Robot Arm Control Method of Moving Below Object Based on Deep Reinforcement Learning

Li, HeYu; Shi, Guoqiang; Xiao, Yingying; Zeng, Bi; Lin, Ting-Yu; Jia, ZhengXuan

doi:10.1007/978-981-15-1078-6_11

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The control strategies include fuzzy neural network, deep reinforcement learning, iterative learning and other intelligent algorithm control. The strong coupling and nonlinear dynamic characteristics of the manipulator with multi degree of freedom make the learning and verification of this problem a more complex problem [2,8,9,10,11,12]. In order to achieve high-precision position tracking, NGO et al [13] proposed a fuzzy neural network control system with robust self-adaption.…”

Section: Related Workmentioning

confidence: 99%

A Manipulator Control Method Based on Deep Deterministic Policy Gradient with Parameter Noise

Zhang¹,

Lei³

et al. 2021

Preprint

View full text Add to dashboard Cite

Focusing on the motion control problem of two link manipulator, a manipulator control approach based on deep deterministic policy gradient with parameter noise is proposed. Firstly, the manipulator simulation environment is built. And then the three deep reinforcement learning models named the deep deterministic policy gradient (DDPG), asynchronous advantage actor-critical (A3C) and distributed proximal policy optimization (DPPO) are established for training according to the target setting, state variables and reward & punishment mechanism of the environment model. Finally the motion control of two link manipulator is realized. After comparing and analyzing the three models, the DDPG approach based on parameter noise is proposed for further research to improve its applicability, so as to cut down the debugging time of the manipulator model and reach the goal smoothly. The experimental results indicate that the DDPG approach based on parameter noise can control the motion of two link manipulator effectively. The convergence speed of the control model is significantly promoted and the stability after convergence is improved. In comparison with the traditional control approach, the DDPG control approach based on parameter noise has higher efficiency and stronger applicability.

show abstract

Section: Related Workmentioning

confidence: 99%