•  
  •  
 

Journal of System Simulation

Heyu Li, 1. Beijing Complex Product Advanced Manufacturing Engineering Research Center, Beijing Simulation Center, Beijing 100854, China; ;
Zhilong Zhao, 1. Beijing Complex Product Advanced Manufacturing Engineering Research Center, Beijing Simulation Center, Beijing 100854, China; ;2. State Key Laboratory of Intelligent Manufacturing System Technology, Beijing Institute of Electronic System Engineering, Beijing 100854, China; ;3. Science and Technology on Space System Simulation Laboratory, Beijing Simulation Center, Beijing 100854, China;
Gu Lei, 1. Beijing Complex Product Advanced Manufacturing Engineering Research Center, Beijing Simulation Center, Beijing 100854, China; ;
Liqin Guo, 1. Beijing Complex Product Advanced Manufacturing Engineering Research Center, Beijing Simulation Center, Beijing 100854, China; ;2. State Key Laboratory of Intelligent Manufacturing System Technology, Beijing Institute of Electronic System Engineering, Beijing 100854, China; ;3. Science and Technology on Space System Simulation Laboratory, Beijing Simulation Center, Beijing 100854, China;
Zeng Bi, 1. Beijing Complex Product Advanced Manufacturing Engineering Research Center, Beijing Simulation Center, Beijing 100854, China; ;
Tingyu Lin, 1. Beijing Complex Product Advanced Manufacturing Engineering Research Center, Beijing Simulation Center, Beijing 100854, China; ;2. State Key Laboratory of Intelligent Manufacturing System Technology, Beijing Institute of Electronic System Engineering, Beijing 100854, China; ;3. Science and Technology on Space System Simulation Laboratory, Beijing Simulation Center, Beijing 100854, China;

Abstract

Abstract: Deep reinforcement learning continues to explore in the environment and adjusts the neural network parameters by the reward function. The actual production line can not be used as the trial and error environment for the algorithm, so there is not enough data. For that, this paper constructs a virtual robot arm simulation environment, including the robot arm and the object. The Deep Deterministic Policy Gradient (DDPG),in which the state variables and reward function are set,is trained by deep reinforcement learning algorithm in the simulation environment to realize the target of controlling the robot arm to move the gripper below the object. The new method using neural network can improve the adaptability of the control algorithm and shorten the debugging time. The simulation results show that in the environment constructed in this paper, the deep learning algorithm can converge in a shorter time and control the robot arm to achieve specific goals.

First Page

2452

Revised Date

2019-07-25

Last Page

2457

CLC

TP391

Recommended Citation

Li Heyu, Zhao Zhilong, Gu Lei, Guo Liqin, Zeng Bi, Lin Tingyu. Robot Arm Control Method Based on Deep Reinforcement Learning[J]. Journal of System Simulation, 2019, 31(11): 2452-2457.

DOI

10.16182/j.issn1004731x.joss.19-FZ0378

Download

Share

COinS