Action training method of human-like multi-degree-of-freedom robot

Abstract

The invention discloses an action training method of a human-like multi-degree-of-freedom robot. The action training method comprises the following steps: 1, using optical equipment to recognize the bone data of a person whose action is captured; 2, mapping bone joint coordinates to a mathematic coordinate system, and calculating the included angle of each joint according to coordinate data; and 3, sending the angle data to corresponding motor controllers on the robot, which control rotating motors to restore the action of the person. The action training method has the beneficial effects that the action accuracy and completeness of the multi-degree-of-freedom robot are improved, and the action training method can be widely applied to the fields of intelligent robots, logistic robots, warehouse management robots, cargo handling robots, bar code robots, children robots, tourist guide manner robots, housekeeping robots, acting entertainment robots, humanoid robots, construction robots and the like.

Description

technical field [0001] The invention relates to an action training method, in particular to an action training method for a humanoid multi-degree-of-freedom robot. Background technique [0002] With the continuous improvement of people's living standards and the continuous advancement of robot technology, robots are entering the lives of ordinary people. In order for a robot to truly behave more intelligently, it must be given the ability to move, see, hear and think. Among them, the movement of multi-degree-of-freedom robots is particularly troublesome to deal with. Taking a robot with 22 degrees of freedom (fixed lower body) as an example, the shoulder joint is the most difficult to deal with, because the shoulder joint of a real person can move in three directions. The robot is constrained by the size of the motor. Generally, the shoulder joint has only two degrees of freedom, and the third freedom is moved to the upper arm. This will cause motion distortion regardless ...

AI Technical Summary

Problems solved by technology

The robot is constrained by the size of the motor. Generally, the shoulder joint has only two degrees of freedom, and the third freedom is moved to the upper arm. This will cause motion distortion regardless of whether it is simulated in the simulator or obtained through motion capture. Coupled with the restriction of the motor speed, this directly reduces the completion of the robot's movements

Images