Analysis on Deep Reinforcement Learning in Industrial Robotic Arm

被引:3
作者
Guan, Hengyue [1 ]
机构
[1] Shandong Univ, Jinan, Shandong, Peoples R China
来源
2020 INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTING AND HUMAN-COMPUTER INTERACTION (ICHCI 2020) | 2020年
关键词
Deep reinforcement learning; robotic arm; manipulation; DQN; DDPG;
D O I
10.1109/ICHCI51889.2020.00094
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Deep reinforcement learning is a combination of reinforcement learning and deep learning. It allows the robot to learn new tasks on its own. In recent years, many studies have applied deep reinforcement learning algorithms to the manipulation of robotic arms, and have achieved excellent results. This article described the basic knowledge of deep reinforcement learning and analyzed the current problems faced by industrial robotic arms. By reviewing the main research that researchers have applied deep reinforcement learning algorithms to the field of manipulator operation in recent years and the development of related deep reinforcement learning algorithms. It concluded that how deep reinforcement learning can solve the problems faced by industrial robotic arms. Finally, this article referred to the challenges faced by the application of deep reinforcement learning and its application in the field of industrial robotic arms and then made a detailed analysis and explanation.
引用
收藏
页码:426 / 430
页数:5
相关论文
共 32 条
[1]  
Akkaya I., 2019, CoRR
[2]  
[Anonymous], 2015, Adaptive Control Processes-A Guided Tour
[3]  
Biao Hu, 2019, 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO), P1097, DOI 10.1109/ROBIO49542.2019.8961651
[4]  
[多南讯 Duo Nanxun], 2019, [机器人, Robot], V41, P276
[5]  
Everett M, 2018, IEEE INT C INT ROBOT, P3052, DOI 10.1109/IROS.2018.8593871
[6]  
Finn C, 2017, PR MACH LEARN RES, V70
[7]  
Gautam R, 2017, INT RES J ENG TECHNO, V4
[8]  
Haarnoja T, 2017, PR MACH LEARN RES, V70
[9]  
Haarnoja T, 2018, IEEE INT CONF ROBOT, P6244
[10]  
HINTON G. E, 2012, Lecture Notes in Computer Science, P599, DOI [DOI 10.1007/978-3-642-35289-8-32, DOI 10.1007/978-3-642, DOI 10.1007/978-3-642-35289-832]