Volume 39, Number 5, October 2021
|Page(s)||1057 - 1063|
|Published online||14 December 2021|
Robotic arm reinforcement learning control method based on autonomous visual perception
School of Computer, Hubei University of Arts and Science, Xiangyang 441053, China
2 School of Computer, Northwestern Polytechnical University, Xi'an 710129, China
The traditional robotic arm control methods are often based on artificially preset fixed trajectories to control them to complete specific tasks, which rely on accurate environmental models, and the control process lacks the ability of self-adaptability. Aiming at the above problems, we proposed an end-to-end robotic arm intelligent control method based on the combination of machine vision and reinforcement learning. The visual perception uses the YOLO algorithm, and the strategy control module uses the DDPG reinforcement learning algorithm, which enables the robotic arm to learn autonomous control strategies in a complex environment. Otherwise, we used imitation learning and hindsight experience replay algorithm during the training process, which accelerated the learning process of the robotic arm. The experimental results show that the algorithm can converge in a shorter time, and it has excellent performance in autonomously perceiving the target position and overall strategy control in the simulation environment.
Key words: machine vision / reinforcement learning / imitation learning / system simulation / intelligent control
关键字 : 机器视觉 / 强化学习 / 模仿学习 / 系统仿真 / 智能控制
© 2021 Journal of Northwestern Polytechnical University. All rights reserved.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.