Efficient mechanical arm grabbing deep reinforcement learning reward training method and system

Abstract

The invention discloses an efficient mechanical arm grabbing deep reinforcement learning reward training method and system, and relates to the technical field of machine learning. A depth camera is used for identifying a target object and a mechanical arm tail end, the sight distance between the center of a mechanical arm tail end actuator and the center of the target object is calculated, and the distance is returned to a computer as a basis for judging whether a mechanical arm can grab the target object or not. Every time the mechanical arm tail end actuator tents, the computer takes the moving distance of the mechanical arm tail end actuator relative to the object, the moving step number of a mechanical arm, the sum of the rotating angles of steering engines of all degrees of freedom of the mechanical arm and the weighted sum of whether the target object is successfully grabbed or not as a reward mechanism of a DDPG depth deterministic strategy gradient network. The end-to-end training process is completed by using a DDPG. The problems that existing mechanical arm control is poor in action coherence and not coordinated are solved.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to an efficient method and system for rewarding training of deep reinforcement learning for manipulator grasping. Background technique [0002] With the development of artificial intelligence and robotics, the use of robotic arms is becoming more and more abundant. It acts as the arm of a robot just like our arms. How to use the robotic arm to accurately grasp objects has become one of the key issues in the development of robot technology. At present, most of the popular kinematics and inverse kinematics methods are used for precise grasping of robotic arms. Accurate grasping is achieved by solving kinematics inverse solutions. This method needs to consider solvability, that is, consider no solution, multiple solutions, etc. In this case, the calculation is complex and time-consuming. Another relatively novel way is to make the robot have its own soul through rein...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide an efficient manipulator grasping depth reinforcement learning reward training method and system, which improves the problems of poor coherence and uncoordination of the existing manipulator control.

Images