Industrial mechanical arm automatic control method based on deep reinforcement learning

Abstract

The invention relates to an industrial mechanical arm automatic control method based on deep reinforcement learning. The industrial mechanical arm automatic control method based on deep reinforcementlearning includes the steps: constructing a deep reinforcement learning model, constructing output interference, establishing a reward rt calculation model, constructing a simulation environment, accumulating an experience pool, training a deep reinforcement learning neural network, and controlling an industrial mechanical arm to move in reality by means of the trained deep reinforcement learningmodel. By adding into the deep reinforcement learning network, the industrial mechanical arm automatic control method based on deep reinforcement learning can solve the automatic control problem of the industrial mechanical arm in an complicated environment, so as to complete automatic control of the mechanical arm, and the operating speed and the accuracy of the industrial mechanical arm are highafter completion of training.

Description

technical field [0001] The invention belongs to the technical field of reinforcement learning algorithms, and in particular relates to an automatic control method of an industrial manipulator based on deep reinforcement learning. Background technique [0002] Compared with manpower, industrial robotic arms can complete some simple, repetitive and cumbersome operations more efficiently. While greatly improving production efficiency, it can also reduce labor costs and labor intensity, while ensuring production quality. Reduce the probability of human accidents. In some harsh environments, such as high temperature, high pressure, low temperature, low pressure, dust, flammable, explosive, etc., it is of great significance to replace manual operations with robotic arms, which can prevent manual accidents caused by negligent operations. [0003] The motion solution process of the robotic arm is to first obtain the pose information of the grasping target, then obtain its own pose ...

Images