Control method for robot to grab object based on coordinated operation of hand, eyes and arm

Abstract

The invention provides a control method for a robot to grab an object based on the coordinated operation of a hand, eyes and an arm. The control method comprises the steps that relevant information of the object is obtained through vision, and a grabbing mode is established; a grabbing position is determined, and then movement of the mechanical arm is planned according to the grabbing pose of the hand; and finally, the hand and the mechanical arm are controlled to act according to a planned curve to achieve grabbing of the object. According to the control method, the hand, the eyes and the arm can be coordinated in true sense, so that the grabbing action is made smoother and more accurate, and the control method has fault tolerance to a certain extent.

Description

technical field [0001] The invention relates to a control method for a robot to grab an object, in particular to a control method for a robot to grab an object based on the coordinated operation of hands, eyes, and arms. The robot's hands, eyes, and arms are coordinated to make the grabbing operation smoother and more efficient. precise. Background technique [0002] The current robots are more and more widely used and more flexible. They are not limited to the movement and simple self-adaptation of fixed action paths, but are developing towards intelligence. Intelligence requires robots to have the ability to recognize and reason, and to make judgments and decisions. [0003] However, traditional robots have shortcomings such as poor flexibility, low efficiency, and inaccurate force control. Moreover, the existing robot control is limited to vision-based manipulator control (Mohebbi A, Keshmiri M, Xie W F.An eye-in-handstereo visual servoing for tracking and catching movi...

AI Technical Summary

Problems solved by technology

[0003] However, traditional robots have disadvantages such as poor flexibility, low efficiency, and inaccurate force control.

Moreover, the existing robot control is limited to vision-based manipulator control (Mohebbi A, Keshmiri M, Xie W F.An eye-in-handstereo visual servoing for tracking and catching moving objects[C] / / ControlConference(CCC),2014 33rd Chinese.IEEE,2014:8570-8577.) or hand and arm control (HuangM B, Huang H P, Cheng C C, et al. Efficient grasp synthesis and control strategy for robot hand-arm system[C] / / Automation Science and Engineering (CASE), 2015IEEE International Conference on. IEEE, 2015:1256-1257.)

In the current robot system including manipulator, manipulator and vision, the vision system is only used for the positioning of the operation target (Cheon S, Ryu K, OhY. Object manipulation using robot arm-hand system[C] / / 2013 10th InternationalConference on Ubiquitous Robots and Ambient Intelligence (URAI).2013.), but did not really combine the hands, eyes, and arms for movement coordination

Images