@inproceedings{7a38e277b3444507bb17893e5ba5946c,
title = "Reinforcement Learning Control for Robot Arm Grasping Based on Improved DDPG",
abstract = "Although the traditional robot arm grasping control has high control accuracy, its price is based on high-precision hardware and lacks flexibility. In order to achieve high control accuracy and flexibility on a relatively inexpensive robot arm. This paper proposes an improved DDPG (Deep Deterministic Policy Gradient) reinforcement learning algorithm to control the gripping of a robot arm. First, build a simulation environment for a six-DOF (six-degree-of-freedom) manipulator with a gripper in ROS (Robot Operating System). Then, aiming at the shortcomings of traditional DDPG rewards, research and design a composite reward function. Aiming at the problem of low sampling efficiency in the free exploration of the robot arm, a batch of teaching data was added to the experience replay pool to improve learning efficiency. The simulation experiment results show that under the same number of episode of training. The improved DDPG grasping control algorithm has significantly improved the grasping success rate. The grasping success rate after comprehensive improvement reaches 70%, which is higher than the 36% level of unimproved DDPG.",
keywords = "DDPG, Demonstration, Reward Function, Six-DOF Arm Robot",
author = "Guangjun Qi and Yuan Li",
note = "Publisher Copyright: {\textcopyright} 2021 Technical Committee on Control Theory, Chinese Association of Automation.; 40th Chinese Control Conference, CCC 2021 ; Conference date: 26-07-2021 Through 28-07-2021",
year = "2021",
month = jul,
day = "26",
doi = "10.23919/CCC52363.2021.9550413",
language = "English",
series = "Chinese Control Conference, CCC",
publisher = "IEEE Computer Society",
pages = "4132--4137",
editor = "Chen Peng and Jian Sun",
booktitle = "Proceedings of the 40th Chinese Control Conference, CCC 2021",
address = "United States",
}