Object rotation detection method suitable for mechanical hand at-hand operation

A target rotation and detection method technology, applied in the field of robotics, can solve problems such as complex visual processing algorithms, unfavorable software and hardware integration of robot control systems, and easy failure of rotation detection methods, so as to improve capabilities and avoid operational errors.

Active Publication Date: 2020-09-01
HARBIN INST OF TECH
View PDF23 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The vision processing algorithm of this type of method is usually relatively complicated. In order to ensure the real-time detection, a special processor is required to implement the algorithm, which is not conducive to the software and hardware integration of the robot control system; in addition, when the vision is occluded, this type of rotation detection method Highly prone to failure; therefore, it is difficult for the vision sensor based rotation detection method to be practically applied in the process of detecting the rotation of the target in the robot
In addition, the device for detecting and controlling the rotational position of a rotating object with the publication number CN207884454U has a large structure and cannot be installed on the manipulator, and the proposed detection method can only be realized by relying on the device, so it cannot be applied to the manipulator. Object rotation detection while grabbing an object
Publication number CN106796118A is a sensor assembly for non-contact detection of the rotation angle of a rotating member. The detection principle of the proposed method is the eddy current effect. This method can only be used for the rotation detection of metal targets, and cannot completely cover all the working targets of the robot.
The sensor assembly with the publication number CN106796119A used to detect the rotation angle of the rotating member without contact is also based on the eddy current effect principle to detect the rotation of the metal target, which cannot meet the rotation detection requirements of different material targets

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Object rotation detection method suitable for mechanical hand at-hand operation
  • Object rotation detection method suitable for mechanical hand at-hand operation
  • Object rotation detection method suitable for mechanical hand at-hand operation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Such as figure 1 As shown, the target rotation detection method suitable for manipulator in-hand operation is suitable for robot target grasping and target manipulation, especially the rotation detection of the operating target after the manipulator grabs the target. The systems involved in the rotation detection of the job target, as attached figure 2 As shown, it includes a manipulator 1 , a manipulator 2 , a force / torque sensor 3 and an operation target 4 .

[0029] The robotic arm 1 described above is a multi-axis robotic arm with common path planning functions.

[0030] The manipulator 2 is a two-finger manipulator and can perform online posture adjustment. The manipulator can be installed at the end of the manipulator 1 , and cooperate with the manipulator 1 to grasp the work object 4 .

[0031] The force / torque sensor 3 can be integrated at the fingertip of the manipulator 2, and has the ability to detect three-dimensional force and three-dimensional torque. ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides an object rotation detection method suitable for mechanical hand at-hand operation. The method includes the steps that a detection system is calibrated and initialized; 2, the initial coordinate section and the initial rotation radius section of the mass center of an operating object under a mechanical hand coordinate system are calculated; 3, a force / torque sensor is used for detecting the force bearing state of the operating object in real time, the condition where the operating object is located at the moment is judged according to the detection result, if the force / torque sensor is in non-pulse-fluctuation output, object rotation detection is carried out with a pure-gravity condition rotation detection method, and if the output value of the force / torque sensor isin pulse fluctuation, object rotation detection is carried out with an external-collision condition rotation detection method; and 4, after a robot completes rotation detection of the operating object in a current state, the step 3 is repeated until the robot completes operating tasks on the operating object. The perception and operation capacity of the robot for unknown objects can be enhanced.

Description

technical field [0001] The invention relates to a method for detecting target rotation, in particular to a method for detecting target rotation suitable for hand-operated manipulators, and belongs to the technical field of robots. Background technique [0002] In recent years, the application scenarios of robots have become more and more extensive, and the requirements for the robot's target manipulation capabilities have become higher and higher, especially the robot's target autonomous grasping and dexterous manipulation capabilities. In order to successfully complete the task, after the robot grabs the target, the target in hand must not rotate accidentally, otherwise it is easy to cause the pose of the target to change or even the target to fall, which will cause the task of the robot to fail. Therefore, for robots, the ability to detect target rotation at hand is of great significance for successfully completing target tasks. [0003] The on-hand operation of the opera...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): B25J9/16B25J19/02
CPCB25J9/1661B25J9/1615B25J19/02
Inventor 臧希喆王超张学贺刘刚峰董惠娟
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products