AUTHOR=Dong Ruyi , Du Junjie , Liu Yanan , Heidari Ali Asghar , Chen Huiling 

TITLE=An enhanced deep deterministic policy gradient algorithm for intelligent control of robotic arms

JOURNAL=Frontiers in Neuroinformatics

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neuroinformatics/articles/10.3389/fninf.2023.1096053

DOI=10.3389/fninf.2023.1096053

ISSN=1662-5196

ABSTRACT=Aiming at the poor robustness and adaptability of traditional control methods for different situation, the Deep Deterministic Policy Gradient (DDPG) algorithm is improved by designing a hybrid function that includes different rewards superimposed on each other. In addition, the experience replay mechanism of DDPG is also improved by a combination of priority sampling and uniform sampling to accelerate the DDPG’s convergence. Finally, a robotic arm simulation environment is built under the PyBullet platform, and the improved DDPG algorithm is trained with the simulated robotic arm interactively to form a control model, so as to achieve accurate control of the robotic arm motion. The experimental results show that the improved DDPG algorithm can converge in a shorter time, and the robotic arm can learn the control strategy to complete a specific task in the simulation environment, which improves the self-adaptability of the robotic arm.