achieve the effect of shortening the estimation time and improving the detection speed.

CN111482967AActive Publication Date: 2020-08-04HEBEI UNIV OF TECH
9 Cites 3 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2020-08-04

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses an intelligent detection and grabbing method based on an ROS platform. According to the method, information collection and processing are carried out on a working scene by utilizing somatosensory peripheral peripherals and an ROS system, a Faster RCNN network model is introduced, and a target is searched through the network model, so that the target detection speed is increased, and the grabbing point estimation time is shortened; and a grabbing process is simulated in advance through a simulation platform so as to avoid grabbing collision caused by errors, and a mechanical arm is controlled to execute a grabbing task according to a simulation result. According to the method, a target object is detected, the total time of grabbing points is estimated to be within the range of [0.074, 0.263] seconds, and the total grabbing success rate is about 87% through 20 times of grabbing statistics on five objects.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of control and motion planning of a mechanical arm, and specifically relates to an intelligent detection and grasping method based on a ROS platform, and relates to a method for grasping an object by a mechanical arm, which can realize object recognition and find out the best grasping method. Grips for grabbing. Background technique

[0002] The control and grabbing of existing manipulators often use teaching methods, such as Chinese Patent Publication No. CN108655026A, titled "A System and Method for Rapid Teaching and Sorting of Robots". Although this teaching method saves some programming links, It has the following disadvantages: the accuracy is completely determined by the visual inspection of the teaching operator, and it is difficult to obtain satisfactory results for the messy path teaching online programming, and accidents are prone to occur during the teaching process, ranging from crashing the equipment to ...

Examples

Embodiment Construction

[0018] The present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments.

[0019] The present invention provides a kind of intelligent detection and grasping method (abbreviation method) based on ROS platform, this method adopts following steps to realize:

[0020] Step 1: Install Kinect somatosensory peripherals through the peripheral fixing frame, place them on the top or side of the robotic arm, and make the robotic arm within the shooting field of view of its camera for easy shooting, and place the objects to be grasped on the platform Installed in front of the robot arm.

[0021] Step 2: Configure the scene realized by this method, connect Kinect somatosensory peripherals, a desktop computer, a mobile notebook computer and the robotic arm for communication. The specific method is to connect the notebook computer to the Internet using WIFI, and connect It is set as the ROS master server, assuming its IP address ...